repeated measures correlation

[Michael Bersick]

Hi,
Maybe I am being obtuse, but Iconfess I am stumped here.I have a data set in which a number of physiological and task measures are taken in each of 3 conditions over 20 days.How might I best compute the correlation within a given conditionbetween 2 variables, taking into account the within subjects structure of the data?Thanks in advance,
MB**********************************************************
Michael Bersick                                                        
Assistant Research Scientist                                    
[hidden email]                              
Cognitive Electrophysiology Laboratory                  
New York State Psychiatric Institute                    
1051 Riverside Drive, Unit 6                              
New York City, NY 10032                              
[phone]                                                        


Harvesting brain grain for a better tomorrow...
**********************************************************

[Alexander J. Shackman-2]

do you just want the correlation, or do you want the regression?
and, is you question "statistical" or "computational" (eg, want a macro or
the like?)

alex shackman

On 5/18/07, Michael Bersick <[hidden email]> wrote:

>
> Hi,
> Maybe I am being obtuse, but Iconfess I am stumped here.I have a data set
> in which a number of physiological and task measures are taken in each of 3
> conditions over 20 days.How might I best compute the correlation within a
> given conditionbetween 2 variables, taking into account the within subjects
> structure of the data?Thanks in advance,
> MB**********************************************************
> Michael Bersick
> Assistant Research Scientist
> [hidden email]
> Cognitive Electrophysiology Laboratory
> New York State Psychiatric Institute
> 1051 Riverside Drive, Unit 6
> New York City, NY 10032
> [phone]
>
>
> Harvesting brain grain for a better tomorrow...
> **********************************************************
>

--
Alexander J. Shackman
Laboratory for Affective Neuroscience
Waisman Laboratory for Brain Imaging & Behavior
University of Wisconsin-Madison
1202 West Johnson Street
Madison, Wisconsin 53706

Telephone: [phone]
FAX: [phone]
EMAIL: [hidden email]
http://psyphz.psych.wisc.edu/~shackman

[Michael Bersick]

Well, I suppose I want both, and my question is statistical.


----- Original Message -----
  From: Alexander J. Shackman
  To: Michael Bersick
  Cc: [hidden email]
  Sent: Friday, May 18, 2007 12:46 PM
  Subject: Re: [SPSSX-L] repeated measures correlation


  do you just want the correlation, or do you want the regression?
  and, is you question "statistical" or "computational" (eg, want a macro or the like?)

  alex shackman


  On 5/18/07, Michael Bersick <[hidden email]> wrote:
    Hi,
    Maybe I am being obtuse, but Iconfess I am stumped here.I have a data set in which a number of physiological and task measures are taken in each of 3 conditions over 20 days.How might I best compute the correlation within a given conditionbetween 2 variables, taking into account the within subjects structure of the data?Thanks in advance,
    MB**********************************************************
    Michael Bersick
    Assistant Research Scientist
    [hidden email]
    Cognitive Electrophysiology Laboratory
    New York State Psychiatric Institute
    1051 Riverside Drive, Unit 6
    New York City, NY 10032
    [phone]


    Harvesting brain grain for a better tomorrow...
    **********************************************************




  --
  Alexander J. Shackman
  Laboratory for Affective Neuroscience
  Waisman Laboratory for Brain Imaging & Behavior
  University of Wisconsin-Madison
  1202 West Johnson Street
  Madison, Wisconsin 53706

  Telephone: [phone]
  FAX: [phone]
  EMAIL: [hidden email]
  http://psyphz.psych.wisc.edu/~shackman

[Dennis Deck]

I assume you mean that you have multiple records per subject.  You need
to run CASESTOVARS to restructure the data to get one record per subject
with the 3 variables.  Then you can run your correlations.

Dennis Deck, PhD
RMC Research Corporation
[hidden email]

-----Original Message-----
From: Michael Bersick [mailto:[hidden email]]
Sent: Friday, May 18, 2007 9:34 AM
Subject: repeated measures correlation

Hi,
Maybe I am being obtuse, but Iconfess I am stumped here.I have a data
set in which a number of physiological and task measures are taken in
each of 3 conditions over 20 days.How might I best compute the
correlation within a given conditionbetween 2 variables, taking into
account the within subjects structure of the data?Thanks in advance,
MB**********************************************************
Michael Bersick
Assistant Research Scientist
[hidden email]
Cognitive Electrophysiology Laboratory
New York State Psychiatric Institute
1051 Riverside Drive, Unit 6
New York City, NY 10032
[phone]


Harvesting brain grain for a better tomorrow...
**********************************************************