Complex Sample Statistics

[SUBSCRIBE SPSSX-L Anonymous]

I am attempting to learn about the Complex Samples Statistics module
of SPSS.  Though I have taken many courses in statistics, it appears
awkward that one would need a separate module to handle the process of
sampling.  That is, the researcher should (1) specify the experimental
design, (2) draw a random sample according to the design, and (3) run
the analyses.  Many of the analyses in SPSS handle that input data as
necessary for doing the analysis.  How is the complex samples module
different?  Why is it necessary to address sampling as a separate
topic?  Does the module integrate with the other procedures of SPSS?

Your response will be appreciated.


Sincerely,
Jon

=====================
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

[ViAnn Beadle]

If you have anything other than a random sample, tests of significance are
biased. Go here for more information:

http://www.spss.com/complex_samples/


-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
SUBSCRIBE SPSSX-L Anonymous
Sent: Thursday, November 15, 2007 7:16 AM
To: [hidden email]
Subject: Complex Sample Statistics

I am attempting to learn about the Complex Samples Statistics module
of SPSS.  Though I have taken many courses in statistics, it appears
awkward that one would need a separate module to handle the process of
sampling.  That is, the researcher should (1) specify the experimental
design, (2) draw a random sample according to the design, and (3) run
the analyses.  Many of the analyses in SPSS handle that input data as
necessary for doing the analysis.  How is the complex samples module
different?  Why is it necessary to address sampling as a separate
topic?  Does the module integrate with the other procedures of SPSS?

Your response will be appreciated.


Sincerely,
Jon

=====================
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

=====================
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

[Lacay, Phebe]

Hi All,

I have a group of ID (9 digit alpha) that start with something other
than a number.  How do I change these ID to start with a '9' if G,R, or
@ appear in the first digit?

Thanks as always,
Phebe

=====================
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

[ViAnn Beadle]

Look at the REPLACE() function in help.

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of
Lacay, Phebe
Sent: Thursday, November 15, 2007 8:06 AM
To: [hidden email]
Subject: Changing first digit

Hi All,

I have a group of ID (9 digit alpha) that start with something other
than a number.  How do I change these ID to start with a '9' if G,R, or
@ appear in the first digit?

Thanks as always,
Phebe

=====================
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

=====================
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

[Spousta Jan]

Easily:

if any(substr(ID,1,1),"G","R","@") substr(ID,1,1) = "9".
exe.

Best regaards,

Jan

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Lacay, Phebe
Sent: Thursday, November 15, 2007 4:06 PM
To: [hidden email]
Subject: Changing first digit

Hi All,

I have a group of ID (9 digit alpha) that start with something other than a number.  How do I change these ID to start with a '9' if G,R, or @ appear in the first digit?

Thanks as always,
Phebe

=====================
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



_____

Tato zpráva a všechny připojené soubory jsou důvěrné a určené výlučně adresátovi(-ům). Jestliže nejste oprávněným adresátem, je zakázáno jakékoliv zveřejňování, zprostředkování nebo jiné použití těchto informací. Jestliže jste tento mail dostali neoprávněně, prosím, uvědomte odesilatele a smažte zprávu i přiložené soubory. Odesilatel nezodpovídá za jakékoliv chyby nebo opomenutí způsobené tímto přenosem.

This message and any attached files are confidential and intended solely for the addressee(s). Any publication, transmission or other use of the information by a person or entity other than the intended addressee is prohibited. If you receive this in error please contact the sender and delete the message as well as all attached documents. The sender does not accept liability for any errors or omissions as a result of the transmission.

-.- --

=====================
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

[Lacay, Phebe]

Perfect! Thanks, Jan.



-----Original Message-----
From: Spousta Jan [mailto:[hidden email]]
Sent: Thursday, November 15, 2007 10:10 AM
To: Lacay, Phebe; [hidden email]
Subject: RE: Changing first digit

Easily:

if any(substr(ID,1,1),"G","R","@") substr(ID,1,1) = "9".
exe.

Best regaards,

Jan

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Lacay, Phebe
Sent: Thursday, November 15, 2007 4:06 PM
To: [hidden email]
Subject: Changing first digit

Hi All,

I have a group of ID (9 digit alpha) that start with something other than a number.  How do I change these ID to start with a '9' if G,R, or @ appear in the first digit?

Thanks as always,
Phebe

=====================
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



_____

Tato zpráva a všechny připojené soubory jsou důvěrné a určené výlučně adresátovi(-ům). Jestliže nejste oprávněným adresátem, je zakázáno jakékoliv zveřejňování, zprostředkování nebo jiné použití těchto informací. Jestliže jste tento mail dostali neoprávněně, prosím, uvědomte odesilatele a smažte zprávu i přiložené soubory. Odesilatel nezodpovídá za jakékoliv chyby nebo opomenutí způsobené tímto přenosem.

This message and any attached files are confidential and intended solely for the addressee(s). Any publication, transmission or other use of the information by a person or entity other than the intended addressee is prohibited. If you receive this in error please contact the sender and delete the message as well as all attached documents. The sender does not accept liability for any errors or omissions as a result of the transmission.

-.- --

=====================
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

[Keith McCormick]

Hi Jon,

The following thought experiment might be useful. In teaching this
module, I often run everything with or without the module. The results
can be instructive:

If you do a simple random sample it doesn't mater (as ViAnn points out).

If you run anything else, some of the basic statistics will not be
right. If you draw upon your stats skills and calculate the weights
(perhaps with syntax), and use the weights command, the basic
statistics will be correct. But ... the standard errors around the
statistics will still be wrong. Thus, the tests of significance will
be wrong.

When you use the module, you begin with the sampling frame, not the
sample. The tool helps you draw the sample (which might be easy
enough), but also creates a "plan file". The plan file automatically
insures that the weights, statistics, and standard errors will be
correct when the time arrives to do the analysis phase. The analysis
is also done in the module, not in the standard SPSS menus.

That the best "short version" I could come up with. I hope that helps.

Best, Keith
www.keithmccormick.com


On 11/15/07, SUBSCRIBE SPSSX-L Anonymous <[hidden email]> wrote:

> I am attempting to learn about the Complex Samples Statistics module
> of SPSS.  Though I have taken many courses in statistics, it appears
> awkward that one would need a separate module to handle the process of
> sampling.  That is, the researcher should (1) specify the experimental
> design, (2) draw a random sample according to the design, and (3) run
> the analyses.  Many of the analyses in SPSS handle that input data as
> necessary for doing the analysis.  How is the complex samples module
> different?  Why is it necessary to address sampling as a separate
> topic?  Does the module integrate with the other procedures of SPSS?
>
> Your response will be appreciated.
>
>
> Sincerely,
> Jon
>
> =====================
> 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
>

=====================
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

[SUBSCRIBE SPSSX-L Anonymous]

Thank you!

=====================
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

[Lacay, Phebe]

Hi All,

 

I need some help creating a table.

 

The 3 variables are

COUNTY

CREDITS

FTPTIND

 

I would like to break out the sum of CREDITS and count by the sum of
FTPTIND for each COUNTY.

 

So for example:

 

I have

ID    COUNTY      CREDITS     FTPTIND

1     COUNTY1     10          1

2     COUNTY1     10          1

3     COUNTY1     10          2

4     COUNTY1     10          1

5     COUNTY2     10          1

6     COUNTY2     10          1

7     COUNTY2     10          2

 

 

I would like it to look something like this:

 

            FTPTIND=1   FTPTIND=1   FTPTIND=2   FTPTIND=2   Total Total

            N           CREDITS     N           CREDITS     N
CREDITS    

COUNTY1     3           30          1           10          4     40

COUNTY2     2           20          1           10          3     30

 

 

 

Any help in the matter would be MUCH appreciated!

Thanks;

Phebe

 

 

====================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