data mgmt question for dyadic studies

[Todd Kashdan]

Hi all:

I have a data management question.  I just cleaned an
entire dataset for an experimental study involving
mixed-sex dyads.  The data are entered with one row
for each participant with a variable indicating the
couple they are part of.  For example:

subject #  dyad #    well-being    rel sat
1            1
2            1
3            2
4            2

I want to examine the interaction of self and partner
effects using dyadic analyses (Kenny).  I know that I
need to have each row set up such that the person and
their partner's variables need to be in the same row
(essentially this is the double-entry method).  Is
there a way to do this other than the incredibly
resource intensive and error-prone method of copying
and pasting the data from one row to the partners row?
 is there a syntax that can be created to do this?

This is way out of my expertise with syntaxes and any
advice would be incredibly appreciated.

thanks so much

gratefully,
Todd


**************************
Todd B. Kashdan, Ph.D.
Assistant Professor
Department of Psychology
George Mason University
Mail Stop 3F5
Fairfax, VA  22030
http://mason.gmu.edu/~tkashdan

Confidentiality Notice: If you have reason to believe that you are not the intended recipient of this communication, please contact the sender immediately, and delete it from your system.  Any unauthorized review, use, disclosure or distribution is prohibited.



____________________________________________________________________________________
Food fight? Enjoy some healthy debate
in the Yahoo! Answers Food & Drink Q&A.
http://answers.yahoo.com/dir/?link=list&sid=396545367

[Maguin, Eugene]

Todd,

I've only got a minute, actually less than that. You want to convert from
'long' to 'wide'. Read up on the Casestovars command.

Gene Maguin

[Richard Ristow]

At 05:09 PM 3/15/2007, Todd Kashdan wrote:

>I [have] an experimental study involving mixed-sex dyads.  The data
>are entered with one row for each participant with a variable
>indicating the
>couple they are part of.  For example:
>
>subject #  dyad #    well-being    rel sat
>1            1
>2            1
>3            2
>4            2
>
>I need to have each row set up such that the person and their
>partner's variables need to be in the same row.

Sure. It's quite simple CASESTOVARS syntax. I clicked this up from the
Data Restructure wizard, accessed by Data> Restructure:

Panel
-----
1. "Restructure selected cases into variables"
2. Identifier variable "Dyad#". NO index variables.
3. I'm not having it sorted; I sorted before doing this. I recommend
that
4. "Group by index" - or, see if you like it better with "Group by
original variable". Don't select anything else

But it might be just as easy to write it. Anyway -- this is SPSS 15
draft output <WRR-not saved separately>:


List
|-----------------------------|---------------------------|
|Output Created               |15-MAR-2007 17:42:55       |
|-----------------------------|---------------------------|
Subject# Dyad# Well.Being Rel.Sat

      1      1  Great      Good
      2      1  Excellent  Medium
      3      2  Fair       Bad
      4      2  Bad        Awful

Number of cases read:  4    Number of cases listed:  4


CASESTOVARS
  /ID = Dyad#
  /GROUPBY = INDEX .


Cases to Variables
|----------------------------|---------------------------|
|Output Created              |15-MAR-2007 17:55:21       |
|----------------------------|---------------------------|

Generated Variables
|------------|------------|
|Original    |Result      |
|Variable    |------------|
|            |Name        |
|----------|-|------------|
|Subject#  |1|Subject#.1  |
|          |2|Subject#.2  |
|----------|-|------------|
|Well.Being|1|Well.Being.1|
|          |2|Well.Being.2|
|----------|-|------------|
|Rel.Sat   |1|Rel.Sat.1   |
|          |2|Rel.Sat.2   |
|----------|-|------------|

Processing Statistics
|---------------|---|
|Cases In       |4  |
|Cases Out      |2  |
|---------------|---|
|Cases In/Cases |2.0|
|Out            |   |
|---------------|---|
|Variables In   |4  |
|Variables Out  |7  |
|---------------|---|
|Index Values   |2  |
|---------------|---|


LIST.

List
|-----------------------------|---------------------------|
|Output Created               |15-MAR-2007 17:55:41       |
|-----------------------------|---------------------------|
Dyad# Subject#.1 Well.Being.1 Rel.Sat.1  Subject#.2 Well.Being.2
Rel.Sat.2

    1        1    Great        Good             2    Excellent
Medium
    2        3    Fair         Bad              4    Bad          Awful

Number of cases read:  2    Number of cases listed:  2
===================
APPENDIX: Test data
===================
DATA LIST LIST SKIP=1/
   Subject# Dyad# (2F3) Well.Being Rel.Sat(2A10).
BEGIN DATA
subject #  dyad #    well-being    rel sat
1            1        Great         Good
2            1        Excellent     Medium
3            2        Fair          Bad
4            2        Bad           Awful
END DATA.
LIST.

[Richard Ristow]

Response to an off-list follow-up: at 02:10 PM 3/18/2007, Todd Kashdan
wrote,

>Thanks Richard.  But one last question that makes it a bit more
>complex than a simple CASESTOVARS syntax. The final dataset should
>have two rows for each dyad. In one row, the S data is listed first
>and then their
>partners data.  But in another row, the partner is the S and the S
>from the prior row's data should come next. Like this:
>
>subject  dyad   well-being   partner well-being
>1          1       4               5
>2          1       5               4

Amazing what you learn, isn't it? Could probably have solved this for
you the first time, if you'd asked the first time.

Just use CASESTOVARS, but use it twice. This requires that both the
original data and the first 'wide' file be saved for re-use. The
following uses SPSS 15 'dataset' logic, but scratch .SAV files would
work fine. This is SPSS 15 draft output:


* ...................................................          .
LIST.

List
|-----------------------------|---------------------------|
|Output Created               |19-MAR-2007 01:16:23       |
|-----------------------------|---------------------------|
Subject# Dyad# Well.Bng Rel.Sat

      1      1  Great    Good
      2      1  Great    Medium
      3      2  Fair     Bad
      4      2  Bad      Awful

Number of cases read:  4    Number of cases listed:  4


.  DATASET COPY InptData   .
*--SAVE OUTFILE=InptData   .

*  ......   I.   Pairs in forward order         ......  .

SORT CASES BY Dyad# (A) Subject#(A).
CASESTOVARS
  /ID = Dyad#
  /GROUPBY = INDEX .

Cases to Variables
|----------------------------|---------------------------|
|Output Created              |19-MAR-2007 01:16:24       |
|----------------------------|---------------------------|

Generated Variables
|----------|----------|
|Original  |Result    |
|Variable  |----------|
|          |Name      |
|--------|-|----------|
|Subject#|1|Subject#.1|
|        |2|Subject#.2|
|--------|-|----------|
|Well.Bng|1|Well.Bng.1|
|        |2|Well.Bng.2|
|--------|-|----------|
|Rel.Sat |1|Rel.Sat.1 |
|        |2|Rel.Sat.2 |
|--------|-|----------|

Processing Statistics
|---------------|---|
|Cases In       |4  |
|Cases Out      |2  |
|---------------|---|
|Cases In/Cases |2.0|
|Out            |   |
|---------------|---|
|Variables In   |4  |
|Variables Out  |7  |
|---------------|---|
|Index Values   |2  |
|---------------|---|


.  /**/  LIST  /*-*/.

List
|-----------------------------|---------------------------|
|Output Created               |19-MAR-2007 01:16:24       |
|-----------------------------|---------------------------|
Dyad# Subject#.1 Well.Bng.1 Rel.Sat.1 Subject#.2 Well.Bng.2 Rel.Sat.2

    1        1    Great      Good            2    Great      Medium
    2        3    Fair       Bad             4    Bad        Awful

Number of cases read:  2    Number of cases listed:  2


.  DATASET NAME FwrdPair   .
*--SAVE OUTFILE=FwrdPair   .

*  ......   II.  Pairs in reverse order         ......  .

.  DATASET ACTIVATE InptData.
.  DATASET COPY     RvrsPair.
.  DATASET ACTIVATE RvrsPair.
*--GET         FILE=InptData.

SORT CASES BY Dyad# (A) Subject#(D).
CASESTOVARS
  /ID = Dyad#
  /GROUPBY = INDEX .

Cases to Variables
|----------------------------|---------------------------|
|Output Created              |19-MAR-2007 01:16:26       |
|----------------------------|---------------------------|
[RvrsPair]

Generated Variables
|----------|----------|
|Original  |Result    |
|Variable  |----------|
|          |Name      |
|--------|-|----------|
|Subject#|1|Subject#.1|
|        |2|Subject#.2|
|--------|-|----------|
|Well.Bng|1|Well.Bng.1|
|        |2|Well.Bng.2|
|--------|-|----------|
|Rel.Sat |1|Rel.Sat.1 |
|        |2|Rel.Sat.2 |
|--------|-|----------|

Processing Statistics
|---------------|---|
|Cases In       |4  |
|Cases Out      |2  |
|---------------|---|
|Cases In/Cases |2.0|
|Out            |   |
|---------------|---|
|Variables In   |4  |
|Variables Out  |7  |
|---------------|---|
|Index Values   |2  |
|---------------|---|


.  /**/  LIST  /*-*/.

List
|-----------------------------|---------------------------|
|Output Created               |19-MAR-2007 01:16:26       |
|-----------------------------|---------------------------|
[RvrsPair]

Dyad# Subject#.1 Well.Bng.1 Rel.Sat.1 Subject#.2 Well.Bng.2 Rel.Sat.2

    1        2    Great      Medium          1    Great      Good
    2        4    Bad        Awful           3    Fair       Bad


Number of cases read:  2    Number of cases listed:  2


*--SAVE     OUTFILE=RvrsPair.

DATASET ACTIVATE RvrsPair.
*  ......   III. Pairs in two orders combined   ......  .
NEW FILE.
ADD FILES
   /FILE=FwrdPair
   /FILE=RvrsPair
   /BY Dyad#.
LIST.

List
|-----------------------------|---------------------------|
|Output Created               |19-MAR-2007 01:18:16       |
|-----------------------------|---------------------------|
Dyad# Subject#.1 Well.Bng.1 Rel.Sat.1 Subject#.2 Well.Bng.2 Rel.Sat.2

    1        1    Great      Good            2    Great      Medium
    1        2    Great      Medium          1    Great      Good
    2        3    Fair       Bad             4    Bad        Awful
    2        4    Bad        Awful           3    Fair       Bad

Number of cases read:  4    Number of cases listed:  4
===================
APPENDIX: Test data
===================
* ............   Test data               ............          .

DATA LIST LIST SKIP=1/
   Subject# Dyad# (2F3) Well.Bng    Rel.Sat(2A06).
BEGIN DATA
subject #  dyad #    well-being    rel sat
1            1        Great         Good
2            1        Great         Medium
3            2        Fair          Bad
4            2        Bad           Awful
END DATA.