I am struggling to understand should I report the results with random effects or not (re_formula = NULL or NA). I have a population based data. Patients are nested in differently sized counties and I would like to report the result closest to the truth. N = 6000. I am interested in population-level…

[image] di4oi4: And these are the predictions for the predictor I am interested in. Study question is: is this predictor associated with outcome variable (received treatment hours) in the whole country. We are not interested in county/regional level effects. Then I’d say use re_formula = NA (…

Should I report the results with random effects or not (brms, re_formula = NULL vs NA)?

Modeling

martinmodrak July 8, 2020, 7:28pm 5

Does the post at Inferences marginal of random effects in multi-level models answer your question?

2 Likes

Topic		Replies	Views
Conditional effects and summary estimate showing opposite results General conditional-effects , brms	8	1330	July 12, 2022
Brms model with a level of "random effect" set to zero? brms	5	631	July 14, 2023
Group-level effects integrated over or set to zero in conditional_effects()? or neither? brms	7	935	May 11, 2020
Random effects brms with few observations per group - meta-analysis Modeling specification , brms	2	905	November 2, 2022
How to compare the effect of different datasets in model Modeling brms	6	445	January 26, 2024

Should I report the results with random effects or not (brms, re_formula = NULL vs NA)?

Related topics