Date:         Sat, 29 Jan 2005 00:15:58 -0500
Reply-To:     Jeffrey Miller <millerjeffm@HOTMAIL.COM>
Sender:       "SPSSX(r) Discussion" <SPSSX-L@LISTSERV.UGA.EDU>
From:         Jeffrey Miller <millerjeffm@HOTMAIL.COM>
Subject:      SPSS growth model problem
Content-Type: text/plain; format=flowed

Hi all,

I am running into a simple unconditional growth model but keep running into
the same problem. My dependent variable is continuous. There are no level-2
predictors. The level-1 predictor is time with 5 levels. The levels are
years (e.g., 2000, 2001) and I am centering such that the first year is 0 in
order to make the intercept meaningful. I get reasonable parameter estimates
for the intercept and time. The level-1 variance and the covariance are
fine, but I get 0 for the level-2 variance and the message "This covariance
parameter is redundant".

Below is my code:

title "Unconditional Growth Model".
mixed y_var with center_time
/print=solution
/method=ml
/fixed = center_time
/random intercept center_time | subject(id) covtype(un).
execute.

Any ideas,

Jeff Miller