0
$\begingroup$

I am currently building a linear mixed model with repeated measurements in SPSS. My syntax is:

MIXED measurement BY female mediansplit time WITH age

/CRITERIA=DFMETHOD(SATTERTHWAITE) CIN(95) MXITER(100) MXSTEP(10) SCORING(1)

SINGULAR(0.000000000001) HCONVERGE(0, ABSOLUTE) LCONVERGE(0, ABSOLUTE) PCONVERGE(0.000001, ABSOLUTE)

/FIXED=female mediansplit time age mediansplit*time | SSTYPE(3)

/METHOD=ML

/REPEATED=time | SUBJECT(study_id) COVTYPE(AR1)

/TEST=’mediansplit over time 0 vs 1’ mediansplit -1 1.

Meadiansplit = 2 levels (0 & 1), Time = 7 levels (0-6)

To find out if there are differences between the two groups of the mediansplit over time I want to calculate ANOVA-style contrasts. To my knowledge this is the /TEST command in SPSS for LMM (last line of my syntax). However, when running the above model, I get the warning “Custom hypothesis test 1 (mediansplit over time 0 vs 1) will not be performed because the L matrix is not estimable”.

So, my question is: how do I have to adjust the /TEST command?

Thanks!

$\endgroup$

1 Answer 1

2
$\begingroup$

As mediansplit has only two levels you get the outcome of the significance test from the Fixed Effect table and if you request the estimated marginal means tables /EMMEANS=TABLES(mediansplit) you get the same in terms of a t-test.

The error occurs as soon as you specify an interaction in the /fixed statement. It should work if you omit the interaction.

I encountered the same problem with a test on a specific contrast for a seven-level factor, where I wanted to test the mean of the first four levels against the mean of the other three levels and I never found a solution with the /TEST command. I eventually created a set of orthogonal contrast variables for the whole fixed model and entered them as covariates that included the one that I was interested in.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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