Rich May
LightNews LightNews
banner
richiemay.bsky.social
Rich May
@richiemay.bsky.social
95 followers 410 following 12 posts
Lecturer/researcher • learning • language •statistics • n of 1 • time series• no merch table or magic beans • Bristol, UK
Posts Replies Media Videos
Reposted by Rich May
fusaroli.bsky.social
The takeaway: Turn-taking isn't a single, monolithic trait that reflects social competence. It’s a multicomponential skill that emerges from the interplay of individual differences, moment-to-moment predictions, and interpersonal adjustments—all shaped by social context. 8/
October 15, 2025 at 9:28 AM
Reposted by Rich May
fusaroli.bsky.social
Conversational turn-taking feels effortless, but it's a complex dance. We find social context—who you're talking to and what you're talking about—fundamentally changes conversational dynamics in both autistic & TD children. 1/

onlinelibrary.wiley.com/doi/10.1111/... w @chrismmcox.bsky.social
Social Context Matters for Turn‐Taking Dynamics: A Comparative Study of Autistic and Typically Developing Children
Engaging in fluent conversation is a surprisingly complex task that requires interlocutors to promptly respond to each other in a way that is appropriate to the social context. In this study, we dise...
onlinelibrary.wiley.com
October 15, 2025 at 9:28 AM
Reposted by Rich May
jamiecummins.bsky.social
Can large language models stand in for human participants?
Many social scientists seem to think so, and are already using "silicon samples" in research.

One problem: depending on the analytic decisions made, you can basically get these samples to show any effect you want.

THREAD 🧵
The threat of analytic flexibility in using large language models to simulate human data: A call to attention
Social scientists are now using large language models to create "silicon samples" - synthetic datasets intended to stand in for human respondents, aimed at revolutionising human subjects research. How...
arxiv.org
September 18, 2025 at 7:56 AM
Reposted by Rich May
mollfw.bsky.social
New paper on precise tool use learning in carrion crows @currentbiology.bsky.social. We show that—like New Caledonian crows—expert carrion crows pay close attention to the working end of their tool, suggesting tool integration into their peripersonal space. 🧵 & vids! 👇

www.cell.com/current-biol...
September 11, 2025 at 10:15 AM
Reposted by Rich May
dingdingpeng.the100.ci
Ever stared at a table of regression coefficients & wondered what you're doing with your life?

Very excited to share this gentle introduction to another way of making sense of statistical models (w @vincentab.bsky.social)
Preprint: doi.org/10.31234/osf...
Website: j-rohrer.github.io/marginal-psy...
Models as Prediction Machines: How to Convert Confusing Coefficients into Clear Quantities Abstract Psychological researchers usually make sense of regression models by interpreting coefficient estimates directly. This works well enough for simple linear models, but is more challenging for more complex models with, for example, categorical variables, interactions, non-linearities, and hierarchical structures. Here, we introduce an alternative approach to making sense of statistical models. The central idea is to abstract away from the mechanics of estimation, and to treat models as “counterfactual prediction machines,” which are subsequently queried to estimate quantities and conduct tests that matter substantively. This workflow is model-agnostic; it can be applied in a consistent fashion to draw causal or descriptive inference from a wide range of models. We illustrate how to implement this workflow with the marginaleffects package, which supports over 100 different classes of models in R and Python, and present two worked examples. These examples show how the workflow can be applied across designs (e.g., observational study, randomized experiment) to answer different research questions (e.g., associations, causal effects, effect heterogeneity) while facing various challenges (e.g., controlling for confounders in a flexible manner, modelling ordinal outcomes, and interpreting non-linear models). Figure illustrating model predictions. On the X-axis the predictor, annual gross income in Euro. On the Y-axis the outcome, predicted life satisfaction. A solid line marks the curve of predictions on which individual data points are marked as model-implied outcomes at incomes of interest. Comparing two such predictions gives us a comparison. We can also fit a tangent to the line of predictions, which illustrates the slope at any given point of the curve. A figure illustrating various ways to include age as a predictor in a model. On the x-axis age (predictor), on the y-axis the outcome (model-implied importance of friends, including confidence intervals). Illustrated are 1. age as a categorical predictor, resultings in the predictions bouncing around a lot with wide confidence intervals 2. age as a linear predictor, which forces a straight line through the data points that has a very tight confidence band and 3. age splines, which lies somewhere in between as it smoothly follows the data but has more uncertainty than the straight line.
August 25, 2025 at 11:49 AM
richiemay.bsky.social
For a coffee person on a budget (me!), there is no better combo….
Cafelat Robot lever press espresso machine and a Commandante C40 hand grinder 36g of Espresso in an espresso cup with a Dachshund illustration
August 23, 2025 at 2:03 PM
Reposted by Rich May
mcxfrank.bsky.social
Experimentology is out today!!! A group of us wrote a free online textbook for experimental methods, available at experimentology.io - the idea was to integrate open science into all aspects of the experimental workflow from planning to design, analysis, and writing.
Experimentology cover: title and curves for distributions.
July 1, 2025 at 6:26 PM
Reposted by Rich May
easystats.github.io
Unlock hidden patterns in longitudinal data! 🚀 Our new vignette shows how to use brms & easystats to perform Growth Mixture Models, identify unique developmental trajectories, and visualize & interpret your findings with ease. #rstats #brms #easystats
easystats.github.io/modelbased/a...
An Introduction to Growth Mixture Models with brms and easystats
easystats.github.io
June 24, 2025 at 5:33 PM
Reposted by Rich May
tsawallis.bsky.social
It's bonkers that in academic science we spend hours obsessing over the wording of a paper, but often only one person has seen the code that produced the results! 2/N
April 16, 2025 at 1:23 PM
richiemay.bsky.social
B.F Skinner from the paper, “How to discover what you have to say” pmc.ncbi.nlm.nih.gov/articles/PMC...
Quote from BF Skinner about writing and self-discovery. It states that immediate consequences like surprising yourself with new ideas, clarifying confusing points, and enjoying your own writing are effective in discovering your authentic voice.
April 18, 2025 at 1:36 PM
Reposted by Rich May
vincentab.bsky.social
📚😅🎉

Yay!! I just submitted the complete manuscript of my upcoming book to the publisher!

Learn to easily and clearly interpret (almost) any stats model w/ R or Python. Simple ideas, consistent workflow, powerful tools, detailed case studies.

Read it for free @ marginaleffects.com

#RStats #PyData
Model to Meaning: How to interpret statistical models with marginaleffects for R and Python
April 10, 2025 at 7:06 PM
Reposted by Rich May
andrew.heiss.phd
writing another review where I point to the Table 2 Fallacy (doi.org/10.1093/aje/... and doi.org/10.1017/psrm...) and say stop interpreting every single coefficient
The Table 2 Fallacy: Presenting and Interpreting Confounder and Modifier Coefficients
Abstract. It is common to present multiple adjusted effect estimates from a single model in a single table. For example, a table might show odds ratios for
doi.org
March 23, 2025 at 2:10 AM
Reposted by Rich May
fusaroli.bsky.social
I was recommending my students @jonathantemplin.com 's awesome course recordings (jonathantemplin.com/teaching/) to get more in-depth discussion of stan tips and psychometrics models and I discovered there's a new 2024 version. house chores will be more fun for a while.
Teaching
jonathantemplin.com
February 28, 2025 at 12:02 PM
Reposted by Rich May
lucyfoulkes.bsky.social
Important new evidence published today: large-scale DofE trial (N=12,166) found that two universal MH awareness interventions, in secondary schools, led to an *increase* in emotional symptoms at long term (9-12 month) follow up

tinyurl.com/4ffday8y

Thread below

/1
Department for Education. Effectiveness of school mental health awareness interventions Universal approaches in English secondary schools February 2025
February 10, 2025 at 12:05 PM
Reposted by Rich May
njclark.bsky.social
Another video in my series on applied time series and forecasting with the {mvgam} #rstats 📦. This one introduces State Space hierarchical GAMs and GPs for tackling multivariate series youtu.be/2POK_FVwCHk?...
Time series in R and Stan using the mvgam package: hierarchical GAMs
YouTube video by Nicholas Clark
youtu.be
February 4, 2025 at 8:09 AM
richiemay.bsky.social
Behaviour goes where reinforcement flows. Choice of task driven by relative success rate. Three preregistered experiments with young kids. Open version here jlnrd.github.io/Publications...
jlnrd.github.io
January 28, 2025 at 9:52 AM
Reposted by Rich May
error.reviews
New report! Hehman et al. (2018) "Disproportionate Use of Lethal Force in Policing Is Associated With Regional Racial Biases". Based on the review by @conjugateprior.org, we find a Major Error that affects a core conclusion. We recommend the authors seek a correction.
error.reviews/reviews/hehm...
Hehman et al. (2018)
ERROR is a bug bounty program for science to systematically detect and report errors in academic publications
error.reviews
January 20, 2025 at 1:14 PM
Reposted by Rich May
markrubin.bsky.social
UK universities might misattribute changes in their rankings to their institutional strategies when random fluctuations in the ranking system are a more likely explanation.

Preprint: osf.io/preprints/ps...

BSky author: @tvpollet.bsky.social

#UKHE #AcademicSky
This issue is especially difficult given the lack of correspondence in increases and deceases in ranks between the RRA method and the university guides. Universities aim to improve their ranks in league tables and undertake different strategies to achieve this. Any changes in ranks from one year to the next may be attributed by university staff to strategies that have been put in place to improve the university. However, if the implementation of such strategies has been effective, we would expect to see similar changes in the rankings based on the RRA method and the university guides. The lack of correspondence suggests changes may be more likely to be driven by random fluctuations. By focusing specifically on the university guides, institutions may misattribute changes to these strategies rather than random fluctuation. As such, resources may be allocated to ineffective strategies for improving the institution (e.g., https://blogs.lse.ac.uk/impactofsocialsciences/2021/03/22/the-absurdity-of-universityrankings/.
January 17, 2025 at 5:07 PM
Reposted by Rich May
ufeest.bsky.social
I am beyond excited to announce the imminent arrival of my book. Operationism in Psychology. An Epistemology of Exploration: press.uchicago.edu/ucp/books/bo...
Brief chapter summaries below (1/10)
Operationism in Psychology
Analyzes psychological research to offer insights into how methodological and ontological questions are intertwined.   Psychology has seen an intense debate about the lack of replicability of results ...
press.uchicago.edu
January 11, 2025 at 5:37 PM
Reposted by Rich May
beadmomsw.bsky.social
12 years. RIP my darling boy.
January 11, 2025 at 5:05 PM
Reposted by Rich May
adamjkucharski.bsky.social
Also, a reminder that the average effect measured in a population study usually has little predictive value if looking at individual health outcomes: kucharski.substack.com/p/the-popula...
The popularity of the average
Or why ‘personalised’ health companies sell everyone the same branded product
kucharski.substack.com
December 20, 2024 at 11:22 AM
Reposted by Rich May
miguelhernan.org
Upgrade your #causalinference arsenal.

A revision of our book "Causal Inference: What If" is available at miguelhernan.org/whatifbook

Thanks to everyone who suggested improvements, reported typos, and proposed new citations and material.

Enjoy the #WhatIfBook plus code and data. Also, it's free.
December 23, 2024 at 9:28 AM
richiemay.bsky.social
“No causes in, no causes out”(Cartwright, 1994)
janelleshane.com Janelle Shane @janelleshane.com · Dec 14
They trained an AI model on a widely used knee osteoarthritis dataset to see if it would be able to make nonsensical predictions - whether the patient ate refried beans, or drank beer. It did, in part by somehow figuring out where the x-ray was taken.
www.dartmouth-health.org/about/news/a...
AI thought X-rays of your knees show if you drink beer—they don’t.
Dartmouth Health study shows how easily AI models can give right answers for wrong reasons
www.dartmouth-health.org
December 17, 2024 at 9:13 AM
Reposted by Rich May
daxkellie.bsky.social
If you missed my talk but still want to learn how to make your R code more reproducible, my slides are here 🙂:

daxkellie.quarto.pub/will-your-co...

All the links to packages and resources I mentioned are there, so hopefully this can be a nice reference, too!

#ESAus2024 #rstats #quartopub 🧪🌏
Title slide: Will your code run again? Tips for making code reproducible in R
December 9, 2024 at 6:06 AM
richiemay.bsky.social
Also presented by Richard Morey here…. youtu.be/TvUSSaU8tVY?...
December 7, 2024 at 6:21 PM