spss mixed: estimate slopes for specific values of continuous IVs

[riding]

Hi everyone,

I’m struggling with SPSS syntax and wonder if someone knows a quick solution? I ran a mixed model on a longitudinal treatment study with 1 outcome, 3 categorical variables, 2 continuous variables and 2 interactions with time.

This is the model:

MIXED health BY treatment gender race WITH time Zattitude
  /CRITERIA=CIN(95) MXITER(100) MXSTEP(10) SCORING(1) SINGULAR(0.000000000001) HCONVERGE(0,
    ABSOLUTE) LCONVERGE(0, ABSOLUTE) PCONVERGE(0.000001, ABSOLUTE)
  /FIXED=treatment gender race time time*treatment time*Zattitude | SSTYPE(3)
  /METHOD=REML
  /PRINT=G  SOLUTION TESTCOV
  /RANDOM=INTERCEPT time | SUBJECT(Patno) COVTYPE(UN).

The time*Zattitude interaction is significant, both are continuous variables. I would like to estimate three slopes (1 for average attitude, +1 SD and -1SD). I know what the command would look like in SAS  (estimate 'AVG CHA' time 1 time*treatment 0.333 0.333 0.334  time*Zattitude 0) , but don’t know how to do this with continuous variables in SPSS. Does the test subcommand apply to categorical levels only?

I would very much appreciate any help, thanks!

riding

[Bruce Weaver]

I have not investigated the /TEST sub-command for MIXED thoroughly, so I can't give a definitive answer to your question.  However, while investigating the /LMATRIX sub-command for UNIANOVA (which is similar in nature to /TEST), I did discover that even though the examples in the documentation are limited to categorical variables only ("factors" as they're called in SPSS), LMATRIX can also handle continuous variables (or "covariates").  So I suspect /TEST can too.  

Ryan B probably has more experience with MIXED than anyone else on the list, and I expect he'll weigh in on this sooner or later.

HTH.


p.s. - To those who maintain the SPSS FM:  Some examples for /LMATRIX and /TEST that include covariates would be quite helpful.  Without them, users may incorrectly conclude that these sub-commands work with factors only.  ;-)

riding wrote

Hi everyone,

I’m struggling with SPSS syntax and wonder if someone knows a quick solution? I ran a mixed model on a longitudinal treatment study with 1 outcome, 3 categorical variables, 2 continuous variables and 2 interactions with time.

This is the model:

MIXED health BY treatment gender race WITH time Zattitude
  /CRITERIA=CIN(95) MXITER(100) MXSTEP(10) SCORING(1) SINGULAR(0.000000000001) HCONVERGE(0,
    ABSOLUTE) LCONVERGE(0, ABSOLUTE) PCONVERGE(0.000001, ABSOLUTE)
  /FIXED=treatment gender race time time*treatment time*Zattitude | SSTYPE(3)
  /METHOD=REML
  /PRINT=G  SOLUTION TESTCOV
  /RANDOM=INTERCEPT time | SUBJECT(Patno) COVTYPE(UN).

The time*Zattitude interaction is significant, both are continuous variables. I would like to estimate three slopes (1 for average attitude, +1 SD and -1SD). I know what the command would look like in SAS  (estimate 'AVG CHA' time 1 time*treatment 0.333 0.333 0.334  time*Zattitude 0) , but don’t know how to do this with continuous variables in SPSS. Does the test subcommand apply to categorical levels only?

I would very much appreciate any help, thanks!

riding

[Ryan]

Answer: You can perform hypothesis tests by specifying linear
combinations of parameters associated with categorical and/or
continuous variables.

Here are two examples I found by doing a quick search in the SPSS-L archives.

http://listserv.uga.edu/cgi-bin/wa?A2=ind1101&L=spssx-l&P=R43996

http://listserv.uga.edu/cgi-bin/wa?A2=ind1008&L=spssx-l&P=R72738

Ryan

On Fri, Dec 7, 2012 at 3:18 PM, riding <[hidden email]> wrote:

> Hi everyone,
>
> I’m struggling with SPSS syntax and wonder if someone knows a quick
> solution? I ran a mixed model on a longitudinal treatment study with 1
> outcome, 3 categorical variables, 2 continuous variables and 2 interactions
> with time.
>
> This is the model:
>
> MIXED health BY treatment gender race WITH time Zattitude
>   /CRITERIA=CIN(95) MXITER(100) MXSTEP(10) SCORING(1)
> SINGULAR(0.000000000001) HCONVERGE(0,
>     ABSOLUTE) LCONVERGE(0, ABSOLUTE) PCONVERGE(0.000001, ABSOLUTE)
>   /FIXED=treatment gender race time time*treatment time*Zattitude |
> SSTYPE(3)
>   /METHOD=REML
>   /PRINT=G  SOLUTION TESTCOV
>   /RANDOM=INTERCEPT time | SUBJECT(Patno) COVTYPE(UN).
>
> The time*Zattitude interaction is significant, both are continuous
> variables. I would like to estimate three slopes (1 for average attitude, +1
> SD and -1SD). I know what the command would look like in SAS  (estimate 'AVG
> CHA' time 1 time*treatment 0.333 0.333 0.334  time*Zattitude 0) , but don’t
> know how to do this with continuous variables in SPSS. Does the test
> subcommand apply to categorical levels only?
>
> I would very much appreciate any help, thanks!
>
> riding
>
> ________________________________
> View this message in context: spss mixed: estimate slopes for specific
> values of continuous IVs
> 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

[Lombardo, Barbara]

Hello everyone,

This is crazy, but I cannot get SPSS to stop jumping to the output
screen every time I do something.
I have tried modifying the options but have not been successful.
How do I turn this off???


Thank you
Barbara


- Please consider the environment before printing this email. -

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

[Rick Oliver-3]

Edit>Options>General tab
Deselect (uncheck) "Raise viewer window"


Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]



From:        "Lombardo, Barbara" <[hidden email]>
To:        [hidden email],
Date:        12/10/2012 09:52 AM
Subject:        how to turn off jump to output screen
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Hello everyone,

This is crazy, but I cannot get SPSS to stop jumping to the output
screen every time I do something.
I have tried modifying the options but have not been successful.
How do I turn this off???


Thank you
Barbara


- Please consider the environment before printing this email. -

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

[Lombardo, Barbara]

I don’t have it checked and it still comes up??

 

Barbara Lombardo

Sr. Applications Specialist/SQL Programmer II

Institutional Research

Camden County College

Blackwood NJ 08012

Office: 856-374-4961

Fax:    [phone]

 

 P Think before you print.

CONFIDENTIALITY: This e-mail (including any attachments) may contain confidential, proprietary and privileged information, and unauthorized disclosure or use is prohibited. If you received this e-mail in error, please notify the sender and delete this e-mail from your system.

 

From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Rick Oliver
Sent: Monday, December 10, 2012 10:56 AM
To: [hidden email]
Subject: Re: how to turn off jump to output screen

 

Edit>Options>General tab
Deselect (uncheck) "Raise viewer window"


Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]



From:        "Lombardo, Barbara" <[hidden email]>
To:        [hidden email],
Date:        12/10/2012 09:52 AM
Subject:        how to turn off jump to output screen
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Hello everyone,

This is crazy, but I cannot get SPSS to stop jumping to the output
screen every time I do something.
I have tried modifying the options but have not been successful.
How do I turn this off???


Thank you
Barbara


- Please consider the environment before printing this email. -

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

<script type="text/javascript"> <!-- if (top.location != self.location) top.location = self.location; // --> </script>   ­­  

[Rick Oliver-3]

If there is no open Viewer window, one will open on top the next time you do anything that generates output. Minimize or put that window in the background somewhere and it won't pop to front on its own after that.

Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]



From:        "Lombardo, Barbara" <[hidden email]>
To:        Rick Oliver/Chicago/IBM@IBMUS, <[hidden email]>,
Date:        12/10/2012 10:01 AM
Subject:        RE:      Re: how to turn off jump to output screen

---

I don’t have it checked and it still comes up??
 
Barbara Lombardo
Sr. Applications Specialist/SQL Programmer II
Institutional Research
Camden County College
Blackwood NJ 08012
Office: 856-374-4961
Fax:    [phone]
 
 P Think before you print.
CONFIDENTIALITY: This e-mail (including any attachments) may contain confidential, proprietary and privileged information, and unauthorized disclosure or use is prohibited. If you received this e-mail in error, please notify the sender and delete this e-mail from your system.
 
From: SPSSX(r) Discussion [[hidden email]] On Behalf Of Rick Oliver
Sent: Monday, December 10, 2012 10:56 AM
To: [hidden email]
Subject: Re: how to turn off jump to output screen
 
Edit>Options>General tab
Deselect (uncheck) "Raise viewer window"


Rick Oliver
Senior Information Developer
IBM Business Analytics (SPSS)
E-mail: [hidden email]



From:        "Lombardo, Barbara" <[hidden email]>
To:        [hidden email],
Date:        12/10/2012 09:52 AM
Subject:        how to turn off jump to output screen
Sent by:        "SPSSX(r) Discussion" <[hidden email]>

---

Hello everyone,

This is crazy, but I cannot get SPSS to stop jumping to the output
screen every time I do something.
I have tried modifying the options but have not been successful.
How do I turn this off???


Thank you
Barbara


- Please consider the environment before printing this email. -

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

  ­­  

[Melissa Ives]

Barbara,
It should be that un-checking the Notification items "Raise viewer window" and "Scroll to new output" under the General tab in Edit-->Options will do this.

Melissa
-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Lombardo, Barbara
Sent: Monday, December 10, 2012 9:51 AM
To: [hidden email]
Subject: [SPSSX-L] how to turn off jump to output screen

Hello everyone,

This is crazy, but I cannot get SPSS to stop jumping to the output screen every time I do something.
I have tried modifying the options but have not been successful.
How do I turn this off???


Thank you
Barbara


- Please consider the environment before printing this email. -

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

PRIVILEGED AND CONFIDENTIAL INFORMATION
This transmittal and any attachments may contain PRIVILEGED AND
CONFIDENTIAL information and is intended only for the use of the
addressee. If you are not the designated recipient, or an employee
or agent authorized to deliver such transmittals to the designated
recipient, you are hereby notified that any dissemination,
copying or publication of this transmittal is strictly prohibited. If
you have received this transmittal in error, please notify us
immediately by replying to the sender and delete this copy from your
system. You may also call us at [phone] for assistance.

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