Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!

Supported by

generalized linear mixed model does not run

Hi,

I'm trying to run a generalized linear mixed model with 5 fixed variables (one of them on a scale score the rest are nominal variables) and one random nominal variable, and a binary outcome variable (see below). Last time I ran a similar model it took the night to calculate it, however, this time, it just keeps on "thinking" after calculating the first variable (see blow) I tried many different computers and gave it over a night to calculate. any ideas please??


Comments

  • That's because JASP has the very, very bad default behavior of including all possible interaction terms as both fixed and random effects. Under Model on the left, remove all terms with a star in it, especially from the random effects box. You might even need to remove more from the random effects box.

  • What default behavior would be better? Could you suggest something on our GitHub page? (for details see https://jasp-stats.org/2018/03/29/request-feature-report-bug-jasp/)

    EJ

  • I think it's quite common for the user to want a 'repeated-measures-ANOVA-like' result, which would include all possible interactions. Thus, even if the default were to exclude interactions, there would still be the question of whether JASP is running with enough speed/efficiency to compute the requested interactions.

    R

  • I think there can also be issues with Type I error inflation if some interactions (or other components) are excluded from the model.

    R

Sign In or Register to comment.