4
$\begingroup$

I have an experiment where participants were assigned to one of four conditions (between-subject), and I want to predict a binary outcome (is_correct). Each participant answered one question so no repeated measures. So far I have come up with two models written in lme4-style formula syntax:

# condition as population effect
is_correct ~ condition

# condition as random intercept
is_correct ~ 1 + (1 | condition)

Which formulation should I use if I want to compare those conditions and determine which condition helps participants get more answers correct? I plan to fit a Bayesian GLM in brms.

$\endgroup$
5
$\begingroup$

Note that in your first model:

is_correct ~ condition

..this is not a mixed model, you are fitting fixed effects for condition and there are no random effects.

In your second model:

is_correct ~ 1 + (1 | condition)

...this is a mixed model where you are controlling for clustering within condition. However, since you only have 4 conditions, it seems likely that the first model will be better.

| cite | improve this answer | |
$\endgroup$
  • $\begingroup$ Does this answer your question ? If so, please consider marking it as the accepted answer, and if not please let us know why. $\endgroup$ – Robert Long Aug 28 at 6:19

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.