Giacomo Bignardi

@bignardi.bsky.social

Research Associate at the Social, Genetic & Developmental Psychiatry Centre, Kings College London. Interests: developmental psychology, data science, coffee. www.bignardi.co.uk

Scientists should be judged not just on their research, but the claims they make. Quitting smoking is one of the most powerful ways you can improve your health. Visiting a museum can never come close. Such a claim should require extraordinary evidence. This study is anything but. 18/18 🧵

🚨 Call for Abstracts: The New Measurement Heretics We welcome proposals from researchers in the philosophy, history, sociology, and anthropology of measurement who would like to address themes around formal & informal measurement concepts ⚖️ Find out more 👇 medhumsplatform.org/call-for-abs...

Call for Abstracts: The New Measurement Heretics

We invite proposals from researchers in the philosophy, history, sociology and anthropology of measurement for a new edited collection. Deadline 15 June 2026.

medhumsplatform.org

I've made an R package for Bayesian Rasch #psychometrics with brms models, easyRaschBayes (on CRAN), implementing simple functions to create figures and tables with model fit metrics, etc. Attaching figures from conditional item infit, item-restscore with GK gamma, and the log-likelihood criterion.

BildBildBild

"There are signs that the Bayes Factor is increasingly taking on a role analogous to that of the p-value, serving as a device for the automation of decisions rather than as a tool for substantive inference." Excellent new preprint by Carol Ting on the rise of NHST. #Methodology #stats

The Rise of Null Hypothesis Significance Testing (NHST): Institutional Massification and the Emergence of a Procedural Epistemology

It has long been a puzzle why, despite sustained reform efforts, many applied scientific fields remain dominated by Null Hypothesis Significance Testing (NHST), a framework that dichotomizes study res...

arxiv.org

as I'm revising my course materials, I keep stumbling upon cool @mc-stan.org developments. Current favorites: 1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective! 1/

In 2021 we reported that live learning outperformed recorded learning. In a new preregistered analysis, my first senior-author paper led by Stan de Visser (pre-print), we find that this benefit does not increase with interactivity. The potential to interact may be enough to boost learning. A thread:

Bild

This is really neat. I have borrowed the reliability() function to my `easyRasch` package, and use plausible values instead of fully Bayesian estimation to produce similar estimates/CIs, see code example below. RMU point estimates are similar to EAP reliability. pgmj.github.io/easyRasch/re...

Giacomo Bignardi@bignardi.bsky.social · 12mo ago

New preprint with @rogierk.bsky.social @paulbuerkner.com - we introduce "relative measurement uncertainty" - a reliability estimation method that's applicable across a broad class of Bayesian measurement models (e.g., generative-, computational- and item response theory-models osf.io/h54k8

I've added a new example to our paper's repo, demonstrating how our reliability method replicates Cronbach's alpha for a simple model, but also how our method can account for: (i) binary data, (ii) varying numbers of items per pps, & (iii) improvement over trials www.bignardi.co.uk/8_bayes_reli...

Estimating Mean Score Reliability with RMU

bignardi.co.uk

Giacomo Bignardi@bignardi.bsky.social · 12mo ago

New preprint with @rogierk.bsky.social @paulbuerkner.com - we introduce "relative measurement uncertainty" - a reliability estimation method that's applicable across a broad class of Bayesian measurement models (e.g., generative-, computational- and item response theory-models osf.io/h54k8