SPSSX Discussion

For those in need of running SAS using an SPSS file

Classic

List

Threaded

14 messages Options

Joseph Teitelman temp2

For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav file, the following steps are required.

Note that I discovered this information from the very popular "Little SAS Book."

1) first save your spss file as a portable file * it has the extension por.
2) use the following SAS syntax:
a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
b) to use the print procedure in SAS type
PROC PRINT DATA = myspss._FIRST_;
c) to list the contents of the spss file (the variables and their attributes type:
PROC CONTENTS DATA = myspss._FIRST_;

d) to convert the spss portable file to a SAS data set, type the following:

DATA 'c:\MySASlib\spsspor';
SET myspss._FIRST_;

e) the output will contain a list of observations/ records grouped by each variable in the data set.

The next procedure * Proc contents will produce the variable #, the variable name, the type of variable (num or char, e.g.), Length of each variable, position of each variable, format of each variable. and label for each variable.

Obviously, the information I provided is not intended for those who prefer to use SPSS rather than SAS. It's for those like me, who were forced to learn SPSS for some reason, such as a job, but would like to analyze the data using SAS.

I hope this proves helpful for those of you in the same shoes as myself.

I am not advocating the use of SAS over SPSS; rather I am merely showing that for those who prefer SAS over SPSS, it's easy to read an SPSS file using SAS, after saving the SPSS file as a portable document.

The portable file will have the extension "por".

jemiller

Re: For those in need of running SAS using an SPSS file

WOW, I am SHOCKED that someone could consider themselves to be 'forced' to
use SPSS! I love the program ;) just kidding with ya!

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Joseph Teitelman temp2
Sent: Friday, July 14, 2006 10:19 AM
To: [hidden email]
Subject: [SPSSX-L] For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my
employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav
file, the following steps are required.

Note that I discovered this information from the very popular "Little SAS
Book."

1) first save your spss file as a portable file * it has the extension por.
2) use the following SAS syntax:
a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
b) to use the print procedure in SAS type
PROC PRINT DATA = myspss._FIRST_;
c) to list the contents of the spss file (the variables and their attributes
type:
PROC CONTENTS DATA = myspss._FIRST_;

d) to convert the spss portable file to a SAS data set, type the following:

DATA 'c:\MySASlib\spsspor';
SET myspss._FIRST_;

e) the output will contain a list of observations/ records grouped by each
variable in the data set.

The next procedure * Proc contents will produce the variable #, the variable
name, the type of variable (num or char, e.g.), Length of each variable,
position of each variable, format of each variable. and label for each
variable.

Obviously, the information I provided is not intended for those who prefer
to use SPSS rather than SAS. It's for those like me, who were forced to
learn SPSS for some reason, such as a job, but would like to analyze the
data using SAS.

I hope this proves helpful for those of you in the same shoes as myself.

I am not advocating the use of SAS over SPSS; rather I am merely showing
that for those who prefer SAS over SPSS, it's easy to read an SPSS file
using SAS, after saving the SPSS file as a portable document.

The portable file will have the extension "por".

Oliver, Richard

Re: For those in need of running SAS using an SPSS file

In reply to this post by Joseph Teitelman temp2

No doubt you have some good reason for not simply saving the data in SAS format from SPSS using either the standard Save Data dialog and selecting the appropriate SAS format or by using the SAVE TRANSLATE command. I'm reasonably sure this is at least mentioned in the SPSS help system. But maybe you tried this and it didn't work? In theory, there should be no need to save the SPSS data in portable format, and there are many instances in which you probably wouldn't want to use SPSS portable format. But if there are problems with the facilities provided for saving data in SAS format, we'd certainly like to know about them.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Joseph Teitelman temp2
Sent: Friday, July 14, 2006 11:19 AM
To: [hidden email]
Subject: For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav file, the following steps are required.

Note that I discovered this information from the very popular "Little SAS Book."

1) first save your spss file as a portable file * it has the extension por.
2) use the following SAS syntax:
a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
b) to use the print procedure in SAS type
PROC PRINT DATA = myspss._FIRST_;
c) to list the contents of the spss file (the variables and their attributes type:
PROC CONTENTS DATA = myspss._FIRST_;

d) to convert the spss portable file to a SAS data set, type the following:

DATA 'c:\MySASlib\spsspor';
SET myspss._FIRST_;

e) the output will contain a list of observations/ records grouped by each variable in the data set.

The next procedure * Proc contents will produce the variable #, the variable name, the type of variable (num or char, e.g.), Length of each variable, position of each variable, format of each variable. and label for each variable.

Obviously, the information I provided is not intended for those who prefer to use SPSS rather than SAS. It's for those like me, who were forced to learn SPSS for some reason, such as a job, but would like to analyze the data using SAS.

I hope this proves helpful for those of you in the same shoes as myself.

I am not advocating the use of SAS over SPSS; rather I am merely showing that for those who prefer SAS over SPSS, it's easy to read an SPSS file using SAS, after saving the SPSS file as a portable document.

The portable file will have the extension "por".

Staffan Lindberg

SV: For those in need of running SAS using an SPSS file

In reply to this post by Joseph Teitelman temp2

Hi!

Being in a somewhat similar situation (although a SPSS user) I often find
myself having to convert SPSS-files to SAS datasets for SAS-people. The
easiest solution (at least for me) is to use a conversion program. I use
DBMSCOPY but there are others (StatTransfer among others). With DMBSCOPY I
can even convert SPSS Value Labels to SAS Formats. This is accomplished by
DMBSCOPY generating a SAS program that you can run in SAS thus getting the
Formats.

An even faster way is to to use the ability of SPSS 14 (and perhaps earlier)
to write SAS files in different formats (although I don't know if the Value
labels are converted).

best

Staffan Lindberg
National Institute of Public Health
Sweden

-----Ursprungligt meddelande-----
Från: SPSSX(r) Discussion [mailto:[hidden email]] För Joseph
Teitelman temp2
Skickat: den 14 juli 2006 18:19
Till: [hidden email]
Ämne: For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my
employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav
file, the following steps are required.

Note that I discovered this information from the very popular "Little SAS
Book."

1) first save your spss file as a portable file * it has the extension por.
2) use the following SAS syntax:
a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
b) to use the print procedure in SAS type
PROC PRINT DATA = myspss._FIRST_;
c) to list the contents of the spss file (the variables and their attributes
type: PROC CONTENTS DATA = myspss._FIRST_;

d) to convert the spss portable file to a SAS data set, type the following:

DATA 'c:\MySASlib\spsspor';
SET myspss._FIRST_;

e) the output will contain a list of observations/ records grouped by each
variable in the data set.

The next procedure * Proc contents will produce the variable #, the variable
name, the type of variable (num or char, e.g.), Length of each variable,
position of each variable, format of each variable. and label for each
variable.

Obviously, the information I provided is not intended for those who prefer
to use SPSS rather than SAS. It's for those like me, who were forced to
learn SPSS for some reason, such as a job, but would like to analyze the
data using SAS.

I hope this proves helpful for those of you in the same shoes as myself.

I am not advocating the use of SAS over SPSS; rather I am merely showing
that for those who prefer SAS over SPSS, it's easy to read an SPSS file
using SAS, after saving the SPSS file as a portable document.

The portable file will have the extension "por".

Peck, Jon

Re: For those in need of running SAS using an SPSS file

In reply to this post by Joseph Teitelman temp2

Note that SPSS can write (and read) native SAS files of various formats directly, so the portable file route is probably not necessary.

Regards,
Jon Peck
SPSS

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Joseph Teitelman temp2
Sent: Friday, July 14, 2006 11:19 AM
To: [hidden email]
Subject: [SPSSX-L] For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav file, the following steps are required.

Oliver, Richard

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

The SPSS facility for writing SAS-format data files includes the ability to write value labels to a SAS formats file. This has been true for quite a few years (it's not new in SPSS 14).

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Staffan Lindberg
Sent: Friday, July 14, 2006 12:44 PM
To: [hidden email]
Subject: SV: For those in need of running SAS using an SPSS file

Hi!

Being in a somewhat similar situation (although a SPSS user) I often find myself having to convert SPSS-files to SAS datasets for SAS-people. The easiest solution (at least for me) is to use a conversion program. I use DBMSCOPY but there are others (StatTransfer among others). With DMBSCOPY I can even convert SPSS Value Labels to SAS Formats. This is accomplished by DMBSCOPY generating a SAS program that you can run in SAS thus getting the Formats.

An even faster way is to to use the ability of SPSS 14 (and perhaps earlier) to write SAS files in different formats (although I don't know if the Value labels are converted).

best

Staffan Lindberg
National Institute of Public Health
Sweden

-----Ursprungligt meddelande-----
Från: SPSSX(r) Discussion [mailto:[hidden email]] För Joseph Teitelman temp2
Skickat: den 14 juli 2006 18:19
Till: [hidden email]
Ämne: For those in need of running SAS using an SPSS file

For the past 2 months, I've been forced to learn how to use SPSS, since my employer uses SPSS solely.

For those interested in analyzing data in SAS created as an SPSS *.sav file, the following steps are required.

Note that I discovered this information from the very popular "Little SAS Book."

1) first save your spss file as a portable file * it has the extension por.
2) use the following SAS syntax:
a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
b) to use the print procedure in SAS type
PROC PRINT DATA = myspss._FIRST_;
c) to list the contents of the spss file (the variables and their attributes
type: PROC CONTENTS DATA = myspss._FIRST_;

d) to convert the spss portable file to a SAS data set, type the following:

DATA 'c:\MySASlib\spsspor';
SET myspss._FIRST_;

e) the output will contain a list of observations/ records grouped by each variable in the data set.

The next procedure * Proc contents will produce the variable #, the variable name, the type of variable (num or char, e.g.), Length of each variable, position of each variable, format of each variable. and label for each variable.

Obviously, the information I provided is not intended for those who prefer to use SPSS rather than SAS. It's for those like me, who were forced to learn SPSS for some reason, such as a job, but would like to analyze the data using SAS.

I hope this proves helpful for those of you in the same shoes as myself.

I am not advocating the use of SAS over SPSS; rather I am merely showing that for those who prefer SAS over SPSS, it's easy to read an SPSS file using SAS, after saving the SPSS file as a portable document.

The portable file will have the extension "por".

Jason Burke

Re: SV: For those in need of running SAS using an SPSS file

If your employer forces you to use SPSS, who pays the SAS license fees
every year?

On 7/15/06, Oliver, Richard <[hidden email]> wrote:

> The SPSS facility for writing SAS-format data files includes the ability to write value labels to a SAS formats file. This has been true for quite a few years (it's not new in SPSS 14).
>
> -----Original Message-----
> From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Staffan Lindberg
> Sent: Friday, July 14, 2006 12:44 PM
> To: [hidden email]
> Subject: SV: For those in need of running SAS using an SPSS file
>
> Hi!
>
> Being in a somewhat similar situation (although a SPSS user) I often find myself having to convert SPSS-files to SAS datasets for SAS-people. The easiest solution (at least for me) is to use a conversion program. I use DBMSCOPY but there are others (StatTransfer among others). With DMBSCOPY I can even convert SPSS Value Labels to SAS Formats. This is accomplished by DMBSCOPY generating a SAS program that you can run in SAS thus getting the Formats.
>
> An even faster way is to to use the ability of SPSS 14 (and perhaps earlier) to write SAS files in different formats (although I don't know if the Value labels are converted).
>
> best
>
> Staffan Lindberg
> National Institute of Public Health
> Sweden
>
> -----Ursprungligt meddelande-----
> Från: SPSSX(r) Discussion [mailto:[hidden email]] För Joseph Teitelman temp2
> Skickat: den 14 juli 2006 18:19
> Till: [hidden email]
> Ämne: For those in need of running SAS using an SPSS file
>
>
> For the past 2 months, I've been forced to learn how to use SPSS, since my employer uses SPSS solely.
>
> For those interested in analyzing data in SAS created as an SPSS *.sav file, the following steps are required.
>
> Note that I discovered this information from the very popular "Little SAS Book."
>
> 1) first save your spss file as a portable file * it has the extension por.
> 2) use the following SAS syntax:
> a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
> b) to use the print procedure in SAS type
> PROC PRINT DATA = myspss._FIRST_;
> c) to list the contents of the spss file (the variables and their attributes
> type: PROC CONTENTS DATA = myspss._FIRST_;
>
> d) to convert the spss portable file to a SAS data set, type the following:
>
> DATA 'c:\MySASlib\spsspor';
> SET myspss._FIRST_;
>
>
> e) the output will contain a list of observations/ records grouped by each variable in the data set.
>
> The next procedure * Proc contents will produce the variable #, the variable name, the type of variable (num or char, e.g.), Length of each variable, position of each variable, format of each variable. and label for each variable.
>
> Obviously, the information I provided is not intended for those who prefer to use SPSS rather than SAS. It's for those like me, who were forced to learn SPSS for some reason, such as a job, but would like to analyze the data using SAS.
>
> I hope this proves helpful for those of you in the same shoes as myself.
>
> I am not advocating the use of SAS over SPSS; rather I am merely showing that for those who prefer SAS over SPSS, it's easy to read an SPSS file using SAS, after saving the SPSS file as a portable document.
>
> The portable file will have the extension "por".
>

Joseph Teitelman temp2

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

That's an obnoxious question; I used SAS as a student first in a sociology Ph.D. program and then in a statistics graduate program. As a graduate student studying statistics, I was able to obtain SAS free of charge, and have continued to use the licensed SAS program since completing my statistics degree.

It is true that my employer is not licensing SAS; rather my employer is licensing SPSS only.

And if you must know, the vast majority of statistics graduate programs prefer SAS to SPSS. In fact, they tend to support SAS, SPLUS, and Stata, but tend not to support SPSS.

The question is what does this fact say about SPSS when compared to SAS, S-PLUS, and Stata.

Typically SPSS is used in graduate level social science courses, such
as sociology.

Given the above, what can you conclude about SPSS?

joe teitelman

>>> Jason Burke <[hidden email]> 7/14/2006 7:46 PM >>>
If your employer forces you to use SPSS, who pays the SAS license fees
every year?

On 7/15/06, Oliver, Richard <[hidden email]> wrote:

Simon Phillip Freidin

Re: SV: For those in need of running SAS using an SPSS file

For a comparison of the strengths and weaknesses of SAS, SPSS and
STATA see the UCLA report

http://www.ats.ucla.edu/stat/technicalreports/Number1/
ucla_ATSstat_tr1_1.0.pdf

cheers
Simon

On 18/07/2006, at 5:52 AM, Joseph Teitelman temp2 wrote:

> That's an obnoxious question; I used SAS as a student first in a
> sociology Ph.D. program and then in a statistics graduate program.
> As a graduate student studying statistics, I was able to obtain SAS
> free of charge, and have continued to use the licensed SAS program
> since completing my statistics degree.
>
> It is true that my employer is not licensing SAS; rather my
> employer is licensing SPSS only.
>
> And if you must know, the vast majority of statistics graduate
> programs prefer SAS to SPSS. In fact, they tend to support SAS,
> SPLUS, and Stata, but tend not to support SPSS.
>
> The question is what does this fact say about SPSS when compared to
> SAS, S-PLUS, and Stata.
>
> Typically SPSS is used in graduate level social science courses, such
> as sociology.
>
> Given the above, what can you conclude about SPSS?
>
> joe teitelman
>
>
>
>>>> Jason Burke <[hidden email]> 7/14/2006 7:46 PM >>>
> If your employer forces you to use SPSS, who pays the SAS license fees
> every year?
>
>
> On 7/15/06, Oliver, Richard <[hidden email]> wrote:
>> The SPSS facility for writing SAS-format data files includes the
>> ability to write value labels to a SAS formats file. This has been
>> true for quite a few years (it's not new in SPSS 14).
>>
>> -----Original Message-----
>> From: SPSSX(r) Discussion [mailto:[hidden email]] On
>> Behalf Of Staffan Lindberg
>> Sent: Friday, July 14, 2006 12:44 PM
>> To: [hidden email]
>> Subject: SV: For those in need of running SAS using an SPSS file
>>
>> Hi!
>>
>> Being in a somewhat similar situation (although a SPSS user) I
>> often find myself having to convert SPSS-files to SAS datasets for
>> SAS-people. The easiest solution (at least for me) is to use a
>> conversion program. I use DBMSCOPY but there are others
>> (StatTransfer among others). With DMBSCOPY I can even convert SPSS
>> Value Labels to SAS Formats. This is accomplished by DMBSCOPY
>> generating a SAS program that you can run in SAS thus getting the
>> Formats.
>>
>> An even faster way is to to use the ability of SPSS 14 (and
>> perhaps earlier) to write SAS files in different formats (although
>> I don't know if the Value labels are converted).
>>
>> best
>>
>> Staffan Lindberg
>> National Institute of Public Health
>> Sweden
>>
>> -----Ursprungligt meddelande-----
>> Från: SPSSX(r) Discussion [mailto:[hidden email]] För
>> Joseph Teitelman temp2
>> Skickat: den 14 juli 2006 18:19
>> Till: [hidden email]
>> Ämne: For those in need of running SAS using an SPSS file
>>
>>
>> For the past 2 months, I've been forced to learn how to use SPSS,
>> since my employer uses SPSS solely.
>>
>> For those interested in analyzing data in SAS created as an SPSS
>> *.sav file, the following steps are required.
>>
>> Note that I discovered this information from the very popular
>> "Little SAS Book."
>>
>> 1) first save your spss file as a portable file * it has the
>> extension por.
>> 2) use the following SAS syntax:
>> a) LIBNAME myspss SPSS 'c:\Myspsslib\spss.por';
>> b) to use the print procedure in SAS type
>> PROC PRINT DATA = myspss._FIRST_;
>> c) to list the contents of the spss file (the variables and their
>> attributes
>> type: PROC CONTENTS DATA = myspss._FIRST_;
>>
>> d) to convert the spss portable file to a SAS data set, type the
>> following:
>>
>> DATA 'c:\MySASlib\spsspor';
>> SET myspss._FIRST_;
>>
>>
>> e) the output will contain a list of observations/ records grouped
>> by each variable in the data set.
>>
>> The next procedure * Proc contents will produce the variable #,
>> the variable name, the type of variable (num or char, e.g.),
>> Length of each variable, position of each variable, format of each
>> variable. and label for each variable.
>>
>> Obviously, the information I provided is not intended for those
>> who prefer to use SPSS rather than SAS. It's for those like me,
>> who were forced to learn SPSS for some reason, such as a job, but
>> would like to analyze the data using SAS.
>>
>> I hope this proves helpful for those of you in the same shoes as
>> myself.
>>
>> I am not advocating the use of SAS over SPSS; rather I am merely
>> showing that for those who prefer SAS over SPSS, it's easy to read
>> an SPSS file using SAS, after saving the SPSS file as a portable
>> document.
>>
>> The portable file will have the extension "por".
>>

Joseph Teitelman temp2

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

I'd suggest that all those who wish to draw comparisons between SAS and SPSS read the article referenced below.

I was surprised by only one finding. I was under the impression that SAS had substantially increased its capabilities to analyze survey data. Unfortunately, this was not the case. It does make a great deal of sense to use SUDAAN for such purposes.

The information about Stata hardly surprised me. I have been told by statisticians at Duke that many of the younger statisticians prefer Stata.

Based upon the author's conclusions about SPSS, it would appear as if he believes that SPSS is the weakest program among the three.

Finally let me add a few corrections to the article.

First, you can perform logistic regression in SAS using either proc logistic, proc catmod, or proc genmod. You can definitely obtain the predicted probabilities in logistic regression. The author of the article was simply incorrect when he stated that only Stata could perform such computations.

Next, Stat/IML is a matrix programming language which comes along with SAS. It is extremely powerful. SPSS has no matrix programming language. And from what I've been told, neither does Stata.

Finally, S-PLUS is an extremely powerful general statistics software program. It is based upon the language S. And R which is similar to S, is a free program; there have been numerous books and other forms of documentation written about R. For the educated R user, R can perform any of the statistical procedures that any of the other programs can perform.

I am in the process of learning R myself. It's power as a statistical programming language is amazing.

It would appear as if the author of the article favored Stata, and spoke most negatively about SPSS.

Those were my impressions.

Joe Teitelman
>>> Simon Freidin <[hidden email]> 7/17/2006 5:43 PM >>>
For a comparison of the strengths and weaknesses of SAS, SPSS and
STATA see the UCLA report

http://www.ats.ucla.edu/stat/technicalreports/Number1/
ucla_ATSstat_tr1_1.0.pdf

cheers
Simon

On 18/07/2006, at 5:52 AM, Joseph Teitelman temp2 wrote:

jemiller

Re: SV: For those in need of running SAS using an SPSS file

So, your point is? - very possibly the people who are on this list prefer
SPSS for their own reason or there would not be a well populated list like
this nor a SPSS software package.

Why come on the SPSS listserv to get pissed off that some people prefer SPSS
(taking into consideration your other recent posts)?? Very strange
behaviour.

I must say I really appreciate SPSS and the prolific contributors to this
list!
jem

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Joseph Teitelman temp2
Sent: Tuesday, July 18, 2006 8:15 AM
To: [hidden email]
Subject: Re: [SPSSX-L] SV: For those in need of running SAS using an SPSS
file

I'd suggest that all those who wish to draw comparisons between SAS and SPSS
read the article referenced below.

I was surprised by only one finding. I was under the impression that SAS had
substantially increased its capabilities to analyze survey data.
Unfortunately, this was not the case. It does make a great deal of sense
to use SUDAAN for such purposes.

The information about Stata hardly surprised me. I have been told by
statisticians at Duke that many of the younger statisticians prefer Stata.

Based upon the author's conclusions about SPSS, it would appear as if he
believes that SPSS is the weakest program among the three.

Finally let me add a few corrections to the article.

First, you can perform logistic regression in SAS using either proc
logistic, proc catmod, or proc genmod. You can definitely obtain the
predicted probabilities in logistic regression. The author of the article
was simply incorrect when he stated that only Stata could perform such
computations.

Next, Stat/IML is a matrix programming language which comes along with SAS.
It is extremely powerful. SPSS has no matrix programming language. And
from what I've been told, neither does Stata.

Finally, S-PLUS is an extremely powerful general statistics software
program. It is based upon the language S. And R which is similar to S, is
a free program; there have been numerous books and other forms of
documentation written about R. For the educated R user, R can perform any
of the statistical procedures that any of the other programs can perform.

I am in the process of learning R myself. It's power as a statistical
programming language is amazing.

It would appear as if the author of the article favored Stata, and spoke
most negatively about SPSS.

Those were my impressions.

Joe Teitelman
>>> Simon Freidin <[hidden email]> 7/17/2006 5:43 PM >>>
For a comparison of the strengths and weaknesses of SAS, SPSS and
STATA see the UCLA report

http://www.ats.ucla.edu/stat/technicalreports/Number1/
ucla_ATSstat_tr1_1.0.pdf

cheers
Simon

On 18/07/2006, at 5:52 AM, Joseph Teitelman temp2 wrote:

Peck, Jon

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

First, let's correct the facts. SPSS in fact does have a matrix language built in. It has 18 statement types, 59 functions, and 20 operators. Users on this list have posted extensive programs using it.

Second, using the programmability features of SPSS 14, you have access to a vast array of scientifically oriented modules from third parties. For example, scipy and numpy can be downloaded free and used within SPSS.

Here is the summary description of scipy

SciPy is an open source library of scientific tools for Python. SciPy gathers a variety of high level science and engineering modules together as a single package. SciPy provides modules for statistics, optimization, integration, linear algebra, Fourier transforms, signal and image processing, genetic algorithms, ODE solvers, special functions, and more. SciPy requires and supplements NumPy, which provides a multidimensional array object and other basic functionality.

Here are a few random examples of simple things you can do with this library within BEGIN PROGRAM in SPSS. Since you can read the SPSS cases and output in this mode, the inputs can be anything in SPSS.

factorial and combination functions:

import scipy
scipy.factorial(4)
-> array(24.0)
int(scipy.factorial(4))
-> 24
scipy.factorial(4.1)
-> array(27.931753738368371) (Gamma function)
scipy.factorial(50, exact=1)
-> 30414093201713378043612608166064768844377641568960512000000000000L

matrix operations:
import scipy
A = scipy.mat('[1 3 5;2 5 1;2 3 8]')
print A
-> matrix [[1 3 5]
[2 5 1]
[2 3 8]]
print A.I
-> matrix([[-1.48, 0.36, 0.88],
[ 0.56, 0.08, -0.36],
[ 0.16, -0.12, 0.04]])
(A * A.I = identity matrix)
scipy.linalg.det(A)
-> -25

solving linear equations (nonlinear also available):
from scipy import *
A= mat('[1 3 5;2 5 1;2 3 8]')
b = mat('[10;8;3]')
Solve linear equations Ax = b...
A.I*b
or
linalg.solve(A,b)

Regards,
Jon Peck
SPSS

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Joseph Teitelman temp2
Sent: Tuesday, July 18, 2006 9:15 AM
To: [hidden email]
Subject: Re: [SPSSX-L] SV: For those in need of running SAS using an SPSS file
[snip]

Next, Stat/IML is a matrix programming language which comes along with SAS. It is extremely powerful. SPSS has no matrix programming language. And from what I've been told, neither does Stata.
[>>>Peck, Jon] [snip]

Those were my impressions.

Joe Teitelman

Weeks, Kyle

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

The UCLA Technical Report is out of date and, in some cases, inaccurate. We have been working with UCLA to update the document and hope to have it updated soon. Also, there are some inaccuracies in some of the posts below.

For example, SPSS does, in fact, have a MATRIX language and also has access through the Programmability Extension to a wide variety of number libraries. Also, SPSS can save directly as a SAS data file, there is no need to save to a portable file first.

Regards.

Kyle Weeks, Ph.D.
Director of Product Management, SPSS Product Line
Product Management
SPSS Inc.
[hidden email]
www.spss.com
SPSS Inc. helps organizations turn data into insight through predictive analytics.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of jemiller
Sent: Tuesday, July 18, 2006 10:32 AM
To: [hidden email]
Subject: Re: SV: For those in need of running SAS using an SPSS file

So, your point is? - very possibly the people who are on this list prefer
SPSS for their own reason or there would not be a well populated list like
this nor a SPSS software package.

Why come on the SPSS listserv to get pissed off that some people prefer SPSS
(taking into consideration your other recent posts)?? Very strange
behaviour.

I must say I really appreciate SPSS and the prolific contributors to this
list!
jem

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Joseph Teitelman temp2
Sent: Tuesday, July 18, 2006 8:15 AM
To: [hidden email]
Subject: Re: [SPSSX-L] SV: For those in need of running SAS using an SPSS
file

I'd suggest that all those who wish to draw comparisons between SAS and SPSS
read the article referenced below.

I was surprised by only one finding. I was under the impression that SAS had
substantially increased its capabilities to analyze survey data.
Unfortunately, this was not the case. It does make a great deal of sense
to use SUDAAN for such purposes.

The information about Stata hardly surprised me. I have been told by
statisticians at Duke that many of the younger statisticians prefer Stata.

Based upon the author's conclusions about SPSS, it would appear as if he
believes that SPSS is the weakest program among the three.

Finally let me add a few corrections to the article.

First, you can perform logistic regression in SAS using either proc
logistic, proc catmod, or proc genmod. You can definitely obtain the
predicted probabilities in logistic regression. The author of the article
was simply incorrect when he stated that only Stata could perform such
computations.

Next, Stat/IML is a matrix programming language which comes along with SAS.
It is extremely powerful. SPSS has no matrix programming language. And
from what I've been told, neither does Stata.

Finally, S-PLUS is an extremely powerful general statistics software
program. It is based upon the language S. And R which is similar to S, is
a free program; there have been numerous books and other forms of
documentation written about R. For the educated R user, R can perform any
of the statistical procedures that any of the other programs can perform.

I am in the process of learning R myself. It's power as a statistical
programming language is amazing.

It would appear as if the author of the article favored Stata, and spoke
most negatively about SPSS.

Those were my impressions.

Joe Teitelman
>>> Simon Freidin <[hidden email]> 7/17/2006 5:43 PM >>>
For a comparison of the strengths and weaknesses of SAS, SPSS and
STATA see the UCLA report

http://www.ats.ucla.edu/stat/technicalreports/Number1/
ucla_ATSstat_tr1_1.0.pdf

cheers
Simon

On 18/07/2006, at 5:52 AM, Joseph Teitelman temp2 wrote:

Joseph Teitelman temp2

Re: SV: For those in need of running SAS using an SPSS file

In reply to this post by Staffan Lindberg

Yes, according to SPSS, the file could be saved in a number of distinct SAS file formats. Yet, if you follow the directions at the SPSS web site, you'll find that SAS cannot read the SPSS files * apparently saved as SAS data files.

Only if you save an SPSS *.sav file as an SAS portable file are you truly able to read the file in SAS. I believe that this very issue is addressed at either the SPSS website or the SAS website.

The bottom line is that only when saved as an SAS portable file was I ever able to read the document in SAS.

With respect to your matrix programming language, I was obviously incorrect.

>>> "Weeks, Kyle" <[hidden email]> 7/18/2006 12:38 PM >>>
The UCLA Technical Report is out of date and, in some cases, inaccurate. We have been working with UCLA to update the document and hope to have it updated soon. Also, there are some inaccuracies in some of the posts below.

For example, SPSS does, in fact, have a MATRIX language and also has access through the Programmability Extension to a wide variety of number libraries. Also, SPSS can save directly as a SAS data file, there is no need to save to a portable file first.

Regards.

Kyle Weeks, Ph.D.
Director of Product Management, SPSS Product Line
Product Management
SPSS Inc.
[hidden email]
www.spss.com
SPSS Inc. helps organizations turn data into insight through predictive analytics.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of jemiller
Sent: Tuesday, July 18, 2006 10:32 AM
To: [hidden email]
Subject: Re: SV: For those in need of running SAS using an SPSS file

So, your point is? - very possibly the people who are on this list prefer
SPSS for their own reason or there would not be a well populated list like
this nor a SPSS software package.

Why come on the SPSS listserv to get pissed off that some people prefer SPSS
(taking into consideration your other recent posts)?? Very strange
behaviour.

I must say I really appreciate SPSS and the prolific contributors to this
list!
jem

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Joseph Teitelman temp2
Sent: Tuesday, July 18, 2006 8:15 AM
To: [hidden email]
Subject: Re: [SPSSX-L] SV: For those in need of running SAS using an SPSS
file

I'd suggest that all those who wish to draw comparisons between SAS and SPSS
read the article referenced below.

I was surprised by only one finding. I was under the impression that SAS had
substantially increased its capabilities to analyze survey data.
Unfortunately, this was not the case. It does make a great deal of sense
to use SUDAAN for such purposes.

The information about Stata hardly surprised me. I have been told by
statisticians at Duke that many of the younger statisticians prefer Stata.

Based upon the author's conclusions about SPSS, it would appear as if he
believes that SPSS is the weakest program among the three.

Finally let me add a few corrections to the article.

First, you can perform logistic regression in SAS using either proc
logistic, proc catmod, or proc genmod. You can definitely obtain the
predicted probabilities in logistic regression. The author of the article
was simply incorrect when he stated that only Stata could perform such
computations.

Next, Stat/IML is a matrix programming language which comes along with SAS.
It is extremely powerful. SPSS has no matrix programming language. And
from what I've been told, neither does Stata.

Finally, S-PLUS is an extremely powerful general statistics software
program. It is based upon the language S. And R which is similar to S, is
a free program; there have been numerous books and other forms of
documentation written about R. For the educated R user, R can perform any
of the statistical procedures that any of the other programs can perform.

I am in the process of learning R myself. It's power as a statistical
programming language is amazing.

It would appear as if the author of the article favored Stata, and spoke
most negatively about SPSS.

Those were my impressions.

Joe Teitelman
>>> Simon Freidin <[hidden email]> 7/17/2006 5:43 PM >>>
For a comparison of the strengths and weaknesses of SAS, SPSS and
STATA see the UCLA report

http://www.ats.ucla.edu/stat/technicalreports/Number1/
ucla_ATSstat_tr1_1.0.pdf

cheers
Simon

On 18/07/2006, at 5:52 AM, Joseph Teitelman temp2 wrote: