SPSSX Discussion

digest e-mail coming as garbled mess...

Classic

List

Threaded

1 message

Koch, Erin C.

digest e-mail coming as garbled mess...

I recently signed up to receive the SPSS-X listserve e-mails in digest form (too many e-mails a day). Unfortunately, what I'm getting are the garbled messages below... Any way to fix this?

Thanks,
Erin

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Automatic digest processor
Sent: Saturday, June 30, 2012 12:01 AM
To: Recipients of SPSSX-L digests
Subject: SPSSX-L Digest - 28 Jun 2012 to 29 Jun 2012 (#2012-180)

There are 33 messages totalling 5008 lines in this issue.

Topics of the day:

1. IBM SPSS Questions (3)
2. SPSS Database Capacity (6)
3. Converting Fortran to SPSS (9)
4. odds ratio to chi square conversion (2)
5. Spss Syntax select all values in a variable? (7)
6. Importing excel (3)
7. Offset in GEE means contrasts? (2)
8. Tree analysis failure

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

----------------------------------------------------------------------

Date: Fri, 29 Jun 2012 16:37:12 +0800
From: Eins Bernardo <[hidden email]>
Subject: IBM SPSS Questions

--1923299080-1311176581-1340959032=:86552
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable

Three questions for IBM SPSS personnel or others:=0A=0A=0A=0A1. Any forum o=
n modeler/clementine?=0A2. Do you have matrix showing the comparison of cap=
abilities/features of AMOS across versions?=0A3. Any forum on AMOS?=0A=0ATh=
ank you.=0AEins
--1923299080-1311176581-1340959032=:86552
Content-Type: text/html; charset=utf-8
Content-Transfer-Encoding: quoted-printable

<html><body><div style=3D"color:#000; background-color:#fff; font-family:ti=
mes new roman, new york, times, serif;font-size:12pt"><div><span style=3D"f=
ont-size: 12pt; ">Three questions for IBM SPSS personnel or others:</span><=
br></div><div style=3D"font-size: 12pt; font-family: 'times new roman', 'ne=
w york', times, serif; "><div style=3D"font-size: 12pt; font-family: 'times=
new roman', 'new york', times, serif; "><div id=3D"yiv1658673517"><div sty=
le=3D"color: rgb(0, 0, 0); background-color: rgb(255, 255, 255); font-size:=
12pt; font-family: 'times new roman', 'new york', times, serif; "><div><br=
></div><div>1. Any forum on modeler/clementine?</div><div>2. Do you have ma=
trix showing the comparison of capabilities/features of AMOS across version=
s?</div><div>3. Any forum on AMOS?</div><div><br></div><div>Thank you.</div=
><div>Eins</div></div></div><br><br> </div> </div> </div></body></html>
--1923299080-1311176581-1340959032=:86552--

------------------------------

Date: Fri, 29 Jun 2012 03:09:07 -0700
From: Albert-Jan Roskam <[hidden email]>
Subject: Re: SPSS Database Capacity

--2119556593-359084761-1340964547=:10469
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

Hi, =0A=0A=0ASee the line "How many variables and cases can SPSS for window=
s handle?"=A0 on http://www.spsstools.net/FAQ.htm Not sure what the differe=
nces are when on a 64 bit architecture.=0A=0A=A0=0ARegards,=0AAlbert-Jan=0A=
=0A=0A~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~=
~=0AAll right, but apart from the sanitation, the medicine, education, wine=
, public order, irrigation, roads, a =0Afresh water system, and public heal=
th, what have the Romans ever done for us?=0A~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~=
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~=A0=0A=0A=0A>______________________=
__________=0A> From: David Marso <[hidden email]>=0A>To: SPSSX-L@LIS=
TSERV.UGA.EDU =0A>Sent: Friday, June 29, 2012 5:56 AM=0A>Subject: Re: [SPSS=
X-L] SPSS Database Capacity=0A> =0A>Hi Jon,=0A>Please (when you have a mome=
nt) restate the actual *ABSOLUTE* max cases X=0A>max vars for both 32 bit a=
nd 64 bits maybe even 132 bit systems just for the=0A>hell of it=A0 (assumi=
ng infinite disk space and RAM).=A0 Would love a core dump=0A>of the theory=
.=0A>=0A>Jon K Peck wrote=0A>>=0A>> 1.5M records is not a large file by SPS=
S standards.=0A>>=0A>> Jon Peck (no "h") aka Kim=0A>> Senior Software Engin=
eer, IBM=0A>> peck@.ibm=0A>> new phone: 720-342-5621=0A>>=0A>>=0A>>=0A>>=0A=
>> From:=A0 btafoya <btafoya@>=0A>> To:=A0 =A0 SPSSX-L@.uga=0A>> Da=
te:=A0 06/26/2012 08:39 PM=0A>> Subject:=A0 =A0 =A0 =A0 [SPSSX-L] SPSS Dat=
abase Capacity=0A>> Sent by:=A0 =A0 =A0 =A0 "SPSSX(r) Discussion" <SPSSX=
-L@.uga>=0A>>=0A>>=0A>>=0A>> I have a population of 1.5 Million records =
that I want to use in SPSS.=0A>> Will=0A>> it work? What platform will I ne=
ed to handle something like this? I will=0A>> be=0A>> taking random samples=
but will need to get descriptive statistics from the=0A>> entire populatio=
n.=0A>>=0A>> --=0A>> View this message in context:=0A>> http://spssx-discus=
sion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html=0A>>=0A>> =
Sent from the SPSSX Discussion mailing list archive at Nabble.com.=0A>>=0A>=
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=0A>> To m=
anage your subscription to SPSSX-L, send a message to=0A>> LISTSERV@.UGA (n=
ot to SPSSX-L), with no body text except the=0A>> command. To leave the lis=
t, send the command=0A>> SIGNOFF SPSSX-L=0A>> For a list of commands to man=
age subscriptions, send the command=0A>> INFO REFCARD=0A>>=0A>=0A>=0A>--=0A=
>View this message in context: http://spssx-discussion.1045642.n5.nabble.co=
m/SPSS-Database-Capacity-tp5713809p5713886.html=0A>Sent from the SPSSX Disc=
ussion mailing list archive at Nabble.com.=0A>=0A>=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=0A>To manage your subscription to S=
PSSX-L, send a message to=0A>[hidden email] (not to SPSSX-L), wi=
th no body text except the=0A>command. To leave the list, send the command=
=0A>SIGNOFF SPSSX-L=0A>For a list of commands to manage subscriptions, send=
the command=0A>INFO REFCARD=0A>=0A>=0A>
--2119556593-359084761-1340964547=:10469
Content-Type: text/html; charset=iso-8859-1
Content-Transfer-Encoding: quoted-printable

<html><body><div style=3D"color:#000; background-color:#fff; font-family:ti=
mes new roman, new york, times, serif;font-size:12pt"><div><span>Hi, <br></=
span></div><div><span><br></span></div><div><span>See the line "How many va=
riables and cases can SPSS for windows handle?"  on http://www.spsstoo=
ls.net/FAQ.htm</span> Not sure what the differences are when on a 64 bit ar=
chitecture.<br></div><div> </div><div>Regards,<br>Albert-Jan<br><br></=
div><div>~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~=
~~~~<br>All right, but apart from the sanitation, the medicine, education, =
wine, public order, irrigation, roads, a <br>fresh water system, and public=
health, what have the Romans ever done for us?<br>~~~~~~~~~~~~~~~~~~~~~~~~=
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ <br> <blockquote style=
=3D"border-left: 2px solid rgb(16, 16, 255); margin-left: 5px; margin-top: =
5px; padding-left: 5px;"> <div style=3D"font-family: times new roman, new
york, times, serif; font-size: 12pt;"> <div style=3D"font-family: times ne=
w roman, new york, times, serif; font-size: 12pt;"> <div dir=3D"ltr"> <font=
face=3D"Arial" size=3D"2"> <hr size=3D"1"> <b><span style=3D"font-weight:=
bold;">From:</span></b> David Marso <[hidden email]><br> <b><s=
pan style=3D"font-weight: bold;">To:</span></b> [hidden email] <b=
r> <b><span style=3D"font-weight: bold;">Sent:</span></b> Friday, June 29, =
2012 5:56 AM<br> <b><span style=3D"font-weight: bold;">Subject:</span></b> =
Re: [SPSSX-L] SPSS Database Capacity<br> </font> </div> <br>=0AHi Jon,<br>P=
lease (when you have a moment) restate the actual *ABSOLUTE* max cases X<br=
>max vars for both 32 bit and 64 bits maybe even 132 bit systems just for t=
he<br>hell of it  (assuming infinite disk space and RAM).  Would =
love a core dump<br>of the theory.<br><br>Jon K Peck wrote<br>><br>> =
1.5M records is not a large file by SPSS standards.<br>><br>> Jon Pec=
k (no "h") aka Kim<br>> Senior Software Engineer, IBM<br>> peck@.ibm<=
br>> new phone: 720-342-5621<br>><br>><br>><br>><br>> Fro=
m:  btafoya &lt;btafoya@&gt;<br>> To:    SPSSX-=
L@.uga<br>> Date:  06/26/2012 08:39 PM<br>> Subject:  &nbs=
p;     [SPSSX-L] SPSS Database Capacity<br>> Sent by:  &n=
bsp;     "SPSSX(r) Discussion" &lt;SPSSX-L@.uga&gt;<br>&g=
t;<br>><br>><br>> I have a population of 1.5 Million records that =
I want to use in SPSS.<br>> Will<br>> it work?
What platform will I need to handle something like this? I will<br>> be=
<br>> taking random samples but will need to get descriptive statistics =
from the<br>> entire population.<br>><br>> --<br>> View this me=
ssage in context:<br>> http://spssx-discussion.1045642.n5.nabble.com/SPS=
S-Database-Capacity-tp5713809.html<br>><br>> Sent from the SPSSX Disc=
ussion mailing list archive at <a target=3D"_blank" href=3D"http://nabble.c=
om/">Nabble.com</a>.<br>><br>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D<br>> To manage your subscription to SPSSX-L,=
send a message to<br>> LISTSERV@.UGA (not to SPSSX-L), with no body tex=
t except the<br>> command. To leave the list, send the command<br>> S=
IGNOFF SPSSX-L<br>> For a list of commands to manage subscriptions, send=
the command<br>> INFO REFCARD<br>><br><br><br>--<br>View this messag=
e in context: http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-C=
apacity-tp5713809p5713886.html<br>Sent
from the SPSSX Discussion mailing list archive at Nabble.com.<br><br>=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D<br>To manage y=
our subscription to SPSSX-L, send a message to<br><a ymailto=3D"mailto:LIST=
[hidden email]" href=3D"mailto:[hidden email]">LISTSERV@L=
ISTSERV.UGA.EDU</a> (not to SPSSX-L), with no body text except the<br>comma=
nd. To leave the list, send the command<br>SIGNOFF SPSSX-L<br>For a list of=
commands to manage subscriptions, send the command<br>INFO REFCARD<br><br>=
<br> </div> </div> </blockquote> </div></div></body></html>
--2119556593-359084761-1340964547=:10469--

------------------------------

Date: Fri, 29 Jun 2012 07:24:48 -0400
From: Art Kendall <[hidden email]>
Subject: Re: Converting Fortran to SPSS

However, until we know what the task is, we don't even know if it can
already be accomplished in SPSS without any MATRIX, macros, (don't look
at this next word David) Python.

As Rich said the OP does not even say what dialect FORTRAN the code is in.
these code snippets on DEC FORTRAN circa 1974 takes a lot more code in
the IBM dialect.

parameter nstim= 20
parameter ncases=210

double precision data (nstim,nstim,ncases)
double precision summary(nstim,nstim)

dimension year (1901/2012)

implicit double precision (a, z)

and in later DEC FORTRAN
real * 16 anything

the code may also rely on the compile time option of turning on array
index checking so that if an array index is out of bounds an error is
created.
for example a value in the data for year that was 1900 would create an
error message

Art Kendall Social
Research Consultants

On 6/28/2012 10:25 PM, David Marso wrote:

> I know you would never think that I would think what would result should be a
> 'line by line' but a first mental pass would be and 10 lines of FORTRAN
> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10 SWEEP....
> etc (MATRIX doesn't have all that many built in linear algebra functions per
> se)
> Depending upon the level of internal documentation, actual supporting math
> equations etc it could be a few spins of the Ouija board and a few spent
> black candles before a blaring epiphany crafts an algorithm.
> Of course one must also consider that MATRIX doesn't *directly* support
> subroutines. OTOH I have clever ways around that.
> In summary I agree 'translate the code to algorithms, and program the
> algorithms.'
> OTOH I want to add screw the code! What is the original algorithm/math and
> code directly for the jugular!
>
>
> Rich Ulrich-2 wrote
>> I haven't used Fortran since they still spelled it FORTRAN -
>> the vector operators are probably transparent; but I
>> wonder how people use assignment of pointers. - So, the
>> version of Fortran might be relevant.
>>
>> Since the Matrix language has matrix operators, I suggest
>> that line-by-line is an awkward way to translate old, primitive
>> Fortran, the stuff that looks mainly like Basis. Is that what
>> it is? Instead, translate the code to algorithms, and program
>> the algorithms.
>>
>> --
>> Rich Ulrich
>>
>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>> From: david.marso@
>>> Subject: Re: Converting Fortran to SPSS
>>> To: SPSSX-L@.UGA
>>>
>>> What does it do?
>>> How long is the code?
>>> Are there verifiable test 'data' to confirm whatever might result?
>>> ---
>>> No such guide exists to my knowledge. Pretty much would need to convert
>>> line by line.
>>> If it is short and sweet, does something interesting and has verifiable
>>> confirmation post it here and I'd be happy to look at it and post
>>> suggestions (probably short of actually writing the code).
>>> If it is long and boring I'd consider doing it for a reasonable
>>> consulting
>>> fee.
>>> I haven't looked at FORTRAN in over 20 years but it's like writing a
>>> tricycle.
>>>
>>>
>>> Dates, Brian wrote
>>>> I have a task on which I'm working in matrix mode in SPSS. The only
>>>> solution that's available in publication regarding this task is written
>>>> in Fortran, with which I'm woefully inadequate. Does a guide exist
>>>> which assists in the conversion of Fortran code to SPSS syntax, similar
>>>> to the guides that are available comparing SPSS to SAS or R? Thanks.
>>>>
>>>>
>> ...
>>
>
> --
> View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS-tp5713876p5713883.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

------------------------------

Date: Fri, 29 Jun 2012 08:46:24 -0400
From: "Dates, Brian" <[hidden email]>
Subject: Re: Converting Fortran to SPSS

Thanks for the responses. The task is the skewness of a Pearson Type
III distribution for Multiresponse Randomized Block Permutation
Procedures (MRBP), so definitely 'long and boring'. I'll just tough it
out with the formulae I have and try to figure out the Fortran for some
assistance. Thanks again.

Brian

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
David Marso
Sent: Thursday, June 28, 2012 10:26 PM
To: [hidden email]
Subject: Re: Converting Fortran to SPSS

I know you would never think that I would think what would result should
be a
'line by line' but a first mental pass would be and 10 lines of FORTRAN
would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
SWEEP....
etc (MATRIX doesn't have all that many built in linear algebra functions
per
se)
Depending upon the level of internal documentation, actual supporting
math
equations etc it could be a few spins of the Ouija board and a few spent
black candles before a blaring epiphany crafts an algorithm.
Of course one must also consider that MATRIX doesn't *directly* support
subroutines. OTOH I have clever ways around that.
In summary I agree 'translate the code to algorithms, and program the
algorithms.'
OTOH I want to add screw the code! What is the original algorithm/math
and
code directly for the jugular!

Rich Ulrich-2 wrote

>
> I haven't used Fortran since they still spelled it FORTRAN -
> the vector operators are probably transparent; but I
> wonder how people use assignment of pointers. - So, the
> version of Fortran might be relevant.
>
> Since the Matrix language has matrix operators, I suggest
> that line-by-line is an awkward way to translate old, primitive
> Fortran, the stuff that looks mainly like Basis. Is that what
> it is? Instead, translate the code to algorithms, and program
> the algorithms.
>
> --
> Rich Ulrich
>
>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>> From: david.marso@
>> Subject: Re: Converting Fortran to SPSS
>> To: SPSSX-L@.UGA
>>
>> What does it do?
>> How long is the code?
>> Are there verifiable test 'data' to confirm whatever might result?
>> ---
>> No such guide exists to my knowledge. Pretty much would need to

convert
>> line by line.
>> If it is short and sweet, does something interesting and has
verifiable

>> confirmation post it here and I'd be happy to look at it and post
>> suggestions (probably short of actually writing the code).
>> If it is long and boring I'd consider doing it for a reasonable
>> consulting
>> fee.
>> I haven't looked at FORTRAN in over 20 years but it's like writing a
>> tricycle.
>>
>>
>> Dates, Brian wrote
>> >
>> > I have a task on which I'm working in matrix mode in SPSS. The

only
>> > solution that's available in publication regarding this task is
written
>> > in Fortran, with which I'm woefully inadequate. Does a guide exist
>> > which assists in the conversion of Fortran code to SPSS syntax,
similar
>> > to the guides that are available comparing SPSS to SAS or R?
Thanks.
>> >
>> >
> ...
>

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
-tp5713876p5713883.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

------------------------------

Date: Fri, 29 Jun 2012 06:15:34 -0700
From: Bruce Weaver <[hidden email]>
Subject: Re: Converting Fortran to SPSS

Have you come across Li Cai's MRPP macro?

http://lcai.bol.ucla.edu/mrpp.txt
http://lcai.bol.ucla.edu/programs.html
http://lcai.bol.ucla.edu/mrpp.pdf

HTH.

Dates, Brian wrote

>
> Thanks for the responses. The task is the skewness of a Pearson Type
> III distribution for Multiresponse Randomized Block Permutation
> Procedures (MRBP), so definitely 'long and boring'. I'll just tough it
> out with the formulae I have and try to figure out the Fortran for some
> assistance. Thanks again.
>
> Brian
>
>
>
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> David Marso
> Sent: Thursday, June 28, 2012 10:26 PM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> I know you would never think that I would think what would result should
> be a
> 'line by line' but a first mental pass would be and 10 lines of FORTRAN
> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
> SWEEP....
> etc (MATRIX doesn't have all that many built in linear algebra functions
> per
> se)
> Depending upon the level of internal documentation, actual supporting
> math
> equations etc it could be a few spins of the Ouija board and a few spent
> black candles before a blaring epiphany crafts an algorithm.
> Of course one must also consider that MATRIX doesn't *directly* support
> subroutines. OTOH I have clever ways around that.
> In summary I agree 'translate the code to algorithms, and program the
> algorithms.'
> OTOH I want to add screw the code! What is the original algorithm/math
> and
> code directly for the jugular!
>
>
> Rich Ulrich-2 wrote
>>
>> I haven't used Fortran since they still spelled it FORTRAN -
>> the vector operators are probably transparent; but I
>> wonder how people use assignment of pointers. - So, the
>> version of Fortran might be relevant.
>>
>> Since the Matrix language has matrix operators, I suggest
>> that line-by-line is an awkward way to translate old, primitive
>> Fortran, the stuff that looks mainly like Basis. Is that what
>> it is? Instead, translate the code to algorithms, and program
>> the algorithms.
>>
>> --
>> Rich Ulrich
>>
>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>> From: david.marso@
>>> Subject: Re: Converting Fortran to SPSS
>>> To: SPSSX-L@.UGA
>>>
>>> What does it do?
>>> How long is the code?
>>> Are there verifiable test 'data' to confirm whatever might result?
>>> ---
>>> No such guide exists to my knowledge. Pretty much would need to
> convert
>>> line by line.
>>> If it is short and sweet, does something interesting and has
> verifiable
>>> confirmation post it here and I'd be happy to look at it and post
>>> suggestions (probably short of actually writing the code).
>>> If it is long and boring I'd consider doing it for a reasonable
>>> consulting
>>> fee.
>>> I haven't looked at FORTRAN in over 20 years but it's like writing a
>>> tricycle.
>>>
>>>
>>> Dates, Brian wrote
>>> >
>>> > I have a task on which I'm working in matrix mode in SPSS. The
> only
>>> > solution that's available in publication regarding this task is
> written
>>> > in Fortran, with which I'm woefully inadequate. Does a guide exist
>>> > which assists in the conversion of Fortran code to SPSS syntax,
> similar
>>> > to the guides that are available comparing SPSS to SAS or R?
> Thanks.
>>> >
>>> >
>> ...
>>
>
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
> -tp5713876p5713883.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

> assistance. Thanks again.
>
> Brian
>
>
>
>
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> David Marso
> Sent: Thursday, June 28, 2012 10:26 PM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> I know you would never think that I would think what would result

should
> be a
> 'line by line' but a first mental pass would be and 10 lines of
FORTRAN
> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
> SWEEP....
> etc (MATRIX doesn't have all that many built in linear algebra
functions
> per
> se)
> Depending upon the level of internal documentation, actual supporting
> math
> equations etc it could be a few spins of the Ouija board and a few
spent
> black candles before a blaring epiphany crafts an algorithm.
> Of course one must also consider that MATRIX doesn't *directly*
support
> subroutines. OTOH I have clever ways around that.
> In summary I agree 'translate the code to algorithms, and program the
> algorithms.'
> OTOH I want to add screw the code! What is the original
algorithm/math

> and
> code directly for the jugular!
>
>
> Rich Ulrich-2 wrote
>>
>> I haven't used Fortran since they still spelled it FORTRAN -
>> the vector operators are probably transparent; but I
>> wonder how people use assignment of pointers. - So, the
>> version of Fortran might be relevant.
>>
>> Since the Matrix language has matrix operators, I suggest
>> that line-by-line is an awkward way to translate old, primitive
>> Fortran, the stuff that looks mainly like Basis. Is that what
>> it is? Instead, translate the code to algorithms, and program
>> the algorithms.
>>
>> --
>> Rich Ulrich
>>
>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>> From: david.marso@
>>> Subject: Re: Converting Fortran to SPSS
>>> To: SPSSX-L@.UGA
>>>
>>> What does it do?
>>> How long is the code?
>>> Are there verifiable test 'data' to confirm whatever might result?
>>> ---
>>> No such guide exists to my knowledge. Pretty much would need to
> convert
>>> line by line.
>>> If it is short and sweet, does something interesting and has
> verifiable
>>> confirmation post it here and I'd be happy to look at it and post
>>> suggestions (probably short of actually writing the code).
>>> If it is long and boring I'd consider doing it for a reasonable
>>> consulting
>>> fee.
>>> I haven't looked at FORTRAN in over 20 years but it's like writing a
>>> tricycle.
>>>
>>>
>>> Dates, Brian wrote
>>> >
>>> > I have a task on which I'm working in matrix mode in SPSS. The
> only
>>> > solution that's available in publication regarding this task is
> written
>>> > in Fortran, with which I'm woefully inadequate. Does a guide

exist

>>> > which assists in the conversion of Fortran code to SPSS syntax,
> similar
>>> > to the guides that are available comparing SPSS to SAS or R?
> Thanks.
>>> >
>>> >
>> ...
>>
>
>
> --
> View this message in context:
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

> -tp5713876p5713883.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

-----
--
Bruce Weaver
[hidden email]
http://sites.google.com/a/lakeheadu.ca/bweaver/

"When all else fails, RTFM."

NOTE: My Hotmail account is not monitored regularly.
To send me an e-mail, please use the address shown above.

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
-tp5713876p5713891.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

------------------------------

Date: Fri, 29 Jun 2012 13:37:58 +0000
From: "Zuluaga, Juan" <[hidden email]>
Subject: Re: Converting Fortran to SPSS

--_000_4B236621C4E4E943B7BB21F73014CD946DA75BBESCSU83Acampusst_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

I would run Fortran code as a call from R. No need to translate it, only so=
me tweaking needed. You do need to understand what the Fortran code does.

--_000_4B236621C4E4E943B7BB21F73014CD946DA75BBESCSU83Acampusst_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3D"Generator" content=3D"Microsoft Word 14 (filtered medium)">
<title>LISTSERV at the University of Georgia</title>
<style></style>
</head>
<body bgcolor=3D"white" lang=3D"EN-US" link=3D"blue" vlink=3D"blue">
<div class=3D"WordSection1">
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">I would run Fortran code =
as a call from R. No need to translate it, only some tweaking needed. You d=
o need to understand what the Fortran code does.
<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D"><o:p> </o:p></span><=
/p>
</div>
</body>
</html>

--_000_4B236621C4E4E943B7BB21F73014CD946DA75BBESCSU83Acampusst_--

------------------------------

Date: Fri, 29 Jun 2012 09:45:35 -0400
From: "Maguin, Eugene" <[hidden email]>
Subject: odds ratio to chi square conversion

Is there a way to convert an odds ratio to a chi square value? Specifically, given a 2x2 crosstabulation of x against y, the association between x and y can be expressed as an odds ratio (OR: bc/ad), as exp(B) from a logistic regression or a chi square. Knowing only either OR or B, can a chi-square be computed? One of the places this problem comes up is in meta-analyses where authors don't report sufficient data in primary reports.

Thanks, Gene Maguin

------------------------------

Date: Fri, 29 Jun 2012 08:13:04 -0600
From: Jon K Peck <[hidden email]>
Subject: Re: IBM SPSS Questions

This is a multipart message in MIME format.
--=_alternative 004E195887257A2C_=
Content-Type: text/plain; charset="US-ASCII"

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621

From: Eins Bernardo <[hidden email]>
To: [hidden email]
Date: 06/29/2012 02:41 AM
Subject: [SPSSX-L] IBM SPSS Questions
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Three questions for IBM SPSS personnel or others:

1. Any forum on modeler/clementine?
>>>The SPSS Community forums linked from the SPSS Community site (
www.ibm.com/developerworks/spssdevcentral) include a Modeler forum. There
are also some LinkedIn forums that cover Modeler.

2. Do you have matrix showing the comparison of capabilities/features of
AMOS across versions?
>>>I am not aware of such an item, but you might find this information in
a What's New section in the AMOS help.
3. Any forum on AMOS?

Thank you.
Eins

--=_alternative 004E195887257A2C_=
Content-Type: text/html; charset="US-ASCII"

<font size=2 face="sans-serif"><br>
Jon Peck (no "h") aka Kim<br>
Senior Software Engineer, IBM<br>
[hidden email]<br>
new phone: 720-342-5621<br>
</font>
<br>
<br>
<br>
<br><font size=1 color=#5f5f5f face="sans-serif">From:      
 </font><font size=1 face="sans-serif">Eins Bernardo <[hidden email]></font>
<br><font size=1 color=#5f5f5f face="sans-serif">To:      
 </font><font size=1 face="sans-serif">[hidden email]</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Date:      
 </font><font size=1 face="sans-serif">06/29/2012 02:41 AM</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Subject:    
   </font><font size=1 face="sans-serif">[SPSSX-L] IBM
SPSS Questions</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Sent by:    
   </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font>
<br>
<hr noshade>
<br>
<br>
<br><font size=3 face="Roman">Three questions for IBM SPSS personnel or
others:</font>
<br>
<br><font size=3 face="Times New Roman">1. Any forum on modeler/clementine?</font>
<br><font size=3 face="Times New Roman">>>>The SPSS Community
forums linked from the SPSS Community site (</font><a href=www.ibm.com/developerworks/spssdevcentral><font size=3 face="Times New Roman">www.ibm.com/developerworks/spssdevcentral</font></a><font size=3 face="Times New Roman">)
include a Modeler forum.  There are also some LinkedIn forums that
cover Modeler.</font>
<br>
<br><font size=3 face="Times New Roman">2. Do you have matrix showing the
comparison of capabilities/features of AMOS across versions?</font>
<br><font size=3 face="Times New Roman">>>>I am not aware of such
an item, but you might find this information in a What's New section in
the AMOS help.</font>
<br><font size=3 face="Times New Roman">3. Any forum on AMOS?</font>
<br>
<br><font size=3 face="Times New Roman">Thank you.</font>
<br><font size=3 face="Times New Roman">Eins</font>
<br><font size=3 face="Times New Roman"><br>
</font>
<br>
--=_alternative 004E195887257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 09:42:05 -0500
From: Rick Oliver <[hidden email]>
Subject: Re: SPSS Database Capacity

This is a multipart message in MIME format.
--=_alternative 004FDAAF86257A2C_=
Content-Type: text/plain; charset="US-ASCII"

I don't think the information on that page is entirely accurate. I'm not
aware of any theoretical limits on either cases or variables. Your
computing environment will determine practical limits.

Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]
Phone: 312.893.4922 | T/L: 206-4922

From: Albert-Jan Roskam <[hidden email]>
To: [hidden email]
Date: 06/29/2012 05:10 AM
Subject: Re: SPSS Database Capacity
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Hi,

See the line "How many variables and cases can SPSS for windows handle?"
on http://www.spsstools.net/FAQ.htm Not sure what the differences are when
on a 64 bit architecture.

Regards,
Albert-Jan

~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
All right, but apart from the sanitation, the medicine, education, wine,
public order, irrigation, roads, a
fresh water system, and public health, what have the Romans ever done for
us?
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
From: David Marso <[hidden email]>
To: [hidden email]
Sent: Friday, June 29, 2012 5:56 AM
Subject: Re: [SPSSX-L] SPSS Database Capacity

Hi Jon,
Please (when you have a moment) restate the actual *ABSOLUTE* max cases X
max vars for both 32 bit and 64 bits maybe even 132 bit systems just for
the
hell of it (assuming infinite disk space and RAM). Would love a core
dump
of the theory.

Jon K Peck wrote

>
> 1.5M records is not a large file by SPSS standards.
>
> Jon Peck (no "h") aka Kim
> Senior Software Engineer, IBM
> peck@.ibm
> new phone: 720-342-5621
>
>
>
>
> From: btafoya <btafoya@>
> To: SPSSX-L@.uga
> Date: 06/26/2012 08:39 PM
> Subject: [SPSSX-L] SPSS Database Capacity
> Sent by: "SPSSX(r) Discussion" <SPSSX-L@.uga>
>
>
>
> I have a population of 1.5 Million records that I want to use in SPSS.
> Will
> it work? What platform will I need to handle something like this? I will
> be
> taking random samples but will need to get descriptive statistics from

the
> entire population.
>
> --
> View this message in context:
>
http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html

>
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html

Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

--=_alternative 004FDAAF86257A2C_=
Content-Type: text/html; charset="US-ASCII"

<font size=2 face="sans-serif">I don't think the information on that page
is entirely accurate. I'm not aware of any theoretical limits on either
cases or variables. Your computing environment will determine practical
limits.</font>
<br>
<br><font size=2 face="sans-serif">Rick Oliver<br>
Senior Information Developer<br>
IBM Business Analytics (SPSS)<br>
E-mail: [hidden email]<br>
Phone: 312.893.4922 | T/L: 206-4922</font>
<br>
<br>
<br>
<br><font size=1 color=#5f5f5f face="sans-serif">From:      
 </font><font size=1 face="sans-serif">Albert-Jan Roskam <[hidden email]></font>
<br><font size=1 color=#5f5f5f face="sans-serif">To:      
 </font><font size=1 face="sans-serif">[hidden email]</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Date:      
 </font><font size=1 face="sans-serif">06/29/2012 05:10 AM</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Subject:    
   </font><font size=1 face="sans-serif">Re: SPSS Database
Capacity</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Sent by:    
   </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font>
<br>
<hr noshade>
<br>
<br>
<br><font size=3 face="Times">Hi, </font>
<br>
<br><font size=3 face="Times">See the line "How many variables and
cases can SPSS for windows handle?"  on </font><a href=http://www.spsstools.net/FAQ.htm><font size=3 face="Times">http://www.spsstools.net/FAQ.htm</font></a><font size=3 face="Times">
Not sure what the differences are when on a 64 bit architecture.</font>
<br><font size=3 face="Times"> </font>
<br><font size=3 face="Times">Regards,<br>
Albert-Jan<br>
</font>
<br><font size=3 face="Times">~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~<br>
All right, but apart from the sanitation, the medicine, education, wine,
public order, irrigation, roads, a <br>
fresh water system, and public health, what have the Romans ever done for
us?<br>
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
</font>
<br>
<hr><font size=2 face="Arial"><b>From:</b> David Marso <[hidden email]><b><br>
To:</b> [hidden email] <b><br>
Sent:</b> Friday, June 29, 2012 5:56 AM<b><br>
Subject:</b> Re: [SPSSX-L] SPSS Database Capacity</font>
<br><font size=3 face="Times"><br>
Hi Jon,<br>
Please (when you have a moment) restate the actual *ABSOLUTE* max cases
X<br>
max vars for both 32 bit and 64 bits maybe even 132 bit systems just for
the<br>
hell of it  (assuming infinite disk space and RAM).  Would love
a core dump<br>
of the theory.<br>
<br>
Jon K Peck wrote<br>
><br>
> 1.5M records is not a large file by SPSS standards.<br>
><br>
> Jon Peck (no "h") aka Kim<br>
> Senior Software Engineer, IBM<br>
> peck@.ibm<br>
> new phone: 720-342-5621<br>
><br>
><br>
><br>
><br>
> From:  btafoya &lt;btafoya@&gt;<br>
> To:    SPSSX-L@.uga<br>
> Date:  06/26/2012 08:39 PM<br>
> Subject:        [SPSSX-L] SPSS Database Capacity<br>
> Sent by:        "SPSSX(r) Discussion"
&lt;SPSSX-L@.uga&gt;<br>
><br>
><br>
><br>
> I have a population of 1.5 Million records that I want to use in SPSS.<br>
> Will<br>
> it work? What platform will I need to handle something like this?
I will<br>
> be<br>
> taking random samples but will need to get descriptive statistics
from the<br>
> entire population.<br>
><br>
> --<br>
> View this message in context:<br>
> </font><a href="http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html"><font size=3 face="Times">http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html</font></a><font size=3 face="Times"><br>
><br>
> Sent from the SPSSX Discussion mailing list archive at </font><a href=http://nabble.com/ target=_blank><font size=3 color=blue face="Times"><u>Nabble.com</u></font></a><font size=3 face="Times">.<br>
><br>
> =====================<br>
> To manage your subscription to SPSSX-L, send a message to<br>
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the<br>
> command. To leave the list, send the command<br>
> SIGNOFF SPSSX-L<br>
> For a list of commands to manage subscriptions, send the command<br>
> INFO REFCARD<br>
><br>
<br>
<br>
--<br>
View this message in context: </font><a href="http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html"><font size=3 face="Times">http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html</font></a><font size=3 face="Times"><br>
Sent from the SPSSX Discussion mailing list archive at Nabble.com.<br>
<br>
=====================<br>
To manage your subscription to SPSSX-L, send a message to</font><font size=3 color=blue face="Times"><u><br>
</u></font><a href=mailto:[hidden email]><font size=3 color=blue face="Times"><u>[hidden email]</u></font></a><font size=3 face="Times">
(not to SPSSX-L), with no body text except the<br>
command. To leave the list, send the command<br>
SIGNOFF SPSSX-L<br>
For a list of commands to manage subscriptions, send the command<br>
INFO REFCARD<br>
<br>
</font>
<br>
--=_alternative 004FDAAF86257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 07:52:57 -0700
From: Tom1234 <[hidden email]>
Subject: Spss Syntax select all values in a variable?

Is there any way in syntax(or otherwise) to select (and count) the number of
values in a variable?
I understand that VALUE LABELS is to assign them, but how would I select
already existing values/Value labels?

The reason being is:
I'm trying to write a script in SAX/WinWrap basic that allows me to
auto-code the value labels of variables in three ways:
1 - Via input box: User is prompted to enter variable and then a loop
selects the next available value and prompts the user to enter a value label
for each value that hasn't got a label already.
2 - By directly copying: User is prompted to enter variable and then a loop
reads the value, if it is a string the script puts a upper case letter at
the start and replaces any ^s with 's (a common error when exporting from
cati or excel) and then displays a message box saying the coding is
complete.
3 - Shift the value labels by a specified amount, user is prompted to enter
the number (positive or negative) that they want the labels to move (very
usefull when recoding large numbers of values) i.e. if you have 245 values
and you remove number 36 and 37 from the list, you'd have to redo the value
labels of every value after 35 so that they were 2 places closer if you
wanted consecutive values.

Here's part of my proto/pseudo code:

-----

"Lo there do I see my father. Lo there do I see my mother and my sisters and my brothers. Lo there do I see the line of my people, back to the beginning. Lo, they do call to me, they bid me take my place among them, in the Halls of Valhalla, where the brave may live...forever."
--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 10:58:09 -0400
From: Rich Ulrich <[hidden email]>
Subject: Re: odds ratio to chi square conversion

--_39102319-98b3-49fe-86d7-f3490a307318_
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

No. You need both sets of marginal totals to convert=20
an OR to a chi squared. You can show this by taking a
fixed total-N and constructing various tables with the
same OR and different tests.

For the meta-analysis: after making sure that the=20
information really is not there=2C contact the authors.
They probably will oblige.

A worthwhile meta-analysis is seldom easy. It wants=20
expertise both in statistics and in the content=2C so=2C good luck.

--=20
Rich Ulrich=20

> Date: Fri=2C 29 Jun 2012 09:45:35 -0400
> From: [hidden email]
> Subject: odds ratio to chi square conversion
> To: [hidden email]
>=20
> Is there a way to convert an odds ratio to a chi square value? Specifical=
ly=2C given a 2x2 crosstabulation of x against y=2C the association between=
x and y can be expressed as an odds ratio (OR: bc/ad)=2C as exp(B) from a =
logistic regression or a chi square. Knowing only either OR or B=2C can a c=
hi-square be computed? One of the places this problem comes up is in meta-a=
nalyses where authors don't report sufficient data in primary reports.
>=20
> Thanks=2C Gene Maguin
> ...
=

--_39102319-98b3-49fe-86d7-f3490a307318_
Content-Type: text/html; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

<html>
<head>
<style></style></head>
<body class=3D'hmmessage'><div dir=3D'ltr'>
No.&nbsp=3B You need both sets of marginal totals to convert <br>an OR to a=
chi squared.&nbsp=3B You can show this by taking a<br>fixed total-N and co=
nstructing various tables with the<br>same OR and different tests.<br><br>F=
or the meta-analysis:&nbsp=3B after making sure that the <br>information re=
ally is not there=2C contact the authors.<br>They probably will oblige.<br>=
<br>A worthwhile meta-analysis is seldom easy.&nbsp=3B It wants <br>experti=
se both in statistics and in the content=2C so=2C good luck.<br><br>-- <br>=
Rich Ulrich <br><br><div><div id=3D"SkyDrivePlaceholder"></div>&gt=3B Date:=
Fri=2C 29 Jun 2012 09:45:35 -0400<br>&gt=3B From: [hidden email]<br>&=
gt=3B Subject: odds ratio to chi square conversion<br>&gt=3B To: SPSSX-L@LI=
STSERV.UGA.EDU<br>&gt=3B <br>&gt=3B Is there a way to convert an odds ratio=
to a chi square value? Specifically=2C given a 2x2 crosstabulation of x ag=
ainst y=2C the association between x and y can be expressed as an odds rati=
o (OR: bc/ad)=2C as exp(B) from a logistic regression or a chi square. Know=
ing only either OR or B=2C can a chi-square be computed? One of the places =
this problem comes up is in meta-analyses where authors don't report suffic=
ient data in primary reports.<br>&gt=3B <br>&gt=3B Thanks=2C Gene Maguin<br=
>&gt=3B ...<br></div> </div></body>
</html>=

--_39102319-98b3-49fe-86d7-f3490a307318_--

------------------------------

Date: Fri, 29 Jun 2012 09:03:17 -0600
From: Jon K Peck <[hidden email]>
Subject: Re: SPSS Database Capacity

This is a multipart message in MIME format.
--=_alternative 0052B23887257A2C_=
Content-Type: text/plain; charset="US-ASCII"

Information on absolute limits on cases and variables in Statistics isn't
readily available, because those limits are far beyond practical
constraints imposed by the hardware and OS. IOW, you can assume that no
such limits exist on the part of Statistics. However, there are a few
procedures - mainly time series oriented, that require the data to be held
in memory and are thus likely to run out of resources sooner than the
general case. Since Statistics mostly does not hold all the cases in
memory, you will run out of patience before you run out of memory.

Our QA testbed goes up to 66,000 variables and more than 4 billion cases.
That is an absurd number of variables, but there you are. Certainly,
keeping the number of variables down to a reasonable number will speed
performance. And I often wonder why people are often so averse to taking
random samples of vast datasets except in situations where they are
searching for needle-in-haystack very rare events.

BTW, I learned an interesting fact recently about the Watson system that
won the Jeopardy contest. It had 155 terabytes of physical memory. Don't
try that at home.

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621

From: David Marso <[hidden email]>
To: [hidden email]
Date: 06/28/2012 09:59 PM
Subject: Re: [SPSSX-L] SPSS Database Capacity
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Hi Jon,
Please (when you have a moment) restate the actual *ABSOLUTE* max cases X
max vars for both 32 bit and 64 bits maybe even 132 bit systems just for
the
hell of it (assuming infinite disk space and RAM). Would love a core
dump
of the theory.

Jon K Peck wrote

the
> entire population.
>
> --
> View this message in context:
>
http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html

Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

--=_alternative 0052B23887257A2C_=
Content-Type: text/html; charset="US-ASCII"

<font size=2 face="sans-serif">Information on absolute limits on cases
and variables in Statistics isn't readily available, because those limits
are far beyond practical constraints imposed by the hardware and OS.  IOW,
you can assume that no such limits exist on the part of Statistics.  However,
there are a few procedures - mainly time series oriented, that require
the data to be held in memory and are thus likely to run out of resources
sooner than the general case.  Since Statistics mostly does not hold
all the cases in memory, you will run out of patience before you run out
of memory.</font>
<br>
<br><font size=2 face="sans-serif">Our QA testbed goes up to 66,000 variables
and more than 4 billion cases.  That is an absurd number of variables,
but there you are.  Certainly, keeping the number of variables down
to a reasonable number will speed performance.  And I often wonder
why people are often so averse to taking random samples of vast datasets
except in situations where they are searching for needle-in-haystack very
rare events.</font>
<br>
<br><font size=2 face="sans-serif">BTW, I learned an interesting fact recently
about the Watson system that won the Jeopardy contest.  It had 155
terabytes of physical memory.  Don't try that at home.</font>
<br><font size=2 face="sans-serif"><br>
Jon Peck (no "h") aka Kim<br>
Senior Software Engineer, IBM<br>
[hidden email]<br>
new phone: 720-342-5621<br>
</font>
<br>
<br>
<br>
<br><font size=1 color=#5f5f5f face="sans-serif">From:      
 </font><font size=1 face="sans-serif">David Marso <[hidden email]></font>
<br><font size=1 color=#5f5f5f face="sans-serif">To:      
 </font><font size=1 face="sans-serif">[hidden email]</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Date:      
 </font><font size=1 face="sans-serif">06/28/2012 09:59 PM</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Subject:    
   </font><font size=1 face="sans-serif">Re: [SPSSX-L]
SPSS Database Capacity</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Sent by:    
   </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font>
<br>
<hr noshade>
<br>
<br>
<br><tt><font size=2>Hi Jon,<br>
Please (when you have a moment) restate the actual *ABSOLUTE* max cases
X<br>
max vars for both 32 bit and 64 bits maybe even 132 bit systems just for
the<br>
hell of it  (assuming infinite disk space and RAM).  Would love
a core dump<br>
of the theory.<br>
<br>
Jon K Peck wrote<br>
><br>
> 1.5M records is not a large file by SPSS standards.<br>
><br>
> Jon Peck (no "h") aka Kim<br>
> Senior Software Engineer, IBM<br>
> peck@.ibm<br>
> new phone: 720-342-5621<br>
><br>
><br>
><br>
><br>
> From:   btafoya &lt;btafoya@&gt;<br>
> To:     SPSSX-L@.uga<br>
> Date:   06/26/2012 08:39 PM<br>
> Subject:        [SPSSX-L] SPSS Database Capacity<br>
> Sent by:        "SPSSX(r) Discussion"
&lt;SPSSX-L@.uga&gt;<br>
><br>
><br>
><br>
> I have a population of 1.5 Million records that I want to use in SPSS.<br>
> Will<br>
> it work? What platform will I need to handle something like this?
I will<br>
> be<br>
> taking random samples but will need to get descriptive statistics
from the<br>
> entire population.<br>
><br>
> --<br>
> View this message in context:<br>
> </font></tt><a href="http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html"><tt><font size=2>http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809.html</font></tt></a><tt><font size=2><br>
><br>
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.<br>
><br>
> =====================<br>
> To manage your subscription to SPSSX-L, send a message to<br>
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the<br>
> command. To leave the list, send the command<br>
> SIGNOFF SPSSX-L<br>
> For a list of commands to manage subscriptions, send the command<br>
> INFO REFCARD<br>
><br>
<br>
<br>
--<br>
View this message in context: </font></tt><a href="http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html"><tt><font size=2>http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html</font></tt></a><tt><font size=2><br>
Sent from the SPSSX Discussion mailing list archive at Nabble.com.<br>
<br>
=====================<br>
To manage your subscription to SPSSX-L, send a message to<br>
[hidden email] (not to SPSSX-L), with no body text except the<br>
command. To leave the list, send the command<br>
SIGNOFF SPSSX-L<br>
For a list of commands to manage subscriptions, send the command<br>
INFO REFCARD<br>
<br>
</font></tt>
<br>
--=_alternative 0052B23887257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 09:05:44 -0600
From: Jon K Peck <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

This is a multipart message in MIME format.
--=_alternative 0052E45C87257A2C_=
Content-Type: text/plain; charset="US-ASCII"

There are many ways to do this. The simplest is to run AGGREGATE using
the variable as a break variable and creating a new dataset from the
output and then examine its size.

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621

From: Tom1234 <[hidden email]>
To: [hidden email]
Date: 06/29/2012 08:58 AM
Subject: [SPSSX-L] Spss Syntax select all values in a variable?
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Is there any way in syntax(or otherwise) to select (and count) the number
of
values in a variable?
I understand that VALUE LABELS is to assign them, but how would I select
already existing values/Value labels?

The reason being is:
I'm trying to write a script in SAX/WinWrap basic that allows me to
auto-code the value labels of variables in three ways:
1 - Via input box: User is prompted to enter variable and then a loop
selects the next available value and prompts the user to enter a value
label
for each value that hasn't got a label already.
2 - By directly copying: User is prompted to enter variable and then a
loop
reads the value, if it is a string the script puts a upper case letter at
the start and replaces any ^s with 's (a common error when exporting from
cati or excel) and then displays a message box saying the coding is
complete.
3 - Shift the value labels by a specified amount, user is prompted to
enter
the number (positive or negative) that they want the labels to move (very
usefull when recoding large numbers of values) i.e. if you have 245 values
and you remove number 36 and 37 from the list, you'd have to redo the
value
labels of every value after 35 so that they were 2 places closer if you
wanted consecutive values.

Here's part of my proto/pseudo code:

-----

"Lo there do I see my father. Lo there do I see my mother and my sisters
and my brothers. Lo there do I see the line of my people, back to the
beginning. Lo, they do call to me, they bid me take my place among them,
in the Halls of Valhalla, where the brave may live...forever."
--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html

Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

--=_alternative 0052E45C87257A2C_=
Content-Type: text/html; charset="US-ASCII"

<font size=2 face="sans-serif">There are many ways to do this.  The
simplest is to run AGGREGATE using the variable as a break variable and
creating a new dataset from the output and then examine its size.</font>
<br><font size=2 face="sans-serif"><br>
Jon Peck (no "h") aka Kim<br>
Senior Software Engineer, IBM<br>
[hidden email]<br>
new phone: 720-342-5621<br>
</font>
<br>
<br>
<br>
<br><font size=1 color=#5f5f5f face="sans-serif">From:      
 </font><font size=1 face="sans-serif">Tom1234 <[hidden email]></font>
<br><font size=1 color=#5f5f5f face="sans-serif">To:      
 </font><font size=1 face="sans-serif">[hidden email]</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Date:      
 </font><font size=1 face="sans-serif">06/29/2012 08:58 AM</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Subject:    
   </font><font size=1 face="sans-serif">[SPSSX-L] Spss
Syntax select all values in a variable?</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Sent by:    
   </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font>
<br>
<hr noshade>
<br>
<br>
<br><tt><font size=2>Is there any way in syntax(or otherwise) to select
(and count) the number of<br>
values in a variable?<br>
I understand that VALUE LABELS is to assign them, but how would I select<br>
already existing values/Value labels?<br>
<br>
The reason being is:<br>
I'm trying to write a script in SAX/WinWrap basic that allows me to<br>
auto-code the value labels of variables in three ways:<br>
1 - Via input box: User is prompted to enter variable and then a loop<br>
selects the next available value and prompts the user to enter a value
label<br>
for each value that hasn't got a label already.<br>
2 - By directly copying: User is prompted to enter variable and then a
loop<br>
reads the value, if it is a string the script puts a upper case letter
at<br>
the start and replaces any ^s with 's (a common error when exporting from<br>
cati or excel) and then displays a message box saying the coding is<br>
complete.<br>
3 - Shift the value labels by a specified amount, user is prompted to enter<br>
the number (positive or negative) that they want the labels to move (very<br>
usefull when recoding large numbers of values) i.e. if you have 245 values<br>
and you remove number 36 and 37 from the list, you'd have to redo the value<br>
labels of every value after 35 so that they were 2 places closer if you<br>
wanted consecutive values.<br>
<br>
Here's part of my proto/pseudo code:<br>
<br>
<br>
-----<br>
<br>
"Lo there do I see my father. Lo there do I see my mother and my sisters
and my brothers. Lo there do I see the line of my people, back to the beginning.
Lo, they do call to me, they bid me take my place among them, in the Halls
of Valhalla, where the brave may live...forever."<br>
--<br>
View this message in context: </font></tt><a href="http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html"><tt><font size=2>http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html</font></tt></a><tt><font size=2><br>
Sent from the SPSSX Discussion mailing list archive at Nabble.com.<br>
<br>
=====================<br>
To manage your subscription to SPSSX-L, send a message to<br>
[hidden email] (not to SPSSX-L), with no body text except the<br>
command. To leave the list, send the command<br>
SIGNOFF SPSSX-L<br>
For a list of commands to manage subscriptions, send the command<br>
INFO REFCARD<br>
<br>
</font></tt>
<br>
--=_alternative 0052E45C87257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 11:17:56 -0400
From: "Maguin, Eugene" <[hidden email]>
Subject: Re: SPSS Database Capacity

--_000_4024B96CBC305F4E863248D2D6CDF5A813E3902295MBCCR5itorgad_
Content-Type: text/plain; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

Jon,

Perhaps you would comment on this please.
Recently somebody asked me off-list about display problems opening a 37Gb S=
PSS file with 90.546M records (rows). This person said he had a pop-up mes=
sage that SPSS can 'only' display 90,500,000 rows. Are there display limits=
and if so, are those limits determined by the specifications of the comput=
er. What specifications go into determining the limits and are there settin=
gs that can be tweaked to increase the limits?

Thanks, Gene Maguin

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Jo=
n K Peck
Sent: Friday, June 29, 2012 11:03 AM
To: [hidden email]
Subject: Re: SPSS Database Capacity

Information on absolute limits on cases and variables in Statistics isn't r=
eadily available, because those limits are far beyond practical constraints=
imposed by the hardware and OS. IOW, you can assume that no such limits e=
xist on the part of Statistics. However, there are a few procedures - main=
ly time series oriented, that require the data to be held in memory and are=
thus likely to run out of resources sooner than the general case. Since S=
tatistics mostly does not hold all the cases in memory, you will run out of=
patience before you run out of memory.

Our QA testbed goes up to 66,000 variables and more than 4 billion cases. =
That is an absurd number of variables, but there you are. Certainly, keepi=
ng the number of variables down to a reasonable number will speed performan=
ce. And I often wonder why people are often so averse to taking random sam=
ples of vast datasets except in situations where they are searching for nee=
dle-in-haystack very rare events.

BTW, I learned an interesting fact recently about the Watson system that wo=
n the Jeopardy contest. It had 155 terabytes of physical memory. Don't tr=
y that at home.

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]<mailto:[hidden email]>
new phone: 720-342-5621

From: David Marso <[hidden email]<mailto:[hidden email]=
m>>
To: [hidden email]<mailto:[hidden email]>
Date: 06/28/2012 09:59 PM
Subject: Re: [SPSSX-L] SPSS Database Capacity
Sent by: "SPSSX(r) Discussion" <[hidden email]<mailto:SPSS=
[hidden email]>>
________________________________

Hi Jon,
Please (when you have a moment) restate the actual *ABSOLUTE* max cases X
max vars for both 32 bit and 64 bits maybe even 132 bit systems just for th=
e
hell of it (assuming infinite disk space and RAM). Would love a core dump
of the theory.

Jon K Peck wrote

>
> 1.5M records is not a large file by SPSS standards.
>
> Jon Peck (no "h") aka Kim
> Senior Software Engineer, IBM
> peck@.ibm<mailto:peck@.ibm>
> new phone: 720-342-5621
>
>
>
>
> From: btafoya <btafoya@>
> To: SPSSX-L@.uga<mailto:SPSSX-L@.uga>
> Date: 06/26/2012 08:39 PM
> Subject: [SPSSX-L] SPSS Database Capacity
> Sent by: "SPSSX(r) Discussion" <SPSSX-L@.uga>
>
>
>
> I have a population of 1.5 Million records that I want to use in SPSS.
> Will
> it work? What platform will I need to handle something like this? I will
> be
> taking random samples but will need to get descriptive statistics from th=

e
> entire population.
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp57=
13809.html
>
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA<mailto:LISTSERV@.UGA> (not to SPSSX-L), with no body text e=
xcept the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com=
/SPSS-Database-Capacity-tp5713809p5713886.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
To manage your subscription to SPSSX-L, send a message to
[hidden email]<mailto:[hidden email]> (not to SPSSX-L=
), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

--_000_139EBE2EF1603B48A3BC8F89B34434D414FE91FECITESMBX3aduill_
Content-Type: text/html; charset="us-ascii"
Content-Transfer-Encoding: quoted-printable

<html xmlns:v=3D"urn:schemas-microsoft-com:vml" xmlns:o=3D"urn:schemas-micr=
osoft-com:office:office" xmlns:w=3D"urn:schemas-microsoft-com:office:word" =
xmlns:m=3D"http://schemas.microsoft.com/office/2004/12/omml" xmlns=3D"http:=
//www.w3.org/TR/REC-html40">
<head>
<meta http-equiv=3D"Content-Type" content=3D"text/html; charset=3Dus-ascii"=
>
<meta name=3D"Generator" content=3D"Microsoft Word 14 (filtered medium)">
<style></style>
</head>
<body lang=3D"EN-US" link=3D"blue" vlink=3D"purple">
<div class=3D"WordSection1">
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">I believe the aversion to=
random sampling (as I experience it) is that people often have a tendency =
to hoard.  There is reluctance to give up the data, given
the time and money spent on collecting it.  Often there is also a bel=
ief that if your sample is actually a population, then then you should anal=
yze the entire population, instead of a sample of it, because its somehow m=
ore valid.  There doesn’t seem to be
a clear understanding that you can infer with near total confidence everyt=
hing you need from just a sample, as compared with the entire population.&n=
bsp; Added to that is the common misconceptions with regard to drawing mult=
iple random samples to confirm results. 
People often don’t understand the statistics they want or use, and d=
on’t understand why we can’t just give them a single number.&nb=
sp; I believe its related to the same mindset that has led to numerous requ=
ests for how to do a multiple imputation and save out a
single data set.  <o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D"><o:p> </o:p></span><=
/p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">To echo what Jon has ment=
ioned on some practical limits, some of my analysis work has required that =
I allow the program to run overnight or for a few hours,
and increased variables and cases are frequently the result.  One exa=
mple you could run into is ridge regression.  Another one I use far mo=
re often are the mixed modeling (MLM/HLM, etc.).  With regard to MLM, =
I have found that the most common cause of overnight
run times is a misspecification of the model in which I attempted to allow=
too many variables to be random to the point of absurdity.  Occasiona=
lly this will happen with a reasonably specified model, where my a-priori t=
heory that some factor be allowed to
vary random is reasonable, but where the number of varied levels and amoun=
t of cases is so large that it takes quite a long time to converge on a fin=
al model.  Again the main cause is a large number of levels to said mo=
del, and many blocks within higher levels. 
This is not an SPSS problem (maybe the efficiency of the algorithm, but I =
don’t know that others are better), rather it’s a hardware reso=
urce problem.     <o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D"><o:p> </o:p></span><=
/p>
<p class=3D"MsoNormal"><b><span style=3D"font-size:11.0pt;font-family:&quot=
;Calibri","sans-serif";color:#1F497D">Matthew J Poes</span><=
/b><span style=3D"font-size:11.0pt;font-family:"Calibri","sa=
ns-serif";color:#1F497D"><o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">Research Data Specialist<=
o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">Center for Prevention Res=
earch and Development<o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">University of Illinois<o:=
p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">510 Devonshire Dr.<o:p></=
o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">Champaign, IL 61820<o:p><=
/o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">Phone: 217-265-4576<=
o:p></o:p></span></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D">email:
<a href=3D"mailto:[hidden email]">[hidden email]</a><o:p></o:p></sp=
an></p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D"><o:p> </o:p></span><=
/p>
<p class=3D"MsoNormal"><span style=3D"font-size:11.0pt;font-family:"Ca=
libri","sans-serif";color:#1F497D"><o:p> </o:p></span><=
/p>
<p class=3D"MsoNormal"><b><span style=3D"font-size:10.0pt;font-family:&quot=
;Tahoma","sans-serif"">From:</span></b><span style=3D"font-s=
ize:10.0pt;font-family:"Tahoma","sans-serif""> SPSSX(r)=
Discussion [mailto:[hidden email]]
<b>On Behalf Of </b>Jon K Peck<br>
<b>Sent:</b> Friday, June 29, 2012 10:03 AM<br>
<b>To:</b> [hidden email]<br>
<b>Subject:</b> Re: SPSS Database Capacity<o:p></o:p></span></p>
<p class=3D"MsoNormal"><o:p> </o:p></p>
<p class=3D"MsoNormal"><span style=3D"font-size:10.0pt;font-family:"Ar=
ial","sans-serif"">Information on absolute limits on cases a=
nd variables in Statistics isn't readily available, because those limits ar=
e far beyond practical constraints imposed by the hardware
and OS.  IOW, you can assume that no such limits exist on the part of=
Statistics.  However, there are a few procedures - mainly time series=
oriented, that require the data to be held in memory and are thus likely t=
o run out of resources sooner than the general
case.  Since Statistics mostly does not hold all the cases in memory,=
you will run out of patience before you run out of memory.</span>
<br>
<br>
<span style=3D"font-size:10.0pt;font-family:"Arial","sans-se=
rif"">Our QA testbed goes up to 66,000 variables and more than 4 billi=
on cases.  That is an absurd number of variables, but there you are. &=
nbsp;Certainly, keeping the number of variables down to a reasonable
number will speed performance.  And I often wonder why people are oft=
en so averse to taking random samples of vast datasets except in situations=
where they are searching for needle-in-haystack very rare events.</span>
<br>
<br>
<span style=3D"font-size:10.0pt;font-family:"Arial","sans-se=
rif"">BTW, I learned an interesting fact recently about the Watson sys=
tem that won the Jeopardy contest.  It had 155 terabytes of physical m=
emory.  Don't try that at home.</span>
<br>
<span style=3D"font-size:10.0pt;font-family:"Arial","sans-se=
rif""><br>
Jon Peck (no "h") aka Kim<br>
Senior Software Engineer, IBM<br>
<a href=3D"mailto:[hidden email]">[hidden email]</a><br>
new phone: 720-342-5621<br>
</span><br>
<br>
<br>
<br>
<span style=3D"font-size:7.5pt;font-family:"Arial","sans-ser=
if";color:#5F5F5F">From:        </span><span style=
=3D"font-size:7.5pt;font-family:"Arial","sans-serif"">D=
avid Marso <<a href=3D"mailto:[hidden email]">[hidden email]=
om</a>></span>
<br>
<span style=3D"font-size:7.5pt;font-family:"Arial","sans-ser=
if";color:#5F5F5F">To:        </span><span style=
=3D"font-size:7.5pt;font-family:"Arial","sans-serif""><=
a href=3D"mailto:[hidden email]">[hidden email]</a></sp=
an>
<br>
<span style=3D"font-size:7.5pt;font-family:"Arial","sans-ser=
if";color:#5F5F5F">Date:        </span><span style=
=3D"font-size:7.5pt;font-family:"Arial","sans-serif"">0=
6/28/2012 09:59 PM</span>
<br>
<span style=3D"font-size:7.5pt;font-family:"Arial","sans-ser=
if";color:#5F5F5F">Subject:        </span><span st=
yle=3D"font-size:7.5pt;font-family:"Arial","sans-serif"=
">Re: [SPSSX-L] SPSS Database Capacity</span>
<br>
<span style=3D"font-size:7.5pt;font-family:"Arial","sans-ser=
if";color:#5F5F5F">Sent by:        </span><span st=
yle=3D"font-size:7.5pt;font-family:"Arial","sans-serif"=
">"SPSSX(r) Discussion" <<a href=3D"mailto:[hidden email]=
a.edu">[hidden email]</a>></span>
<o:p></o:p></p>
<div class=3D"MsoNormal" align=3D"center" style=3D"text-align:center">
<hr size=3D"2" width=3D"100%" noshade=3D"" style=3D"color:#A0A0A0" align=3D=
"center">
</div>
<p class=3D"MsoNormal" style=3D"margin-bottom:12.0pt"><br>
<br>
<br>
<tt><span style=3D"font-size:10.0pt">Hi Jon,</span></tt><span style=3D"font=
-size:10.0pt;font-family:"Courier New""><br>
<tt>Please (when you have a moment) restate the actual *ABSOLUTE* max cases=
X</tt><br>
<tt>max vars for both 32 bit and 64 bits maybe even 132 bit systems just fo=
r the</tt><br>
<tt>hell of it  (assuming infinite disk space and RAM).  Would lo=
ve a core dump</tt><br>
<tt>of the theory.</tt><br>
<br>
<tt>Jon K Peck wrote</tt><br>
<tt>></tt><br>
<tt>> 1.5M records is not a large file by SPSS standards.</tt><br>
<tt>></tt><br>
<tt>> Jon Peck (no "h") aka Kim</tt><br>
<tt>> Senior Software Engineer, IBM</tt><br>
<tt>> <a href=3D"mailto:peck@.ibm">peck@.ibm</a></tt><br>
<tt>> new phone: 720-342-5621</tt><br>
<tt>></tt><br>
<tt>></tt><br>
<tt>></tt><br>
<tt>></tt><br>
<tt>> From:   btafoya &lt;btafoya@&gt;</tt><br>
<tt>> To:     <a href=3D"mailto:SPSSX-L@.uga">SPSSX-L@.uga</a>=
</tt><br>
<tt>> Date:   06/26/2012 08:39 PM</tt><br>
<tt>> Subject:        [SPSSX-L] SPSS Database Capaci=
ty</tt><br>
<tt>> Sent by:        "SPSSX(r) Discussion&quot=
; &lt;SPSSX-L@.uga&gt;</tt><br>
<tt>></tt><br>
<tt>></tt><br>
<tt>></tt><br>
<tt>> I have a population of 1.5 Million records that I want to use in S=
PSS.</tt><br>
<tt>> Will</tt><br>
<tt>> it work? What platform will I need to handle something like this? =
I will</tt><br>
<tt>> be</tt><br>
<tt>> taking random samples but will need to get descriptive statistics =
from the</tt><br>
<tt>> entire population.</tt><br>
<tt>></tt><br>
<tt>> --</tt><br>
<tt>> View this message in context:</tt><br>
<tt>> </tt></span><a href=3D"http://spssx-discussion.1045642.n5.nabble.c=
om/SPSS-Database-Capacity-tp5713809.html"><tt><span style=3D"font-size:10.0=
pt">http://spssx-discussion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp=
5713809.html</span></tt></a><span style=3D"font-size:10.0pt;font-family:&qu=
ot;Courier New""><br>
<tt>></tt><br>
<tt>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.=
</tt><br>
<tt>></tt><br>
<tt>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D</t=
t><br>
<tt>> To manage your subscription to SPSSX-L, send a message to</tt><br>
<tt>> <a href=3D"mailto:LISTSERV@.UGA">LISTSERV@.UGA</a> (not to SPSSX-L=
), with no body text except the</tt><br>
<tt>> command. To leave the list, send the command</tt><br>
<tt>> SIGNOFF SPSSX-L</tt><br>
<tt>> For a list of commands to manage subscriptions, send the command</=
tt><br>
<tt>> INFO REFCARD</tt><br>
<tt>></tt><br>
<br>
<br>
<tt>--</tt><br>
<tt>View this message in context: </tt></span><a href=3D"http://spssx-discu=
ssion.1045642.n5.nabble.com/SPSS-Database-Capacity-tp5713809p5713886.html">=
<tt><span style=3D"font-size:10.0pt">http://spssx-discussion.1045642.n5.nab=
ble.com/SPSS-Database-Capacity-tp5713809p5713886.html</span></tt></a><span =
style=3D"font-size:10.0pt;font-family:"Courier New""><br>
<tt>Sent from the SPSSX Discussion mailing list archive at Nabble.com.</tt>=
<br>
<br>
<tt>=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D</tt><br=
>
<tt>To manage your subscription to SPSSX-L, send a message to</tt><br>
<tt><a href=3D"mailto:[hidden email]">[hidden email]<=
/a> (not to SPSSX-L), with no body text except the</tt><br>
<tt>command. To leave the list, send the command</tt><br>
<tt>SIGNOFF SPSSX-L</tt><br>
<tt>For a list of commands to manage subscriptions, send the command</tt><b=
r>
<tt>INFO REFCARD</tt><br>
<br>
</span><o:p></o:p></p>
</div>
</body>
</html>

--_000_139EBE2EF1603B48A3BC8F89B34434D414FE91FECITESMBX3aduill_--

------------------------------

Date: Fri, 29 Jun 2012 09:45:22 -0600
From: Jon K Peck <[hidden email]>
Subject: Re: SPSS Database Capacity

This is a multipart message in MIME format.
--=_alternative 0056865D87257A2C_=
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: base64
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--=_alternative 0056865D87257A2C_=
Content-Type: text/html; charset="UTF-8"
Content-Transfer-Encoding: base64
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--=_alternative 0056865D87257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 10:41:44 -0500
From: Kyle Weeks <[hidden email]>
Subject: Re: IBM SPSS Questions

This is a multipart message in MIME format.
--=_alternative 0056376686257A2C_=
Content-Type: text/plain; charset="US-ASCII"

There is a forum about Structural Equation Modeling. See
http://www2.gsu.edu/~mkteer/semnet.html.

From: Jon K Peck/Chicago/IBM@IBMUS
To: [hidden email]
Date: 06/29/2012 09:29 AM
Subject: Re: IBM SPSS Questions
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Jon Peck (no "h") aka Kim
Senior Software Engineer, IBM
[hidden email]
new phone: 720-342-5621

From: Eins Bernardo <[hidden email]>
To: [hidden email]
Date: 06/29/2012 02:41 AM
Subject: [SPSSX-L] IBM SPSS Questions
Sent by: "SPSSX(r) Discussion" <[hidden email]>

Three questions for IBM SPSS personnel or others:

1. Any forum on modeler/clementine?
>>>The SPSS Community forums linked from the SPSS Community site (
www.ibm.com/developerworks/spssdevcentral) include a Modeler forum. There
are also some LinkedIn forums that cover Modeler.

2. Do you have matrix showing the comparison of capabilities/features of
AMOS across versions?
>>>I am not aware of such an item, but you might find this information in
a What's New section in the AMOS help.
3. Any forum on AMOS?

Thank you.
Eins

--=_alternative 0056376686257A2C_=
Content-Type: text/html; charset="US-ASCII"

<font size=2 face="sans-serif">There is a forum about Structural Equation
Modeling.  See </font><a href=http://www2.gsu.edu/~mkteer/semnet.html><font size=2 face="sans-serif">http://www2.gsu.edu/~mkteer/semnet.html</font></a><font size=2 face="sans-serif">.
 <br>
</font>
<br>
<br>
<br>
<br><font size=1 color=#5f5f5f face="sans-serif">From:      
 </font><font size=1 face="sans-serif">Jon K Peck/Chicago/IBM@IBMUS</font>
<br><font size=1 color=#5f5f5f face="sans-serif">To:      
 </font><font size=1 face="sans-serif">[hidden email]</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Date:      
 </font><font size=1 face="sans-serif">06/29/2012 09:29 AM</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Subject:    
   </font><font size=1 face="sans-serif">Re: IBM SPSS
Questions</font>
<br><font size=1 color=#5f5f5f face="sans-serif">Sent by:    
   </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font>
<br>
<hr noshade>
<br>
<br>
<br><font size=2 face="sans-serif"><br>
Jon Peck (no "h") aka Kim<br>
Senior Software Engineer, IBM<br>
[hidden email]<br>
new phone: 720-342-5621</font><font size=3><br>
<br>
<br>
<br>
</font><font size=1 color=#5f5f5f face="sans-serif"><br>
From:        </font><font size=1 face="sans-serif">Eins
Bernardo <[hidden email]></font><font size=3> </font><font size=1 color=#5f5f5f face="sans-serif"><br>
To:        </font><font size=1 face="sans-serif">[hidden email]</font><font size=3>
</font><font size=1 color=#5f5f5f face="sans-serif"><br>
Date:        </font><font size=1 face="sans-serif">06/29/2012
02:41 AM</font><font size=3> </font><font size=1 color=#5f5f5f face="sans-serif"><br>
Subject:        </font><font size=1 face="sans-serif">[SPSSX-L]
IBM SPSS Questions</font><font size=3> </font><font size=1 color=#5f5f5f face="sans-serif"><br>
Sent by:        </font><font size=1 face="sans-serif">"SPSSX(r)
Discussion" <[hidden email]></font><font size=3> <br>
</font>
<hr noshade><font size=3><br>
<br>
</font><font size=3 face="Roman"><br>
Three questions for IBM SPSS personnel or others:</font><font size=3> <br>
</font><font size=3 face="Times New Roman"><br>
1. Any forum on modeler/clementine?</font><font size=3> </font><font size=3 face="Times New Roman"><br>
>>>The SPSS Community forums linked from the SPSS Community site
(</font><a href=www.ibm.com/developerworks/spssdevcentral><font size=3 color=blue face="Times New Roman"><u>www.ibm.com/developerworks/spssdevcentral</u></font></a><font size=3 face="Times New Roman">)
include a Modeler forum.  There are also some LinkedIn forums that
cover Modeler.</font><font size=3> <br>
</font><font size=3 face="Times New Roman"><br>
2. Do you have matrix showing the comparison of capabilities/features of
AMOS across versions?</font><font size=3> </font><font size=3 face="Times New Roman"><br>
>>>I am not aware of such an item, but you might find this information
in a What's New section in the AMOS help.</font><font size=3> </font><font size=3 face="Times New Roman"><br>
3. Any forum on AMOS?</font><font size=3> <br>
</font><font size=3 face="Times New Roman"><br>
Thank you.</font><font size=3> </font><font size=3 face="Times New Roman"><br>
Eins</font><font size=3> </font><font size=3 face="Times New Roman"><br>
</font><font size=3><br>
</font>
<br>
--=_alternative 0056376686257A2C_=--

------------------------------

Date: Fri, 29 Jun 2012 08:56:37 -0700
From: David Marso <[hidden email]>
Subject: Re: Converting Fortran to SPSS

FWIW: I located Blossom software :
http://www.fort.usgs.gov/Products/Software/blossom/
where would one find a link for the source code?

Dates, Brian wrote

>
> Bruce,
>
> Thanks. Yes, I have copies, and it's somewhat helpful, but the blocking
> factor changes the way that all of the cumulants are calculated. The
> Fortran code I have is from the Blossom software. I think between the
> two, I can get through it. I was looking for a time-saver, something
> like the "R for SPSS and SAS Users" document. I'm very rusty on
> Fortran. I really appreciate the suggestion. When I'm finished I'll
> let the list know, or contact Raynald to see if he wants to post it, in
> case anyone is interested in the macro.
>
> Brian
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> Bruce Weaver
> Sent: Friday, June 29, 2012 9:16 AM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> Have you come across Li Cai's MRPP macro?
>
> http://lcai.bol.ucla.edu/mrpp.txt
> http://lcai.bol.ucla.edu/programs.html
> http://lcai.bol.ucla.edu/mrpp.pdf
>
> HTH.
>
>
>
> Dates, Brian wrote
>>
>> Thanks for the responses. The task is the skewness of a Pearson Type
>> III distribution for Multiresponse Randomized Block Permutation
>> Procedures (MRBP), so definitely 'long and boring'. I'll just tough
> it
>> out with the formulae I have and try to figure out the Fortran for
> some
>> assistance. Thanks again.
>>
>> Brian
>>
>>
>>
>>
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>> David Marso
>> Sent: Thursday, June 28, 2012 10:26 PM
>> To: SPSSX-L@.UGA
>> Subject: Re: Converting Fortran to SPSS
>>
>> I know you would never think that I would think what would result
> should
>> be a
>> 'line by line' but a first mental pass would be and 10 lines of
> FORTRAN
>> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
>> SWEEP....
>> etc (MATRIX doesn't have all that many built in linear algebra
> functions
>> per
>> se)
>> Depending upon the level of internal documentation, actual supporting
>> math
>> equations etc it could be a few spins of the Ouija board and a few
> spent
>> black candles before a blaring epiphany crafts an algorithm.
>> Of course one must also consider that MATRIX doesn't *directly*
> support
>> subroutines. OTOH I have clever ways around that.
>> In summary I agree 'translate the code to algorithms, and program the
>> algorithms.'
>> OTOH I want to add screw the code! What is the original
> algorithm/math
>> and
>> code directly for the jugular!
>>
>>
>> Rich Ulrich-2 wrote
>>>
>>> I haven't used Fortran since they still spelled it FORTRAN -
>>> the vector operators are probably transparent; but I
>>> wonder how people use assignment of pointers. - So, the
>>> version of Fortran might be relevant.
>>>
>>> Since the Matrix language has matrix operators, I suggest
>>> that line-by-line is an awkward way to translate old, primitive
>>> Fortran, the stuff that looks mainly like Basis. Is that what
>>> it is? Instead, translate the code to algorithms, and program
>>> the algorithms.
>>>
>>> --
>>> Rich Ulrich
>>>
>>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>>> From: david.marso@
>>>> Subject: Re: Converting Fortran to SPSS
>>>> To: SPSSX-L@.UGA
>>>>
>>>> What does it do?
>>>> How long is the code?
>>>> Are there verifiable test 'data' to confirm whatever might result?
>>>> ---
>>>> No such guide exists to my knowledge. Pretty much would need to
>> convert
>>>> line by line.
>>>> If it is short and sweet, does something interesting and has
>> verifiable
>>>> confirmation post it here and I'd be happy to look at it and post
>>>> suggestions (probably short of actually writing the code).
>>>> If it is long and boring I'd consider doing it for a reasonable
>>>> consulting
>>>> fee.
>>>> I haven't looked at FORTRAN in over 20 years but it's like writing a
>>>> tricycle.
>>>>
>>>>
>>>> Dates, Brian wrote
>>>> >
>>>> > I have a task on which I'm working in matrix mode in SPSS. The
>> only
>>>> > solution that's available in publication regarding this task is
>> written
>>>> > in Fortran, with which I'm woefully inadequate. Does a guide
> exist
>>>> > which assists in the conversion of Fortran code to SPSS syntax,
>> similar
>>>> > to the guides that are available comparing SPSS to SAS or R?
>> Thanks.
>>>> >
>>>> >
>>> ...
>>>
>>
>>
>> --
>> View this message in context:
>>
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
>> -tp5713876p5713883.html
>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>
>
> -----
> --
> Bruce Weaver
> bweaver@
> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
> -tp5713876p5713891.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS-tp5713876p5713903.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 09:14:23 -0700
From: Robert Jones <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

Alternately, you could use frequencies for the mean and suppress "display
frequency tables". For a string field, you will just get the N and count of
missing values, while for a numeric you will get the mean but that only
occupies one line of the report.
Robert

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897p5713906.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 12:51:02 -0400
From: "Dates, Brian" <[hidden email]>
Subject: Re: Converting Fortran to SPSS

David,

The source of this information is John Pezzullo's website of free
statistical software: http://statpages.org/javasta2.html . In the first
section on the left, the next to last entry is titled Statistical
Software by Paul W. Mielke Jr. The address for the software is
http://www.stat.colostate.edu/~mielke/permute.html (so you can skip
going to Johns' site). On the webpage, I used the dos/win link. MRBP is
in the resulting PRGMS2 folder.

Brian

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
David Marso
Sent: Friday, June 29, 2012 11:57 AM
To: [hidden email]
Subject: Re: Converting Fortran to SPSS

FWIW: I located Blossom software :
http://www.fort.usgs.gov/Products/Software/blossom/
where would one find a link for the source code?

Dates, Brian wrote
>
> Bruce,
>
> Thanks. Yes, I have copies, and it's somewhat helpful, but the
blocking
> factor changes the way that all of the cumulants are calculated. The
> Fortran code I have is from the Blossom software. I think between the
> two, I can get through it. I was looking for a time-saver, something
> like the "R for SPSS and SAS Users" document. I'm very rusty on
> Fortran. I really appreciate the suggestion. When I'm finished I'll
> let the list know, or contact Raynald to see if he wants to post it,
in

> case anyone is interested in the macro.
>
> Brian
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> Bruce Weaver
> Sent: Friday, June 29, 2012 9:16 AM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> Have you come across Li Cai's MRPP macro?
>
> http://lcai.bol.ucla.edu/mrpp.txt
> http://lcai.bol.ucla.edu/programs.html
> http://lcai.bol.ucla.edu/mrpp.pdf
>
> HTH.
>
>
>
> Dates, Brian wrote
>>
>> Thanks for the responses. The task is the skewness of a Pearson Type
>> III distribution for Multiresponse Randomized Block Permutation
>> Procedures (MRBP), so definitely 'long and boring'. I'll just tough
> it
>> out with the formulae I have and try to figure out the Fortran for
> some
>> assistance. Thanks again.
>>
>> Brian
>>
>>
>>
>>
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>> David Marso
>> Sent: Thursday, June 28, 2012 10:26 PM
>> To: SPSSX-L@.UGA
>> Subject: Re: Converting Fortran to SPSS
>>
>> I know you would never think that I would think what would result
> should
>> be a
>> 'line by line' but a first mental pass would be and 10 lines of
> FORTRAN
>> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
>> SWEEP....
>> etc (MATRIX doesn't have all that many built in linear algebra
> functions
>> per
>> se)
>> Depending upon the level of internal documentation, actual supporting
>> math
>> equations etc it could be a few spins of the Ouija board and a few
> spent
>> black candles before a blaring epiphany crafts an algorithm.
>> Of course one must also consider that MATRIX doesn't *directly*
> support
>> subroutines. OTOH I have clever ways around that.
>> In summary I agree 'translate the code to algorithms, and program the
>> algorithms.'
>> OTOH I want to add screw the code! What is the original
> algorithm/math
>> and
>> code directly for the jugular!
>>
>>
>> Rich Ulrich-2 wrote
>>>
>>> I haven't used Fortran since they still spelled it FORTRAN -
>>> the vector operators are probably transparent; but I
>>> wonder how people use assignment of pointers. - So, the
>>> version of Fortran might be relevant.
>>>
>>> Since the Matrix language has matrix operators, I suggest
>>> that line-by-line is an awkward way to translate old, primitive
>>> Fortran, the stuff that looks mainly like Basis. Is that what
>>> it is? Instead, translate the code to algorithms, and program
>>> the algorithms.
>>>
>>> --
>>> Rich Ulrich
>>>
>>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>>> From: david.marso@
>>>> Subject: Re: Converting Fortran to SPSS
>>>> To: SPSSX-L@.UGA
>>>>
>>>> What does it do?
>>>> How long is the code?
>>>> Are there verifiable test 'data' to confirm whatever might result?
>>>> ---
>>>> No such guide exists to my knowledge. Pretty much would need to
>> convert
>>>> line by line.
>>>> If it is short and sweet, does something interesting and has
>> verifiable
>>>> confirmation post it here and I'd be happy to look at it and post
>>>> suggestions (probably short of actually writing the code).
>>>> If it is long and boring I'd consider doing it for a reasonable
>>>> consulting
>>>> fee.
>>>> I haven't looked at FORTRAN in over 20 years but it's like writing

>>>> tricycle.
>>>>
>>>>
>>>> Dates, Brian wrote
>>>> >
>>>> > I have a task on which I'm working in matrix mode in SPSS. The
>> only
>>>> > solution that's available in publication regarding this task is
>> written
>>>> > in Fortran, with which I'm woefully inadequate. Does a guide
> exist
>>>> > which assists in the conversion of Fortran code to SPSS syntax,
>> similar
>>>> > to the guides that are available comparing SPSS to SAS or R?
>> Thanks.
>>>> >
>>>> >
>>> ...
>>>
>>
>>
>> --
>> View this message in context:
>>
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

>> -tp5713876p5713883.html
>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>
>
> -----
> --
> Bruce Weaver
> bweaver@
> http://sites.google.com/a/lakeheadu.ca/bweaver/
>
> "When all else fails, RTFM."
>
> NOTE: My Hotmail account is not monitored regularly.
> To send me an e-mail, please use the address shown above.
>
> --
> View this message in context:
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

> -tp5713876p5713891.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
-tp5713876p5713903.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

------------------------------

Date: Fri, 29 Jun 2012 10:42:35 -0700
From: David Marso <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

As Jon said AGGREGATE...
HOWEVER!!!
Violating the generally acceptable social convention of
"If you can't say anything good don't say anything at all".

I am NOT sure what 'problem' such a tool is intended/likely to solve or it's
'real' world applicability.
Is there ANY good/necessary reason that values must be consecutive?
How is it that the hypothetical 36,37 should be removed from the list of
245? Seems to violate basic principles of data integrity, ability to track
from data origins to final deliverable(s).
----
What happens when/if you *EVER* need to merge multiple files which have
*NOT* been processed IDENTICALLY by this 'tool'.
What happens if/when multiple users hammer on the same file at the same
time?
What do you tell your client when many of the numbers they thought they had
DON'T agree?
Short of going BACK to the original source files and tracking down many tiny
annoying discrepancies such reconciliation is likely to be hopeless/futile.
Usually data is best left alone/as is/unmolested and/or 'corrected' prior
to importation into SPSS.
Basically in a nutshell, Such a tool permitted to run wild in any group
setting or on data of any sort of complexity (relational tables, multiple
data waves) without a precise audit trail and backup techniques promises to
create MANY more problems than it is likely to solve.
Sorry for the overall negative tone of this missive but this is one of those
potential '... where angels fear to tread' situations and you may not have
thought through the possible terrible implications.
I have a RULE: If I can't recreate a deliverable from start to finish from
raw data sources with syntax I have failed to create a
reproducible/verifiable piece of work and have dropped the ball.

I think I will now STFU and return to our previously scheduled programming.

Tom1234 wrote

>
> Is there any way in syntax(or otherwise) to select (and count) the number
> of values in a variable?
> I understand that VALUE LABELS is to assign them, but how would I select
> already existing values/Value labels?
>
> The reason being is:
> I'm trying to write a script in SAX/WinWrap basic that allows me to
> auto-code the value labels of variables in three ways:
> 1 - Via input box: User is prompted to enter variable and then a loop
> selects the next available value and prompts the user to enter a value
> label for each value that hasn't got a label already.
> 2 - By directly copying: User is prompted to enter variable and then a
> loop reads the value, if it is a string the script puts a upper case
> letter at the start and replaces any ^s with 's (a common error when
> exporting from cati or excel) and then displays a message box saying the
> coding is complete.
> 3 - Shift the value labels by a specified amount, user is prompted to
> enter the number (positive or negative) that they want the labels to move
> (very usefull when recoding large numbers of values) i.e. if you have 245
> values and you remove number 36 and 37 from the list, you'd have to redo
> the value labels of every value after 35 so that they were 2 places closer
> if you wanted consecutive values.
>
> Here's part of my proto/pseudo code:
>
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897p5713909.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 11:03:50 -0700
From: David Marso <[hidden email]>
Subject: Re: Converting Fortran to SPSS

Thanks Brian,
I downloaded the source and scanned through it without going blond.
All in all it looks fairly straightforward with a single caveat.
The *entire* bloody thing uses 3 dimensional arrays.
SPSS MATRIX only understands 2 dimensions so you will need to carefully
redesign it and decide how best to factor out the additional dimension. One
can easily map 2 dimensional array to one dimension and indeed 3->2 or 3-> 1
but I guarantee such an approach will impact performance.

1 2
3 4
5 6
--> 1 2 3 4 5 6
(i-1)*NJ + j
(NJ=2 in this case -number of columns).

--HTH--

Dates, Brian wrote

>
> David,
>
> The source of this information is John Pezzullo's website of free
> statistical software: http://statpages.org/javasta2.html . In the first
> section on the left, the next to last entry is titled Statistical
> Software by Paul W. Mielke Jr. The address for the software is
> http://www.stat.colostate.edu/~mielke/permute.html (so you can skip
> going to Johns' site). On the webpage, I used the dos/win link. MRBP is
> in the resulting PRGMS2 folder.
>
> Brian
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> David Marso
> Sent: Friday, June 29, 2012 11:57 AM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> FWIW: I located Blossom software :
> http://www.fort.usgs.gov/Products/Software/blossom/
> where would one find a link for the source code?
>
> Dates, Brian wrote
>>
>> Bruce,
>>
>> Thanks. Yes, I have copies, and it's somewhat helpful, but the
> blocking
>> factor changes the way that all of the cumulants are calculated. The
>> Fortran code I have is from the Blossom software. I think between the
>> two, I can get through it. I was looking for a time-saver, something
>> like the "R for SPSS and SAS Users" document. I'm very rusty on
>> Fortran. I really appreciate the suggestion. When I'm finished I'll
>> let the list know, or contact Raynald to see if he wants to post it,
> in
>> case anyone is interested in the macro.
>>
>> Brian
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>> Bruce Weaver
>> Sent: Friday, June 29, 2012 9:16 AM
>> To: SPSSX-L@.UGA
>> Subject: Re: Converting Fortran to SPSS
>>
>> Have you come across Li Cai's MRPP macro?
>>
>> http://lcai.bol.ucla.edu/mrpp.txt
>> http://lcai.bol.ucla.edu/programs.html
>> http://lcai.bol.ucla.edu/mrpp.pdf
>>
>> HTH.
>>
>>
>>
>> Dates, Brian wrote
>>>
>>> Thanks for the responses. The task is the skewness of a Pearson Type
>>> III distribution for Multiresponse Randomized Block Permutation
>>> Procedures (MRBP), so definitely 'long and boring'. I'll just tough
>> it
>>> out with the formulae I have and try to figure out the Fortran for
>> some
>>> assistance. Thanks again.
>>>
>>> Brian
>>>
>>>
>>>
>>>
>>>
>>> -----Original Message-----
>>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>>> David Marso
>>> Sent: Thursday, June 28, 2012 10:26 PM
>>> To: SPSSX-L@.UGA
>>> Subject: Re: Converting Fortran to SPSS
>>>
>>> I know you would never think that I would think what would result
>> should
>>> be a
>>> 'line by line' but a first mental pass would be and 10 lines of
>> FORTRAN
>>> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
>>> SWEEP....
>>> etc (MATRIX doesn't have all that many built in linear algebra
>> functions
>>> per
>>> se)
>>> Depending upon the level of internal documentation, actual supporting
>>> math
>>> equations etc it could be a few spins of the Ouija board and a few
>> spent
>>> black candles before a blaring epiphany crafts an algorithm.
>>> Of course one must also consider that MATRIX doesn't *directly*
>> support
>>> subroutines. OTOH I have clever ways around that.
>>> In summary I agree 'translate the code to algorithms, and program the
>>> algorithms.'
>>> OTOH I want to add screw the code! What is the original
>> algorithm/math
>>> and
>>> code directly for the jugular!
>>>
>>>
>>> Rich Ulrich-2 wrote
>>>>
>>>> I haven't used Fortran since they still spelled it FORTRAN -
>>>> the vector operators are probably transparent; but I
>>>> wonder how people use assignment of pointers. - So, the
>>>> version of Fortran might be relevant.
>>>>
>>>> Since the Matrix language has matrix operators, I suggest
>>>> that line-by-line is an awkward way to translate old, primitive
>>>> Fortran, the stuff that looks mainly like Basis. Is that what
>>>> it is? Instead, translate the code to algorithms, and program
>>>> the algorithms.
>>>>
>>>> --
>>>> Rich Ulrich
>>>>
>>>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>>>> From: david.marso@
>>>>> Subject: Re: Converting Fortran to SPSS
>>>>> To: SPSSX-L@.UGA
>>>>>
>>>>> What does it do?
>>>>> How long is the code?
>>>>> Are there verifiable test 'data' to confirm whatever might result?
>>>>> ---
>>>>> No such guide exists to my knowledge. Pretty much would need to
>>> convert
>>>>> line by line.
>>>>> If it is short and sweet, does something interesting and has
>>> verifiable
>>>>> confirmation post it here and I'd be happy to look at it and post
>>>>> suggestions (probably short of actually writing the code).
>>>>> If it is long and boring I'd consider doing it for a reasonable
>>>>> consulting
>>>>> fee.
>>>>> I haven't looked at FORTRAN in over 20 years but it's like writing
> a
>>>>> tricycle.
>>>>>
>>>>>
>>>>> Dates, Brian wrote
>>>>> >
>>>>> > I have a task on which I'm working in matrix mode in SPSS. The
>>> only
>>>>> > solution that's available in publication regarding this task is
>>> written
>>>>> > in Fortran, with which I'm woefully inadequate. Does a guide
>> exist
>>>>> > which assists in the conversion of Fortran code to SPSS syntax,
>>> similar
>>>>> > to the guides that are available comparing SPSS to SAS or R?
>>> Thanks.
>>>>> >
>>>>> >
>>>> ...
>>>>
>>>
>>>
>>> --
>>> View this message in context:
>>>
>>
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
>>> -tp5713876p5713883.html
>>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>> bweaver@
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> View this message in context:
>>
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
>> -tp5713876p5713891.html
>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>
>
> --
> View this message in context:
> http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
> -tp5713876p5713903.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS-tp5713876p5713910.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 14:06:32 -0400
From: Art Kendall <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix"><font size="+1">Amen!<br>
And unless you can do that you cannot pass a quality assurance
review.<br>
Long time list members know that one of my soapboxes is that QA
review should be built into the very first intros to SPSS.<br>
(In accounting "referencing" is standard practice. That is
accounting's terminology for QA review.)<br>
<br>
Also without a full audit trail you cannot go back and do it
right.<br>
</font>
<pre class="moz-signature" cols="72">Art Kendall
Social Research Consultants</pre>
On 6/29/2012 1:42 PM, David Marso wrote:<br>
</div>
<blockquote cite="mid:[hidden email]"
type="cite">
<pre wrap="">I have a RULE: If I can't recreate a deliverable from start to finish from
raw data sources with syntax I have failed to create a
reproducible/verifiable piece of work and have dropped the ball.</pre>
</blockquote>
<br>
<br>
</body>
</html>

------------------------------

Date: Fri, 29 Jun 2012 14:17:59 -0400
From: "Dates, Brian" <[hidden email]>
Subject: Re: Converting Fortran to SPSS

David,

You're welcome...and thank-you!!! I'll be more specific next time. I
appreciate all the time you've spent on this. Take care and have a nice
weekend.

Brian

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
David Marso
Sent: Friday, June 29, 2012 2:04 PM
To: [hidden email]
Subject: Re: Converting Fortran to SPSS

Thanks Brian,
I downloaded the source and scanned through it without going blond.
All in all it looks fairly straightforward with a single caveat.
The *entire* bloody thing uses 3 dimensional arrays.
SPSS MATRIX only understands 2 dimensions so you will need to carefully
redesign it and decide how best to factor out the additional dimension.
One
can easily map 2 dimensional array to one dimension and indeed 3->2 or
3-> 1
but I guarantee such an approach will impact performance.

1 2
3 4
5 6
--> 1 2 3 4 5 6
(i-1)*NJ + j
(NJ=2 in this case -number of columns).

--HTH--

Dates, Brian wrote
>
> David,
>
> The source of this information is John Pezzullo's website of free
> statistical software: http://statpages.org/javasta2.html . In the
first
> section on the left, the next to last entry is titled Statistical
> Software by Paul W. Mielke Jr. The address for the software is
> http://www.stat.colostate.edu/~mielke/permute.html (so you can skip
> going to Johns' site). On the webpage, I used the dos/win link. MRBP
is

> in the resulting PRGMS2 folder.
>
> Brian
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
> David Marso
> Sent: Friday, June 29, 2012 11:57 AM
> To: SPSSX-L@.UGA
> Subject: Re: Converting Fortran to SPSS
>
> FWIW: I located Blossom software :
> http://www.fort.usgs.gov/Products/Software/blossom/
> where would one find a link for the source code?
>
> Dates, Brian wrote
>>
>> Bruce,
>>
>> Thanks. Yes, I have copies, and it's somewhat helpful, but the
> blocking
>> factor changes the way that all of the cumulants are calculated. The
>> Fortran code I have is from the Blossom software. I think between

the

>> two, I can get through it. I was looking for a time-saver, something
>> like the "R for SPSS and SAS Users" document. I'm very rusty on
>> Fortran. I really appreciate the suggestion. When I'm finished I'll
>> let the list know, or contact Raynald to see if he wants to post it,
> in
>> case anyone is interested in the macro.
>>
>> Brian
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>> Bruce Weaver
>> Sent: Friday, June 29, 2012 9:16 AM
>> To: SPSSX-L@.UGA
>> Subject: Re: Converting Fortran to SPSS
>>
>> Have you come across Li Cai's MRPP macro?
>>
>> http://lcai.bol.ucla.edu/mrpp.txt
>> http://lcai.bol.ucla.edu/programs.html
>> http://lcai.bol.ucla.edu/mrpp.pdf
>>
>> HTH.
>>
>>
>>
>> Dates, Brian wrote
>>>
>>> Thanks for the responses. The task is the skewness of a Pearson

Type

>>> III distribution for Multiresponse Randomized Block Permutation
>>> Procedures (MRBP), so definitely 'long and boring'. I'll just tough
>> it
>>> out with the formulae I have and try to figure out the Fortran for
>> some
>>> assistance. Thanks again.
>>>
>>> Brian
>>>
>>>
>>>
>>>
>>>
>>> -----Original Message-----
>>> From: SPSSX(r) Discussion [mailto:SPSSX-L@.UGA] On Behalf Of
>>> David Marso
>>> Sent: Thursday, June 28, 2012 10:26 PM
>>> To: SPSSX-L@.UGA
>>> Subject: Re: Converting Fortran to SPSS
>>>
>>> I know you would never think that I would think what would result
>> should
>>> be a
>>> 'line by line' but a first mental pass would be and 10 lines of
>> FORTRAN
>>> would likely end up as a CSUM, MSUM... 50 might be CALL EIGEN...10
>>> SWEEP....
>>> etc (MATRIX doesn't have all that many built in linear algebra
>> functions
>>> per
>>> se)
>>> Depending upon the level of internal documentation, actual

supporting
>>> math
>>> equations etc it could be a few spins of the Ouija board and a few
>> spent
>>> black candles before a blaring epiphany crafts an algorithm.
>>> Of course one must also consider that MATRIX doesn't *directly*
>> support
>>> subroutines. OTOH I have clever ways around that.
>>> In summary I agree 'translate the code to algorithms, and program
the

>>> algorithms.'
>>> OTOH I want to add screw the code! What is the original
>> algorithm/math
>>> and
>>> code directly for the jugular!
>>>
>>>
>>> Rich Ulrich-2 wrote
>>>>
>>>> I haven't used Fortran since they still spelled it FORTRAN -
>>>> the vector operators are probably transparent; but I
>>>> wonder how people use assignment of pointers. - So, the
>>>> version of Fortran might be relevant.
>>>>
>>>> Since the Matrix language has matrix operators, I suggest
>>>> that line-by-line is an awkward way to translate old, primitive
>>>> Fortran, the stuff that looks mainly like Basis. Is that what
>>>> it is? Instead, translate the code to algorithms, and program
>>>> the algorithms.
>>>>
>>>> --
>>>> Rich Ulrich
>>>>
>>>>> Date: Thu, 28 Jun 2012 15:10:33 -0700
>>>>> From: david.marso@
>>>>> Subject: Re: Converting Fortran to SPSS
>>>>> To: SPSSX-L@.UGA
>>>>>
>>>>> What does it do?
>>>>> How long is the code?
>>>>> Are there verifiable test 'data' to confirm whatever might result?
>>>>> ---
>>>>> No such guide exists to my knowledge. Pretty much would need to
>>> convert
>>>>> line by line.
>>>>> If it is short and sweet, does something interesting and has
>>> verifiable
>>>>> confirmation post it here and I'd be happy to look at it and post
>>>>> suggestions (probably short of actually writing the code).
>>>>> If it is long and boring I'd consider doing it for a reasonable
>>>>> consulting
>>>>> fee.
>>>>> I haven't looked at FORTRAN in over 20 years but it's like writing
> a
>>>>> tricycle.
>>>>>
>>>>>
>>>>> Dates, Brian wrote
>>>>> >
>>>>> > I have a task on which I'm working in matrix mode in SPSS. The
>>> only
>>>>> > solution that's available in publication regarding this task is
>>> written
>>>>> > in Fortran, with which I'm woefully inadequate. Does a guide
>> exist
>>>>> > which assists in the conversion of Fortran code to SPSS syntax,
>>> similar
>>>>> > to the guides that are available comparing SPSS to SAS or R?
>>> Thanks.
>>>>> >
>>>>> >
>>>> ...
>>>>
>>>
>>>
>>> --
>>> View this message in context:
>>>
>>
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

>>> -tp5713876p5713883.html
>>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>>
>>> =====================
>>> To manage your subscription to SPSSX-L, send a message to
>>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>>> command. To leave the list, send the command
>>> SIGNOFF SPSSX-L
>>> For a list of commands to manage subscriptions, send the command
>>> INFO REFCARD
>>>
>>
>>
>> -----
>> --
>> Bruce Weaver
>> bweaver@
>> http://sites.google.com/a/lakeheadu.ca/bweaver/
>>
>> "When all else fails, RTFM."
>>
>> NOTE: My Hotmail account is not monitored regularly.
>> To send me an e-mail, please use the address shown above.
>>
>> --
>> View this message in context:
>>
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

>> -tp5713876p5713891.html
>> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>> =====================
>> To manage your subscription to SPSSX-L, send a message to
>> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
>> command. To leave the list, send the command
>> SIGNOFF SPSSX-L
>> For a list of commands to manage subscriptions, send the command
>> INFO REFCARD
>>
>
>
> --
> View this message in context:
>

http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS

> -tp5713876p5713903.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Converting-Fortran-to-SPSS
-tp5713876p5713910.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

------------------------------

Date: Fri, 29 Jun 2012 14:33:44 -0400
From: Art Kendall <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix"><font size="+1">If I understand
correctly #3 can be done something like this, assuming that a
value exists with the desired label.<br>
note that variables are not written over.<br>
<br>
data list list/x (f2).<br>
begin data<br>
1<br>
2<br>
3<br>
4<br>
5<br>
6<br>
7<br>
8<br>
9<br>
10<br>
11<br>
end data.<br>
numeric y(f2).<br>
value labels x y<br>
1 'abc'<br>
2 'ABC'<br>
3 'Abc'<br>
4 'def'<br>
5 'DEF'<br>
6 'DeF'<br>
7 'dEF'<br>
8 'GHI'<br>
9 'ghi'<br>
10 'Ghi'<br>
11 'ghI'.<br>
*recode to the value for all caps.<br>
recode x (1 thru 3=2)(4 thru 7=5)(8 thru 11=8) into y.<br>
execute.<br>
autorecode variables=y /into z.<br>
frequencies variables = x y z.<br>
<br>
</font>
<pre class="moz-signature" cols="72">Art Kendall
Social Research Consultants</pre>
On 6/29/2012 10:52 AM, Tom1234 wrote:<br>
</div>
<blockquote cite="mid:[hidden email]"
type="cite">
<pre wrap="">Is there any way in syntax(or otherwise) to select (and count) the number of
values in a variable?
I understand that VALUE LABELS is to assign them, but how would I select
already existing values/Value labels?

The reason being is:
I'm trying to write a script in SAX/WinWrap basic that allows me to
auto-code the value labels of variables in three ways:
1 - Via input box: User is prompted to enter variable and then a loop
selects the next available value and prompts the user to enter a value label
for each value that hasn't got a label already.
2 - By directly copying: User is prompted to enter variable and then a loop
reads the value, if it is a string the script puts a upper case letter at
the start and replaces any ^s with 's (a common error when exporting from
cati or excel) and then displays a message box saying the coding is
complete.
3 - Shift the value labels by a specified amount, user is prompted to enter
the number (positive or negative) that they want the labels to move (very
usefull when recoding large numbers of values) i.e. if you have 245 values
and you remove number 36 and 37 from the list, you'd have to redo the value
labels of every value after 35 so that they were 2 places closer if you
wanted consecutive values.

Here's part of my proto/pseudo code:

-----

"Lo there do I see my father. Lo there do I see my mother and my sisters and my brothers. Lo there do I see the line of my people, back to the beginning. Lo, they do call to me, they bid me take my place among them, in the Halls of Valhalla, where the brave may live...forever."
--
View this message in context: <a class="moz-txt-link-freetext" href="http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html">http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897.html</a>
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

=====================
To manage your subscription to SPSSX-L, send a message to
<a class="moz-txt-link-abbreviated" href="mailto:[hidden email]">[hidden email]</a> (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD

</pre>
</blockquote>
<br>
<br>
</body>
</html>

------------------------------

Date: Fri, 29 Jun 2012 12:14:29 -0700
From: David Marso <[hidden email]>
Subject: Re: Spss Syntax select all values in a variable?

Brings back one terrible memory from the late 90's (when I was a Sr
Consultant at SPSS in Chicago).
Urgent call from back east to Chicago from HUGE marketing research client
(MRC) who will remain nameless suggesting possible unspecified (bugs)
terrible showstopping problems with SPSS.
Flew out the same night got picked up by MRC limo and crashed in a hotel.
Arrived 8:00 AM next day ready to rock and roll...
Well, their HUGE client was unable to reconcile their reports with MRC's
reports...
I sat down with their 'analyst' and was appalled to witness her process.
She was MANUALLY copying/pasting HUGE blocks of crap from Excel into her
master SPSS data file and repeatedly saving over the same copy. WOW!!! WTF
am I supposed to do for these people?
Well, I tried to describe some fundamentals such as the UPDATE command but
all I got were those scary deer in the headlights zombie stare... *BRAINS* I
want BRAINS!!!
Later that day I had to go with them to an URGENT client meeting where the
goal was to explain the numerous glaring discrepancies in a 500 page report.
Being the diplomatic, restrained person I am I tried to say as little as
possible during that uncomfortable session faintly murmuring something about
'I only saw this for the first time this AM and am attempting to develop
some theories about the problem but that will take some time,.... hence I
can provide no conclusive suggestions or certifiable remedy at present blah
blah blah...snooze (GET ME OUT OF HERE!!!).
Flew home that night with a giant headache.
Next day MRC's 'analyst's' manager called something like 6 times wanting an
explanation of what the problem had been and if we had determined any
workaround.
WOW!!! Response(s): There is NO problem with the software, there is a
problem with your analyst.
Is there anything that can be done?
1. Sure, fly me out again and I'll train your analyst how to properly
manage data and hopefully wean her of MANY terrible habits and potentially
catastrophic practices.
2. Fire the doofus and hire a reasonably competent person to do the job.
3. Prepare to lose more clients if this is your process.
They went with option 1.

Art Kendall wrote

>
> Amen!
> And unless you can do that you cannot pass a quality assurance
> review.
> Long time list members know that one of my soapboxes is that QA
> review should be built into the very first intros to SPSS.
> (In accounting "referencing" is standard practice. That is
> accounting's terminology for QA review.)
>
> Also without a full audit trail you cannot go back and do it
> right.
>
> Art Kendall
> Social Research Consultants
> On 6/29/2012 1:42 PM, David Marso wrote:
>
>
> I have a RULE: If I can't recreate a deliverable from start to
> finish from
> raw data sources with syntax I have failed to create a
> reproducible/verifiable piece of work and have dropped the ball.
>
>
>
>
>
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> LISTSERV@.UGA (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Spss-Syntax-select-all-values-in-a-variable-tp5713897p5713914.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Sat, 30 Jun 2012 01:59:43 +0530
From: Rajeshms <[hidden email]>
Subject: Importing excel

--0015173febeeef9b2204c3a24ea3
Content-Type: text/plain; charset=ISO-8859-1

Hi all,

I am facing problem while importing excel sheet data. Lets say for example,
In excel we have labels and other unwanted names and texts , so while
importing we have to clean the excel sheet and make ready to get it
imported into spss.Is there any option so that I can over come this time
consuming procedure.

thanking you for comments,

--
Rajesh M S

--0015173febeeef9b2204c3a24ea3
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

Hi all,<div><br></div><div>I am facing problem while importing excel sheet =
data. Lets say for example, In excel we have labels and other unwanted name=
s and texts , so while importing we have to clean the excel sheet and make =
ready to get it imported into spss.Is there any option so that I can over c=
ome this time consuming procedure.</div>
<div><br></div><div>thanking you for comments,</div><div><div><br></div>-- =
<br><div><font color=3D"#666666" size=3D"1" face=3D"comic sans ms,sans-seri=
f"><span></span><span></span>Rajesh M S</font></div><div><font color=3D"#66=
6666" size=3D"1" face=3D"comic sans ms,sans-serif"><br>
</font></div><div><font color=3D"#666666" face=3D"'comic sans ms', =
sans-serif" size=3D"1"><br></font></div><br>
</div>

--0015173febeeef9b2204c3a24ea3--

------------------------------

Date: Fri, 29 Jun 2012 13:36:26 -0700
From: "J. R. Carroll" <[hidden email]>
Subject: Re: Importing excel

--e89a8ff253aef5f19304c3a266c6
Content-Type: text/plain; charset=ISO-8859-1

I'm going to pull a David M and say:

Don't screw up your Excel?

=P

Then I'm going to pull a Justin (me) and say:

Excel is great for exporting out in csv or some other delimited format, I
always default to Python as a knee-jerk solution because I work a lot with
it and feel comfortable work in it - I know there exists Syntax solutions
for parsing - but Python could delete unwanted data and save the resulting
data to a flat file for easy importing into SPSS. The script would take
~20 min to write (and that includes watching TV in the background), and
would take about 2 sec to run (depending on the size of your datafile).
It's another step, but if the Excel file is being pulled from a database
with garbage in it that you dont want (or someone is preparing it for you
and cannot deliver it in the format you want) this would be a easy solution
and save you time.

-J

----

J. R. Carroll
Cell: (650) 776-6613
Email: [hidden email]
[hidden email]
[hidden email]
[hidden email]

On Fri, Jun 29, 2012 at 1:29 PM, Rajeshms <[hidden email]> wrote:

> Hi all,
>
> I am facing problem while importing excel sheet data. Lets say for
> example, In excel we have labels and other unwanted names and texts , so
> while importing we have to clean the excel sheet and make ready to get it
> imported into spss.Is there any option so that I can over come this time
> consuming procedure.
>
> thanking you for comments,
>
> --
> Rajesh M S
>
>
>
>

--e89a8ff253aef5f19304c3a266c6
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

I'm going to pull a David M and say:<div><br></div><div>Don't screw=
up your Excel?=A0</div><div><br></div><div>=3DP</div><div><br></div><div>T=
hen I'm going to pull a Justin (me) and say:</div><div><br></div><div>E=
xcel is great for exporting out in csv or some other delimited format, I al=
ways default to Python as a knee-jerk solution because I work a lot with it=
and feel comfortable work in it - I know there exists Syntax solutions for=
parsing - but Python could delete unwanted data and save the resulting dat=
a to a flat file for easy importing into SPSS. =A0The script would take ~20=
min to write (and that includes watching TV in the background), and would =
take about 2 sec to run (depending on the size of your datafile). =A0It&#39=
;s another step, but if the Excel file is being pulled from a database with=
garbage in it that you dont want (or someone is preparing it for you and c=
annot deliver it in the format you want) this would be a easy solution and =
save you time. =A0</div>
<div><br></div><div>-J</div><div><br clear=3D"all">----<br>
<img src=3D"http://jrcresearch.net/blog/wp-content/uploads/2010/07/sig.gif"=
width=3D"200" height=3D"67"><br clear=3D"all"><br>
J. R. Carroll<div>
<div>Cell:=A0 (650) 776-6613</div>
<div>Email: <a href=3D"mailto:[hidden email]" target=3D"_blank">=
[hidden email]</a></div>
<div>=A0=A0 =A0 =A0 =A0 =A0<a href=3D"mailto:[hidden email]" target=
=3D"_blank">[hidden email]</a></div>
<div>=A0=A0 =A0 =A0 =A0 =A0<a href=3D"mailto:[hidden email]" target=3D"=
_blank">[hidden email]</a></div></div><div>=A0 =A0 =A0 =A0 =A0 <a href=
=3D"mailto:[hidden email]" target=3D"_blank">jcarroll@comirates=
ting.com</a></div><div><br>
</div><br>
<br><br><div class=3D"gmail_quote">On Fri, Jun 29, 2012 at 1:29 PM, Rajeshm=
s <span dir=3D"ltr"><<a href=3D"mailto:[hidden email]" target=3D"=
_blank">[hidden email]</a>></span> wrote:<br><blockquote class=3D=
"gmail_quote" style=3D"margin:0 0 0 .8ex;border-left:1px #ccc solid;padding=
-left:1ex">
Hi all,<div><br></div><div>I am facing problem while importing excel sheet =
data. Lets say for example, In excel we have labels and other unwanted name=
s and texts , so while importing we have to clean the excel sheet and make =
ready to get it imported into spss.Is there any option so that I can over c=
ome this time consuming procedure.</div>

<div><br></div><div>thanking you for comments,</div><span class=3D"HOEnZb">=
<font color=3D"#888888"><div><div><br></div>-- <br><div><font color=3D"#666=
666" size=3D"1" face=3D"comic sans ms,sans-serif"><span></span><span></span=
>Rajesh M S</font></div>
<div><font color=3D"#666666" size=3D"1" face=3D"comic sans ms,sans-serif"><=
br>
</font></div><div><font color=3D"#666666" face=3D"'comic sans ms', =
sans-serif" size=3D"1"><br></font></div><br>
</div>
</font></span></blockquote></div><br></div>

--e89a8ff253aef5f19304c3a266c6--

------------------------------

Date: Fri, 29 Jun 2012 09:43:07 -0700
From: titopuente <[hidden email]>
Subject: Re: Offset in GEE means contrasts?

Ryan,

Thanks for running a test to verify that it works properly.

I have solved my problem. My original data are in Excel, where I did my log
transformations. I used "lg()" to transform the data, mistakenly thinking
that this returned the natural log (which is "ln()") when the "lg()" code
actually returns the log 10 in Excel. As I imagine most of you are already
aware, for the offset to work it must be the natural log of the independent
variable used as the offset (in this case area sampled to give me #
individuals/square kilometer).

Thanks again to everyone who read my post and especially to those who
replied.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Offset-in-GEE-means-contrasts-tp5713799p5713907.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 12:49:45 -0400
From: J Paul Grayson <[hidden email]>
Subject: Tree analysis failure

--_21ad33c8-c751-4062-bb63-029bf04275aa_
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

Hi=2C

I have SPSS installed on a Mac. With the exception of 'tree
analysis'=2C functions I have tried work. With the tree analysis=2C I'm to=
ld that
the program is running but it freezes and I must force quit the program.
I've tired several data files with the same effect.

What I would like to do if find out if this is a problem common to the Mac.
If so=2C my next steps are obvious.

Thanks=20

Professor J. Paul Grayson=2C

Department of Sociology=2C

York University=2C

4700 Keele St.=2C

Toronto=2C

Ontario=2C

Canada=2C

M3J 1P3.
=

--_21ad33c8-c751-4062-bb63-029bf04275aa_
Content-Type: text/html; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable

<html>
<head>
<style></style></head>
<body class=3D'hmmessage'><div dir=3D'ltr'>
<pre>Hi=2C<br><br>I have SPSS installed on a Mac. With the exception of 't=
ree<br>analysis'=2C functions I have tried work. With the tree analysis=2C=
I'm told that<br>the program is running but it freezes and I must force qu=
it the program.<br>I've tired several data files with the same effect.<br><=
br>What I would like to do if find out if this is a problem common to the M=
ac.<br>If so=2C my next steps are obvious.<br><br>Thanks <br id=3D"ecxFontB=
reak"></pre><br><br>Professor J. Paul Grayson=2C<br>
Department of Sociology=2C<br>
York University=2C<br>
4700 Keele St.=2C<br>
Toronto=2C<br>
Ontario=2C<br>
Canada=2C<br>
M3J 1P3.<br> </div></body>
</html>=

--_21ad33c8-c751-4062-bb63-029bf04275aa_--

------------------------------

Date: Fri, 29 Jun 2012 14:38:40 -0700
From: David Marso <[hidden email]>
Subject: Re: Importing excel

I believe you need to be more specific re what it actually looks like before
and what it should look like later. What does it look like if you don't
clean up the excel and read it straight up.
Might be somewhere between VERY easy (or a royal PIA) to clean it afterwards
within SPSS dependent upon the actual structure of the file.

Rajeshms wrote

>
> Hi all,
>
> I am facing problem while importing excel sheet data. Lets say for
> example,
> In excel we have labels and other unwanted names and texts , so while
> importing we have to clean the excel sheet and make ready to get it
> imported into spss.Is there any option so that I can over come this time
> consuming procedure.
>
> thanking you for comments,
>
> --
> Rajesh M S
>

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Importing-excel-tp5713915p5713918.html
Sent from the SPSSX Discussion mailing list archive at Nabble.com.

------------------------------

Date: Fri, 29 Jun 2012 21:47:05 -0400
From: R B <[hidden email]>
Subject: Re: Offset in GEE means contrasts?

--90e6ba5bb8ebf42ac204c3a6bdec
Content-Type: text/plain; charset=ISO-8859-1

As general guideline, one should first estimate the coefficient of
ln(offset); that is, you should enter ln(offset) as a covariate first. If
the coefficient of ln(offset) is near 1.0 (taking into account the standard
error) AND it makes intuitive sense to treat it as an offset, then it is
probably safe to treat it as such. Put another way, by fixing the
coefficient to 1.0, you are assuming that the response is directly
proportional to the offset (McCullagh & Nelder, 1989).

Ryan

REFERENCE: McCullagh, P. and Nelder, J. A. (1989). Generalized Linear
Models. London: Chapman and Hall.

On Fri, Jun 29, 2012 at 12:43 PM, titopuente <[hidden email]> wrote:
>
> Ryan,
>
> Thanks for running a test to verify that it works properly.
>
> I have solved my problem. My original data are in Excel, where I did my
log
> transformations. I used "lg()" to transform the data, mistakenly thinking
> that this returned the natural log (which is "ln()") when the "lg()" code
> actually returns the log 10 in Excel. As I imagine most of you are already
> aware, for the offset to work it must be the natural log of the
independent
> variable used as the offset (in this case area sampled to give me #
> individuals/square kilometer).
>
> Thanks again to everyone who read my post and especially to those who
> replied.
>
> --
> View this message in context:
http://spssx-discussion.1045642.n5.nabble.com/Offset-in-GEE-means-contrasts-tp5713799p5713907.html
> Sent from the SPSSX Discussion mailing list archive at Nabble.com.
>
> =====================
> To manage your subscription to SPSSX-L, send a message to
> [hidden email] (not to SPSSX-L), with no body text except the
> command. To leave the list, send the command
> SIGNOFF SPSSX-L
> For a list of commands to manage subscriptions, send the command
> INFO REFCARD

--90e6ba5bb8ebf42ac204c3a6bdec
Content-Type: text/html; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable

<div>As=A0general guideline, one=A0should first estimate the coefficient of=
ln(offset); that is, you should enter ln(offset) as a covariate first. If =
the coefficient of ln(offset) is=A0near 1.0 (taking into account the standa=
rd error) AND it makes intuitive sense to treat it as an offset, then it is=
probably safe to treat it as such. Put another way, by=A0fixing the coeffi=
cient to 1.0, you are assuming=A0that the=A0response=A0is directly proporti=
onal to the offset (McCullagh & Nelder, 1989).</div>
<div>=A0</div><div>Ryan</div><div>=A0</div><div>REFERENCE: McCullagh, P. an=
d Nelder, J. A. (1989). Generalized Linear Models. London: Chapman and Hall=
.</div><div>=A0</div><div>On Fri, Jun 29, 2012 at 12:43 PM, titopuente <=
<a href=3D"mailto:[hidden email]">[hidden email]</a>> wrote:</div>
<div>></div><div>> Ryan,</div><div>></div><div>> Thanks for run=
ning a test to verify that it works properly.</div><div>></div><div>>=
I have solved my problem. My original data are in Excel, where I did my lo=
g</div>
<div>> transformations. I used "lg()" to transform the data, m=
istakenly thinking</div><div>> that this returned the natural log (which=
is "ln()") when the "lg()" code</div><div>> actuall=
y returns the log 10 in Excel. As I imagine most of you are already</div>
<div>> aware, for the offset to work it must be the natural log of the i=
ndependent</div><div>> variable used as the offset (in this case area sa=
mpled to give me #</div><div>> individuals/square kilometer).</div><div>
></div><div>> Thanks again to everyone who read my post and especiall=
y to those who</div><div>> replied.</div><div>></div><div>> --</di=
v><div>> View this message in context: <a href=3D"http://spssx-discussio=
n.1045642.n5.nabble.com/Offset-in-GEE-means-contrasts-tp5713799p5713907.htm=
l">http://spssx-discussion.1045642.n5.nabble.com/Offset-in-GEE-means-contra=
sts-tp5713799p5713907.html</a></div>
<div>> Sent from the SPSSX Discussion mailing list archive at Nabble.com=
.</div><div>></div><div>> =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D</div><div>> To manage your subscription to SPSSX-L=
, send a message to</div><div>> <a href=3D"mailto:[hidden email].=
EDU">[hidden email]</a> (not to SPSSX-L), with no body text exce=
pt the</div>
<div>> command. To leave the list, send the command</div><div>> SIGNO=
FF SPSSX-L</div><div>> For a list of commands to manage subscriptions, s=
end the command</div><div>> INFO REFCARD</div><div>=A0</div><div>=A0</di=
v>

--90e6ba5bb8ebf42ac204c3a6bdec--

------------------------------

End of SPSSX-L Digest - 28 Jun 2012 to 29 Jun 2012 (#2012-180)
**************************************************************

=====================
To manage your subscription to SPSSX-L, send a message to
[hidden email] (not to SPSSX-L), with no body text except the
command. To leave the list, send the command
SIGNOFF SPSSX-L
For a list of commands to manage subscriptions, send the command
INFO REFCARD