Data simulation to find out why GAM and brms disagree

Does replication in the RPP predict how often a paper is cited before and after the RPP results were published? No.

When not modelling ordinal data properly, can we mistake a floor effect in the outcome as an interaction effect with a variable that causes the floor effect?

Demonstration of waffle plot functions in ggplot2

showing a problem with my prediction function for MCMCglmm zero-altered methods where the CI of the prediction depends on the factor reference chosen

These warnings show after knitting instead of processing file: convergence_warnings_bolker.Rmd output file: convergence_warnings_bolker.knit.md /usr/local/bin/pandoc convergence_warnings_bolker.utf8.md --to html --from markdown+autolink_bare_uris+ascii_identifiers+tex_math_single_backslash-implicit_figures --output convergence_warnings_bolker.html --smart --email-obfuscation none --self-contained --standalone --section-divs --template /Library/Frameworks/R.framework/Versions/3.1/Resources/library/rmarkdown/rmd/h/default.html --variable 'theme:bootstrap' --include-in-header /var/folders/tr/lgwjmdgd72bckr1hj5gd_7640000gp/T//Rtmpi037yn/rmarkdown-str1067799c69d7.html --mathjax --variable 'mathjax-url:https://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML' --no-highlight --variable highlightjs=/Library/Frameworks/R.framework/Versions/3.1/Resources/library/rmarkdown/rmd/h/highlight Output created: convergence_warnings_bolker.html Warning messages: 1: In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model failed to converge with max|grad| = 1.52675 (tol = 0.001, component 17) 2: In checkConv(attr(opt, "derivs"), opt$par, ctrl = control$checkConv, : Model is nearly unidentifiable: very large eigenvalue - Rescale variables?;Model is nearly unidentifiable: large eigenvalue ratio - Rescale variables?