0
$\begingroup$

I am conducting longitudinal multilevel models with Daily observations as level-1 variable and PARTICIPANT as level-2 variable. Predictors and outcome variables are measured every day.

I am confused about the use of TIME in SPSS syntax. Models that I find use TIME both as a predictor and as the level-1 identifier. Is this appropriate?

Some models include the following row and some dont:

/REPEATED=time | SUBJECT(Participant) COVTYPE (ar1)

Some of them only add TIME as a predictor without the row above.

What is the correct way to write SPSS syntax if I want to indicate that TIME is the level-1 measurement unit? Is the command above indispensable? Do I need to /can I also add TIME as a predictor (fixed or random effect).

$\endgroup$
0
$\begingroup$

Yes, you can use time as both the index for REPEATED and as a fixed predictor. REPEATED sets up the R matrix structure in the mixed model. There are different ways to handle the repeated measures, some involving using REPEATED, some involving just RANDOM effects. Multiple approaches can be valid.

| cite | improve this answer | |
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.