That sounds to me like you need to perform a Chi-square test of percentages.
Arthur Kramer, Ph.D.
Director of Institutional Research
New Jersey City University
"Believe half of what you see and none of what you hear."
N. Whitfield
B. Strong
-----Original Message-----
From: SPSSX(r) Discussion [mailto:
[hidden email]] On Behalf Of Anton
Sent: Sunday, April 18, 2010 1:04 PM
To:
[hidden email]
Subject: Comparing % change between two groups
Hi All-
I think I have a relatively easy question, however I am stumped as to how to
proceed. I essentially have two variables:
* Group (Treatment/Control)
* Employed (Yes/No) same people measured at two separate time periods
I’d like to directly compare the rate of change between the two groups,
i.e., whether the increase/decrease (%) in employment for the control group
is statistically different than the increase/decrease (%) for the treatment
group.
Sounds really easy, but...
Should I compare the odds ratios for each group? If so, how?
Should I be running a logistic regression with employment at time 1 & group
(and the group by time 1 interaction) as covariates and time 2 as the
dependent variable?
Any help is much appreciated. Some basic code would be even better.
And, no, this is not a homework assignment; just me being
non-parametrically challenged.
Anton
=====================
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
=====================
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
Locked
