Inquiry about the Pooling Function 'brm_multiple' and Consideration of Zhou & Reiter's Recommendations

Hello everyone,

I hope you’re all doing well. I have a couple of questions regarding the ‘brm_multiple’ pooling function in the ‘brms’ package for Bayesian statistical analysis in R. I would greatly appreciate your insights on the following:

  1. How does the ‘brm_multiple’ pooling function in the ‘brms’ package perform pooling? Could anyone provide information on the specific method it employs?
  2. Does the ‘brm_multiple’ function take into consideration the recommendations of Zhou, X. & Reiter, J. P. in their paper titled “A Note on Bayesian Inference After Multiple Imputation” published in the American Statistician journal in 2010 (Vol. 64, pp. 159-163)?

Thank you in advance for your help and expertise!

Best regards,

brm_multiple takes a list of dataframes, fits models to each of them, and combines the resulting posterior chains for inference. This is in line with the recommendations of the paper you mention.