JsonGeller @jgeller1phd.bsky.social · 06/10/2026For those examples, I would choose something beta-flavored. Simulations for non-independence would def be interesting. Maybe @rmkubinec.bsky.social has more info? 100
JsonGeller @jgeller1phd.bsky.social · 06/10/2026In the first example of the paper the original paper modeled proportions, thus the reason we use beta. 000
JsonGeller @jgeller1phd.bsky.social · 06/10/2026Successes out of known n → binomial (beta-binomial if overdispersed) Continuous, no 0s/1s → beta 0s/1s, same process as interior → ordered beta 0s/1s from a distinct process → ZIB / OIB / ZOIB . 210
Reposted by JsonGellerJames Balamuta @coatless.bsky.social · 04/10/2026webrarian is a new R package. It turns a folder of R scripts and data into a static website where R runs in the visitor's browser, with no compute server and nothing to install. blog.thecoatlessprofessor.com/posts/introd... #rstats #webr #webassembly 516166
JsonGeller @jgeller1phd.bsky.social · 03/10/2026@dominiquemakowski.bsky.social created dominiquemakowski.github.io/cogmod/ based on some of our convos.dominiquemakowski.github.ioCognitive Models for Subjective Scales and Decision Making TasksImplements cognitive models for data from subjective (Likert or analog) scales and from decision making tasks with reaction times and choice data. Provides random generation, density functions, and cu... 020
JsonGeller @jgeller1phd.bsky.social · 03/10/2026Paul did not seem like he wanted it changed when I posted about it 110
JsonGeller @jgeller1phd.bsky.social · 03/10/2026In this case zeros can be theoretical interesting (maybe students are disengaging not paying any attention) and binomial model doesn't really get at that question 110
JsonGeller @jgeller1phd.bsky.social · 03/10/2026So many defensible options! For me it comes down to whether I care about the binomial sampling process. If it’s x/10, beta-binomial seems natural + handles overdispersion. If I want to model the proportion itself, ordered beta is appealing since it naturally accommodates 0 and 1. 110
JsonGeller @jgeller1phd.bsky.social · 03/10/2026@chelseaparlett.bsky.social you are too kind and generous! You were a huge help! 120
JsonGeller @jgeller1phd.bsky.social · 02/10/2026Probably doesn’t matter in your case the skewed dist probably better but see osf.io/preprints/ps...osf.ioOSF 110
JsonGeller @jgeller1phd.bsky.social · 02/10/2026Out of curiosity, when comparing models did you test the default exgauss family in brms? 110
Reposted by JsonGellerHenrik Singmann @singmann.bsky.social · 02/10/2026New preprint: When should you use linear mixed models (LMMs), and when is repeated-measures (RM) ANOVA enough? LMMs offer greater flexibility. But does that make them a better default? My paper argues for statistical parsimony: use RM-ANOVA when both methods are appropriate. osf.io/preprints/ps...osf.ioWhen to Use Mixed Models and When RM-ANOVA - An Argument for Statistical ParsimonyWhen should researchers use linear mixed-effects models (LMMs) versus repeated-measures analysis of variance (RM-ANOVA) for analysing repeated-measures data? I first outline the conceptual and statist... 17317
JsonGeller @jgeller1phd.bsky.social · 02/10/2026Much appreciation to @matti.vuorre.com @rmkubinec.bsky.social @chelseaparlett.bsky.social for helping craft this beast! Also to reviewers @scoretta.bsky.social and @solomonkurz.bsky.social for making this a better paper! 280
JsonGeller @jgeller1phd.bsky.social · 02/10/2026link.springer.com/article/10.3...link.springer.comA beta way: A tutorial on Bayesian beta regression for psychological research - Behavior Research MethodsRates, percentages, and proportions are common outcomes in psychology and the social sciences. These outcomes are often analyzed using models that assume normality, but this practice overlooks importa... 1124
JsonGeller @jgeller1phd.bsky.social · 02/10/2026New tutorial finally in press with @rmkubinec.bsky.social @chelseaparlett.bsky.social and @matti.vuorre.com. It has everything you could possible want: Quippy headings, a whole lot of beta, bayesian analyses and frequentist analyses side by side in harmony. link.springer.com/article/10.3...rdcu.be 27825
JsonGeller @jgeller1phd.bsky.social · 01/10/2026Erin asked if you can contact her: EBuchanan@harrisburgu.edu. She said you can have more than three columns just can't scroll sideways. 100
JsonGeller @jgeller1phd.bsky.social · 01/10/2026Seems like this could be a very useful feature to have 100
JsonGeller @jgeller1phd.bsky.social · 01/10/2026I can ask Erin how hard it would to be implement something like that. 120
JsonGeller @jgeller1phd.bsky.social · 01/10/2026Yes! I just submitted one on ex Gaussian Bayesian analyses in brms—Lots of people using x and x is not really doing what a lot of people think it is. 010
JsonGeller @jgeller1phd.bsky.social · 01/10/2026Have you thought about commentary and notes option at BRM? 120
Reposted by JsonGellerGlossa Psycholinguistics @glossapsycholx.bsky.social · 30/09/2026We're excited to announce the publication of 'Readers can recognise multiple words at a glance but out of order: Evidence from transposed word effects in Japanese' by Kondo & Yano, available here: escholarship.org/uc/item/1jd2...escholarship.org 185
JsonGeller @jgeller1phd.bsky.social · 30/09/2026If it is tutorial based then BRM has a tutorial series it could fall under. 111
JsonGeller @jgeller1phd.bsky.social · 30/09/2026@akmontoya.bsky.social probably has some good suggestions! 200
JsonGeller @jgeller1phd.bsky.social · 30/09/2026Feel this! Too bad p < .05 or * is all you need if you use some freq methods. 020
JsonGeller @jgeller1phd.bsky.social · 29/09/2026Anyone at Brain and Language journal know how to reach an actual person LOL. 010
Reposted by JsonGellerDan Quintana @dsquintana.bsky.social · 19/09/2026New preprint! 🎉 I analysed 1660 papers from 4 psychology journals and found materials sharing went from 9% of papers in 2015 to 82% in 2025, and these materials *do* get downloaded — a median of 135 times each. BUT shared code is often hard to run. doi.org/10.31234/osf... Let's walk through it 🧵 4265113
JsonGeller @jgeller1phd.bsky.social · 17/09/2026Oh man! I didn't think we could get a close replication of this study and I think Netflix has done it! I'm glad there will be a director there coaching the prisoners and guards how to act. 040
JsonGeller @jgeller1phd.bsky.social · 15/09/2026quantitude.org/s2e09-manova...quantitude.orgS2E09: MANOVA Must Die – Quantitude 160
JsonGeller @jgeller1phd.bsky.social · 15/09/2026The one with Will Ramos from The deathcore band Lorna Shore is excellent! 010
JsonGeller @jgeller1phd.bsky.social · 11/09/2026Now worries! Share the materials when you have them :). 000
JsonGeller @jgeller1phd.bsky.social · 11/09/2026Submit! Submit! Please repost if you might have interested networks. 011
JsonGeller @jgeller1phd.bsky.social · 11/09/2026I want to attend but won't be able! Will it be recorded? 220
JsonGeller @jgeller1phd.bsky.social · 11/09/2026Join @felipefv.bsky.social next week if you can! He will chat about our most recent paper showing how to use nix and rix! 020
JsonGeller @jgeller1phd.bsky.social · 10/09/2026They were in Boston. What a fantastic show! Bruce never fails to amaze me. 000
JsonGeller @jgeller1phd.bsky.social · 09/09/2026Seeing Iron Maiden tonight. I wonder if @profandyfield.com approves. 140