Simulation with SPSS

[Humphrey Paulie]

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[Art Kendall]

Yes you probably need to use syntax.

Simulations can be done in SPSS, but the term "simulate" covers a a lot of ground. Please be more specific about what you want to simulate.

Art Kendall
Social Research Consultants


On 9/28/2010 3:58 AM, Humphrey Paulie wrote:

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[John Exton]

I found an old thread apparently starting a discussion on simulation, but the OP didn't respond to a clarification question, so it seems to have died long ago.  I am interested in creating simulated data sets for student use.  I want to ensure that the data sets have the appropriate characteristics for weekly discussion.  I assume there is a mechanism for creating such data sets in SPSS/PASW, but I do not know how to do it.  Ideally, I would like to begin with very simple descriptive statistics but "non-small" data sets (not really large, but a couple hundred observations would be nice).

Can anyone point me in the right direction for a start?  I assume this is something that must be done through syntax rather than menus, but I haven't been able to find a primer that discusses it so far.

[David Marso]

Here is the results of a search of this group for INPUT PROGRAM (the key to data simulation in SPSS).
Happy browsing!
--
http://spssx-discussion.1045642.n5.nabble.com/template/NamlServlet.jtp?macro=search_page&node=1068821&query=INPUT+PROGRAM&sort=date

[Bruce Weaver]

Please provide more information.

1. Is it a two-group (or more) pre-post design?

2. What kind of analysis are you intending to do?  ANCOVA?

3. It's not clear what you mean when you say "the means of the tests are not significant".  If you are doing ANCOVA, do you mean the F-test for Group should not be statistically significant?  

4. What are the sample sizes?  (The answer to this has a bearing on Q3, assuming you did mean you want the F-test for group to be non-significant.)

5. What is the correlation between pre- and post-test scores?  


The following links might be useful:

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/CorrData.SPS

https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/files/Two%20correlated%20samples%20macro.sps?attredirects=0&d=1

HTH.

Humphrey Paulie wrote

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[David Marso]

;-)
Hi Bruce, The post you responded to is over a year and a half old (Sept 2010).
Looks like this thread is a revived zombie.
--

Bruce Weaver wrote

Please provide more information.

1. Is it a two-group (or more) pre-post design?

2. What kind of analysis are you intending to do?  ANCOVA?

3. It's not clear what you mean when you say "the means of the tests are not significant".  If you are doing ANCOVA, do you mean the F-test for Group should not be statistically significant?  

4. What are the sample sizes?  (The answer to this has a bearing on Q3, assuming you did mean you want the F-test for group to be non-significant.)

5. What is the correlation between pre- and post-test scores?  


The following links might be useful:

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/CorrData.SPS

https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/files/Two%20correlated%20samples%20macro.sps?attredirects=0&d=1

HTH.

Humphrey Paulie wrote

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[Ryan]

Humphrey,

The following syntax will generate data which meets your specification of a non-significant paired t-test. Write back if you have any questions about the syntax.

HTH, 

Ryan

--

*Generate data for a pair t-test.

set seed 65923454.

new file.

inp pro.

 compute subject=-99.

 compute time = -99.

 compute x1 = -99.

 compute x2 = -99.

 compute e1 = -99.

 compute e2 = -99.

 compute sigma = 1.

 compute rho = 0.50.

 compute a11 = 1.

 compute a21 = rho.

 compute a22 = sqrt(1 - rho**2).

 leave subject to a22.

  loop subject= 1 to 500.

  compute x1 = rv.normal(0,1).

  compute x2 = rv.normal(0,1).

  compute e1 = sigma * a11*x1.

  compute e2 = sigma * (a21*x1 + a22*x2).

 loop time = 1 to 2.

 compute y = 1.5 + 0.0*(time=1) + e1*(time=1) + e2*(time=2).

 end case.

 end loop.

end loop.

end file.

end inp pro.

exe.

delete variables x1 x2 sigma rho a11 a21 a22 e1 e2.

*Restrcture dataset from long to wide.

SORT CASES BY subject time.

CASESTOVARS

  /ID=subject

  /INDEX=time

  /GROUPBY=VARIABLE.

*Run paired t-test.

T-TEST PAIRS=y.1.00 WITH y.2.00 (PAIRED)

  /CRITERIA=CI(.9500)

  /MISSING=ANALYSIS.

On Tue, Sep 28, 2010 at 3:58 AM, Humphrey Paulie <[hidden email]> wrote:

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[Bruce Weaver]

Ah yes, so it is!  Didn't notice the date.  

David Marso wrote

;-)
Hi Bruce, The post you responded to is over a year and a half old (Sept 2010).
Looks like this thread is a revived zombie.
--

Bruce Weaver wrote

Please provide more information.

1. Is it a two-group (or more) pre-post design?

2. What kind of analysis are you intending to do?  ANCOVA?

3. It's not clear what you mean when you say "the means of the tests are not significant".  If you are doing ANCOVA, do you mean the F-test for Group should not be statistically significant?  

4. What are the sample sizes?  (The answer to this has a bearing on Q3, assuming you did mean you want the F-test for group to be non-significant.)

5. What is the correlation between pre- and post-test scores?  


The following links might be useful:

http://www.uvm.edu/~dhowell/StatPages/More_Stuff/CorrData.SPS

https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/files/Two%20correlated%20samples%20macro.sps?attredirects=0&d=1

HTH.

Humphrey Paulie wrote

Dear colleagues,
I want to simulate data with SPSS. I want to have a dataset on a test (pre-test and post-test) in such a way that the means of the tests are not significant. I don't know the exactly where and which icons are for simulation in SPSS. Do I need syntax for this? I'd be thankful if you give me the syntax if syntax is required.
Regards
Humphrey

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

[Jon K Peck]

If you want random data, you can install the MakeDataWithCases dialog box from the SPSS Community website (www.ibm.com/developerworks/spssdevcentral).  It will generate data from any of 22 (or is it 23) probability distributions.  It can generate correlated or uncorrelated data.  Prerequisites are detailed in the download.

It works by generating an INPUT PROGRAM and then optionally using MATRIX to generate correlations by linear transformations.  That, of course, changes some of the distribution families.  I'm thinking about some more sophisticated ways of generating correlated variables.

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




From:        John Exton <[hidden email]>
To:        [hidden email]
Date:        02/21/2012 07:44 PM
Subject:        [SPSSX-L] Simulation with SPSS
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

I found an old thread apparently starting a discussion on simulation, but the
OP didn't respond to a clarification question, so it seems to have died long
ago.  I am interested in creating simulated data sets for student use.  I
want to ensure that the data sets have the appropriate characteristics for
weekly discussion.  I assume there is a mechanism for creating such data
sets in SPSS/PASW, but I do not know how to do it.  Ideally, I would like to
begin with very simple descriptive statistics but "non-small" data sets (not
really large, but a couple hundred observations would be nice).

Can anyone point me in the right direction for a start?  I assume this is
something that must be done through syntax rather than menus, but I haven't
been able to find a primer that discusses it so far.

--
View this message in context: http://spssx-discussion.1045642.n5.nabble.com/Simulation-with-SPSS-tp2856363p5503497.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

[Ryan]

Are you guys telling me that I provided a solution to a problem that was posted over a year ago?! I'll be certain to check the date of each message in the future. Not sure how such an old message ended up in my mailbox today. Oh well. 

Ryan

On Tue, Feb 21, 2012 at 9:23 PM, Bruce Weaver <[hidden email]> wrote:

Ah yes, so it is!  Didn't notice the date.


David Marso wrote

>
> ;-)
> Hi Bruce, The post you responded to is over a year and a half old (Sept
> 2010).
> Looks like this thread is a revived zombie.
> --
>
> Bruce Weaver wrote
>>
>> Please provide more information.
>>
>> 1. Is it a two-group (or more) pre-post design?
>>
>> 2. What kind of analysis are you intending to do?  ANCOVA?
>>
>> 3. It's not clear what you mean when you say "the means of the tests are
>> not significant".  If you are doing ANCOVA, do you mean the F-test for
>> Group should not be statistically significant?
>>
>> 4. What are the sample sizes?  (The answer to this has a bearing on Q3,
>> assuming you did mean you want the F-test for group to be
>> non-significant.)
>>
>> 5. What is the correlation between pre- and post-test scores?
>>
>>
>> The following links might be useful:
>>
>> http://www.uvm.edu/~dhowell/StatPages/More_Stuff/CorrData.SPS
>>
>> https://sites.google.com/a/lakeheadu.ca/bweaver/Home/statistics/files/Two%20correlated%20samples%20macro.sps?attredirects=0&d=1
>>
>> HTH.
>>
>>
>>
>> Humphrey Paulie wrote
>>>
>>> Dear colleagues,
>>> I want to simulate data with SPSS. I want to have a dataset on a test
>>> (pre-test and post-test) in such a way that the means of the tests are
>>> not significant. I don't know the exactly where and which icons are for
>>> simulation in SPSS. Do I need syntax for this? I'd be thankful if you
>>> give me the syntax if syntax is required.
>>> Regards
>>> Humphrey
>>>
>>> =====================
>>> 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/Simulation-with-SPSS-tp2856363p5503927.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