Date:         Fri, 1 Sep 2006 11:11:16 +0100
Reply-To:     Paul Mcgeoghan <mcgeoghan@Cardiff.ac.uk>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Paul Mcgeoghan <mcgeoghan@Cardiff.ac.uk>
Subject:      repeated measures with varying covariates
Content-Type: text/plain; charset=US-ASCII

Hi,

I have the following:

Dependent variable is TotalScore and this is recorded for 74 companies on 2
different websites and in 2 successive years so SITE and YEAR are 2 within
subject factors with 2 levels.

I have 3 between subject factors (each with 2 levels).
I have 3 constant covariates (LOGSIZE, GASHARE and FORSHARE) whose values do
not change over the 4 within subject levels.
I have 4 other covariates (LEVERAGE, RTA, RETURNEQUITY and FIXEDASSETS) whose
values are the same for the 2 websites but change for the 2 years.

I have syntax as follows:

GLM
  TOTALSCORE04 TOTALSCORE05 TOTALSCORE04T TOTALSCORE05t BY BIG4 INDUSTRY
  LOCATION  WITH FIXEDASSETS04 TO FIXEDASSETS05t  LEVERAGE04 TO LEVERAGE05t
  RTA04 TO RTA05t RETURNEQUITY04 TO RETURNEQUITY05t
  GASHARE FORSHARE LOGSIZE
  /WSFACTOR = SITE 2 Polynomial TIME 2 Polynomial
  /METHOD = SSTYPE(3)
  /CRITERIA = ALPHA(.05)
  /WSDESIGN = SITE TIME SITE*TIME.

The problem I have is in specifying the covarying covariates. An added problem
is that the covarying covariates do not vary over the 2 sites (only over the 2
years). Is the above the correct syntax?

Would it be better to use Linear Mixed Models Repeated Measures in this case?

Paul


==================
Paul McGeoghan,
Application support specialist (Statistics and Databases),
University Infrastructure Group (UIG),
Information Services,
Cardiff University.
Tel. 02920 (875035).