Multiple Response Syntax

[Ulrich Schubert]

Dear colleagues,

By chance I discovered that 2 different syntaxes we are using to table
multiple response items are yielding different results. Could anybody
explain me why? What is the difference between these syntaxes?
The first (newer) one sometimes seems to give incomplete results (i.e. an
MR set of 3 questions not summing to 300%)

1)

MRSETS
  /MCGROUP NAME=$XXX LABEL='MODELOS' VARIABLES= FAM_MOD_1 FAM_MOD_2 FAM_MOD_3
  /DISPLAY NAME=[$XXX].
CTABLES
  /FORMAT EMPTY=BLANK MISSING='.'  /SMISSING VARIABLE
  /VLABELS VARIABLES= LONDON PARIS REUS $XXX DISPLAY=DEFAULT
  /TABLE $XXX  [COLPCT.COUNT '% Coluna' PCT40.1] BY LONDON + PARIS + REUS
  /SLABELS POSITION=ROW
  /CATEGORIES VARIABLES=LONDON ORDER=A KEY=VALUE EMPTY=include TOTAL=YES
POSITION=BEFORE
  /CATEGORIES VARIABLES=$XXX EMPTY=EXclude TOTAL=YES POSITION=AFTER.


2)

table /format  ZERO
      /MRgroup ip '' FAM_MOD_1 FAM_MOD_2 FAM_MOD_3
      /ftotal tot 'TOTAL'
      /table ip + tot by LONDON+PARIS+REUS+tot
      /statistics cpct (ip '%Vertical':LONDON PARIS REUS).


Thank you very much!
Best regards,

Ulrich Schubert
ACZIONA Quanlitative Market Consultants
Enrique Granados 113 2º1ª
08008 Barcelona, ESPAÑA
Tel. + 34.93.238.43.53
[hidden email]
www.acziona.com

 Please don't print this e-mail unless you really need to.

=====================
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]

It may have to do with the difference between multiple categories and multiple dichotomies.
The MCGROUP subcommand defines or modifies a multiple category group. A name and variable list must be specified. Optionally, a label can be specified for the set.

The MDGROUP subcommand defines or modifies a multiple dichotomy set. A name, variable list, and value must be specified. Optionally, you can control assignment of set and category labels.

Or more likely a combination of the above and missing value handling:
MRGROUP  Exclude missing values listwise for multiple-response groups. Cases with missing values for any component variable are excluded from the tabulation of the multiple-response group.
Melissa

-----Original Message-----
From: SPSSX(r) Discussion [mailto:[hidden email]] On Behalf Of Ulrich Schubert
Sent: Friday, April 04, 2008 3:29 AM
To: [hidden email]
Subject: [SPSSX-L] Multiple Response Syntax

Dear colleagues,

By chance I discovered that 2 different syntaxes we are using to table multiple response items are yielding different results. Could anybody explain me why? What is the difference between these syntaxes?
The first (newer) one sometimes seems to give incomplete results (i.e. an MR set of 3 questions not summing to 300%)

1)

MRSETS
  /MCGROUP NAME=$XXX LABEL='MODELOS' VARIABLES= FAM_MOD_1 FAM_MOD_2 FAM_MOD_3
  /DISPLAY NAME=[$XXX].
CTABLES
  /FORMAT EMPTY=BLANK MISSING='.'  /SMISSING VARIABLE
  /VLABELS VARIABLES= LONDON PARIS REUS $XXX DISPLAY=DEFAULT
  /TABLE $XXX  [COLPCT.COUNT '% Coluna' PCT40.1] BY LONDON + PARIS + REUS
  /SLABELS POSITION=ROW
  /CATEGORIES VARIABLES=LONDON ORDER=A KEY=VALUE EMPTY=include TOTAL=YES POSITION=BEFORE
  /CATEGORIES VARIABLES=$XXX EMPTY=EXclude TOTAL=YES POSITION=AFTER.


2)

table /format  ZERO
      /MRgroup ip '' FAM_MOD_1 FAM_MOD_2 FAM_MOD_3
      /ftotal tot 'TOTAL'
      /table ip + tot by LONDON+PARIS+REUS+tot
      /statistics cpct (ip '%Vertical':LONDON PARIS REUS).


Thank you very much!
Best regards,

Ulrich Schubert
ACZIONA Quanlitative Market Consultants
Enrique Granados 113 2º1ª
08008 Barcelona, ESPAÑA
Tel. + 34.93.238.43.53
[hidden email]
www.acziona.com

 Please don't print this e-mail unless you really need to.

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

[Zdaniuk, Bozena-2]

Hello, I am predicting occurrence of death in a sample using cox regression. All my predictors are baseline measures except for one: a dichotomous variable whether or not the person was placed in institution during the time of the study. The placement occurred to some that died and to some that did not die. I think I should control for the time between baseline and placement when predicting death. Should I just add the time-btw-baseline-and-placement variable to the list of predictors in addition to the dichotomous (placed vs not-placed) predictor? Would this be equivalent to controlling for the time btw baseline and placement when using placement as a predictor of bereavement?
Thanks a lot in advance for any thoughts on that.
Bozena

Bozena Zdaniuk, Ph.D.
University of Pittsburgh
UCSUR, 6th Fl.
121 University Place
Pittsburgh, PA 15260
Ph.: 412-624-5736
Fax: [phone]
Email: [hidden email]


D

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