Math Forum / Math Software / SPSS / December 2007

I've just discovered that much of the analysis I want to do can be
done in Excel pivot tables.
My data, however, is in SPSS format (cases in rows, variables in
columns) and I wondered:

Hi --
Does anyone have suggestions for a reasonable way to perform
"internal" (within the model generation sample) cross-validation on a
binary logistic regression model, perhaps using bootstrapping?

This might seem trivial. But I am trying to create a hedonic index and
thus have to calculate the product of all the values of a certain
variable and then calculate the geometric average of this. I didnt
manage to do it yet.

I have been unable to find an elegant Syntax for the following problem
and was hoping somebody could help me.
My data looks like this (the E vars represent employment status over a
series of months; 1= new job; 2= in old job; 3= lost job; 4=still out

Hi you,
I'm new here.
It should  be possible to generate a new file completely syntax-
driven.

I have an SPSS secondary dataset for a consumer satisfaction
questionnaire.  Instead of one variable for each variable, I have a
variable for each response option.  Each of these are dichotomous
1=yes 0=no outputs.

I'm trying to figure out how to understand/run what I think is a
partially nested design. Once I figure it out I'm fairly certain I'll
be able to run it on SPSS.
Let's say you have a treatment that you believe is effective at

Is SPSS a good program to use in order to choose a clustering method?
I can't find much information on how to go about it.
Thank you.
Sheryl

I would like to compare my sample with a reference sample.
Since i know only the mean value and standard deviation of the reference
sample i can not use T-Test for independent samples in Spss.
Should I use One-Sample T-Test (with constant "Test-Value" form the

Good morning!
I have encountered a problem with my data analysis and hoped someone
out there may have a suggestion or two about how I should proceed.
I conducted a study comparing the effects of positive and negative

I have this huge data set (200+ variables and 500.000+ cases!!!)
containing information about the status for an observation for each
week the last 4 years (4 years x 52 weeks = 200+ variables). First I
have an identifier variable and then the 200+ variables for each week

I want to use the Generalized Linear Models module to test whether
relations between physiology and performance accuracy differ across 2
tasks (Task x Accuracy interaction) in a completely repeated-measures
design, but I am not certain that I am setting up the syntax

I'm trying to make some processes at work (market research) more
efficient and I've modifed a scipt found in this group. The idea is to
open a data set and then run my scrpit, that will create a syntax with
the informations needed to make frequencies for all relevant variables

I've queried the history on the group but I'm not finding what I'm
looking for. My social science education left me woefully in the dark
about transforming data, so I need help.
The suggested power for transformation given with the spread v level

I am using SPSS 12 and hav found wierd problem with macro DO loop and
INCLUDE. I try to give an example.
I have a syntax file "D:\temp\comp.sps" which contains some dummy
syntax: