1
$\begingroup$

What is the appropriate way to report results for linear mixed model based on the "test of fixed effects" table in SPSS?

Is it just (F=xxx, p=xxx)?

This isn't my data but this is an image I found of the output table I am talking about: http://www.ats.ucla.edu/stat/spss/faq/test11.gif

enter image description here

$\endgroup$
  • $\begingroup$ and the parameter estimates... I'm pretty sure they're t tests, not F tests. Just report the fixed effects like you would in linear regression. $\endgroup$ – Patrick Coulombe Mar 15 '15 at 1:04
  • $\begingroup$ Can you paste in the output you are referring to? $\endgroup$ – gung Mar 15 '15 at 1:12
  • $\begingroup$ @gung Sure, I just found an image online of a table (I cant figure out how to add my own) $\endgroup$ – Jazz Mar 24 '15 at 14:05
  • $\begingroup$ Hi @gung thanks for inserting the table for me, but that table was just included per your request. I was wondering would the correct way to report this example data set for diet be (F=10.1, p=0.004)? I am not sure what you mean by the parameter estimates Patrick because I don't have a table reporting that in my output. Thank you! $\endgroup$ – Jazz Mar 24 '15 at 18:47
  • $\begingroup$ Hi @PatrickCoulombe I am not sure what you mean by the parameter estimates because I don't have a table reporting that in my output. Thank you! $\endgroup$ – Jazz Mar 26 '15 at 12:00
0
$\begingroup$

It depends on how you want to report it. AFAIK, there is no APA format for reporting LMMs.

Based on this reference, the author chose to report F and p values alone. For example, he states:

The “Tests of Fixed Effects” table, Table 15.6, shows that grade (F=12.9, p=0.002) and stdTest (F=25.6, p<0.0005) each have a significant effect on a student’s reading score difference, but treatment (F=1.2, p=0.289) does not.

As you can see, he reported it as (F=25.6, p<0.0005) ignoring adding more details for the F value.

Your second option is to report it the same way F value is reported on APA style

F (numerator_df, denominator_df) = F_value, p = ...
$\endgroup$

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.