F. Javier Rubio

GitHub - FJRubio67/MOOMIN: Moment-Objective Minimum-Discrepancy (MOOMIN) Prior Moment-Objective Minimum-Discrepancy (MOOMIN) Prior - FJRubio67/MOOMIN

R code and data: github.com/FJRubio67/MO...

New short paper forthcoming in Statistics & Probability Letters:

An objective non-local prior for skew-symmetric models.

arxiv.org/abs/2603.08285

This paper develops a Moment-Objective Minimum-Discrepancy (MOOMIN) Prior for testing symmetry against skew-symmetric alternatives.

4-panel Comic "Women in Science" by War and Peas. 1. Man in ancient clothes and wig enters the room. He says, "I've returned from my trip to the future!" 2. "Women are doing science!" 3. Another man answers, "But there's still structural inequality and sexism making it difficult for them?" 4. "YES!" "Thank God!"

Happy International Day of Women and Girls in Science!

#InternationalDayofWomenandGirlsinScience

New preprint with my student Eric Chen, co-supervised with Jim Griffin:

“Bayesian variable and hazard structure selection in the General Hazard model”

arxiv.org/abs/2602.03756

We develop Bayesian methododology for simultaneous selection of variables and the hazard structure in survival analysis

FDA guidance on Bayesian clinical trials
statmodeling.stat.columbia.edu/2026/01/15/f...

The effect of the shape (skewness) parameter in skew-symmetric models, Part III

Based on Le Cam divergence, showing that the effect of this parameter in some models, such as the skew-normal, is tiny in a neighbourhood of 0

rpubs.com/FJRubio/DivM...

Mathematical Colloquium (at King's College London): A duality in the foundations of probability and statistics through history by Vladimir Vovk

www.kcl.ac.uk/events/mathe...

#OTD 1763 Richard Price (1723-1791) reads ‘An Essay towards solving a Problem in the Doctrine of Chances' to the Royal Society. It is the basis of what is now called Bayes's Theorem, written by his friend Thomas Bayes who had died 2 years before.

New paper with J.A. Christen, just accepted in Statistical Methods in Medical Research

"Hazard-based distributional regression via ordinary differential equations"

preprint: arxiv.org/abs/2512.16336

R and Julia code + data: github.com/FJRubio67/Su...

#rstats #JuliaLang #SciML

All the material for my Bayesian Data Analysis course is available online, including the lectures, which we re-recorded this fall (some of them by @aloctavodia.bsky.social and Noa Kallioinen while I was on vacation). The video links are listed in the schedule at avehtari.github.io/BDA_course_A...

4 or more UCL Departmental Studentships

Deadline 9 January 2026

PhD Studentships, based at the UCL Department of Statistical Science. Open to Home and Overseas applicants.

www.ucl.ac.uk/mathematical...

Also, apply for admission to the MPhil/PhD programme.

www.ucl.ac.uk/mathematical...

We are hiring!

We are recruiting two Assistant Professors. The closing date is 25 January 2026. More information here 🔗: warwick-careers.tal.....

The great debate: innovation, sustainability & equity in cancer care | LSHTM The great debate: is delivering innovation compatible with sustainable and equitable cancer care?The current state of cancer care in England is a regular news feature, whether its long waiting

How can we make cancer care in England both equitable and sustainable for the NHS? 🤔

Join researchers, patient advocates & experts for The Great Debate. This event is part of London Global Cancer Week, co-hosted ICON & the Institute of Cancer Policy @kingscollegelondon.bsky.social

👉 bit.ly/43eRxiY

Daniela Witten

Journal submissions got you stressed? Daniela Witten of the University of Washington shares advice about editing and dealing with rejection when submitting papers to academic journals. magazine.amstat.org/...

English indices of deprivation 2025 Statistics on relative deprivation in small areas in England. Further details are provided at the bottom of this page and in the FAQ document.

English Indices of Deprivation 2025 (IoD25) and Index of Multiple Deprivation (IMD25) are published today. This is an update in the series, following on from the 2019 #deprivation indices.

UK Government website:
www.gov.uk/government/s...

📘 An interesting initial book release by David Rossell on variable and model selection:

👉 davidrusi.github.io/modelSelecti...

it provides accessible material for students learning the fundamentals of high-dimensional model selection, and it documents the R package modelSelection (formerly mombf).

Bayesian Variable Selection Under Sample Selection and Model Misspecification Sample selection bias arises when missingness in the outcome of interest correlates with the outcome itself, leading to non-randomly selected samples. A common approach to correct bias from sample selection is to use sample selection models that jointly model the selection mechanism and the outcome of interest. Formulating these models typically rely on exclusion restrictions (variables that are predictors of selection but not appearing in the outcome equation) to ensure identifiability of the parameters. However, the choice of exclusion restrictions often depends on heuristics or expert judgment, potentially leading to the inclusion of irrelevant variables or the omission of important ones. Additionally, distributional misspecification and omitted variable bias are frequent challenges in this framework. To formally address these issues, we propose a Bayesian variable selection (BVS) methodology that incorporates both local priors (LPs) and non-local priors (NLPs), enabling the identification of variables with predictive power for the outcome and selection processes. We develop computational tools to conduct BVS in sample selection models based on a Laplace approximation of the marginal likelihood, and characterize the resulting Bayes factor rates under model misspecification. We establish model selection consistency for both classes of priors, showing that the proposed methodology correctly identifies active variables for both the selection process and outcome process asymptotically. The priors are calibrated to account for the possibility of distributional misspecification and omitted variable bias. We present a simulation study and real-data applications to explore the finite-sample effects of model misspecification on BVS. We compare the performance of the proposed methodology against BVS based on spike-and-slab (SS) priors and the Adaptive LASSO (ALASSO), an adaptive weighting of the least absolute shrinkage and selection operator (LASSO).

New paper with E.O. Ogundimu and our PhD student Adam Iqbal, just accepted in Bayesian Analysis

Bayesian Variable Selection Under Sample Selection and Model Misspecification

doi.org/10.1214/25-B...

R code and data can be found at:

github.com/adam-iqbal/b...

GitHub - FJRubio67/PTCMGH: Promotion Time Cure Models with a General Hazard structure Promotion Time Cure Models with a General Hazard structure - FJRubio67/PTCMGH

New R package PTCMGH: The PTCMGH R package implements promotion time cure models with a general hazard structure. The package, along with a tutorial for simulating and fitting these models, can be found at:

github.com/FJRubio67/PT...

rpubs.com/FJRubio/PTCMGH

#rstats #survival

The new Bayesian Social Sciences section of @isba-bayesian.bsky.social has just been created: bss-isba.github.io. The committee is myself as chair, @robinryder.bsky.social, chair elect from 2027, @nialfriel.bsky.social, program chair, @monjalexander.bsky.social, Treasurer, EJWagenmakers, Secretary.

A Deep Dive Into DifferentialEquations.jl | JuliaCon Global 2025 | Rackauckas, Smith YouTube video by The Julia Programming Language

DifferentialEquations.jl is many things, and lots of people only use a small portion of it. Check out the JuliaCon 2025 workshop: introduces many aspects of the packages that the developers feel are underutilized and under-understood!

#julialang #sciml

www.youtube.com/watch?v=lSGF...

4-panel-comic by War and Peas Panel 1: Jim, a man in a yellow jacket, excitedly approaches a woman in a pink dress. He says, "Honey, I finally finished the prediction machine!" while pointing at a prediction machine on a small table. The machine displays an unclear message. Panel 2: The woman, standing next to the prediction machine, says, "I'm leaving you, Jim." Panel 3: The machine's screen reads, "Everyone you love will leave you." Jim, looking at the machine, appears shocked. Panel 4: Jim, with a confident pose, says, "What a success!" The prediction machine now displays a garbled message, "Everyone love will have you," and a "SLAM" sound effect indicates the woman has left, shutting the door behind her.

Handbook of Markov Chain Monte Carlo This thoroughly revised and expanded second edition of the Handbook of Markov Chain Monte Carlo reflects the dramatic evolution of MCMC methods since the publication of the first edition. With the add...

Handbook of Markov Chain Monte Carlo, 2nd Edition. Radu V. Craiu, Dootika Vats, Galin Jones, Steve Brooks, Andrew Gelman, Xiao-Li Meng (eds.) Chapman & Hall 2026, 680 Pages. www.routledge.com/Handbook-of-...

Model Uncertainty and Missing Data: An Objective Bayesian Perspective The interplay between missing data and model uncertainty—two classic statistical problems—leads to primary questions that we formally address from an objective Bayesian perspective. For the general regression problem, we discuss the probabilistic justification of Rubin’s rules applied to the usual components of Bayesian variable selection, arguing that prior predictive marginals should be central to the pursued methodology. In the regression settings, we explore the conditions of prior distributions that make the missing data mechanism ignorable, provided that it is missing at random or completely at random. Moreover, when comparing multiple linear models, we provide a complete methodology for dealing with special cases, such as variable selection or uncertainty regarding model errors. In numerous simulation experiments, we demonstrate that our method outperforms or equals others, in consistently producing results close to those obtained using the full dataset. In general, the difference increases with the percentage of missing data and the correlation between the variables used for imputation. Finally, we summarize possible directions for future research.

The subsequent webinar will be on:

📅 November 5, 2025 (4:00 PM UTC | 11:00 AM EST | 5:00 PM CET)
“Model Uncertainty and Missing Data: An Objective Bayesian Perspective”
by G. García-Donato, M. Eugenia Castellanos, S. Cabras, A. Quirós, and A. Forte
doi.org/10.1214/25-B...

The 𝐈𝐧𝐭𝐞𝐫𝐧𝐚𝐭𝐢𝐨𝐧𝐚𝐥 𝐒𝐨𝐜𝐢𝐞𝐭𝐲 𝐟𝐨𝐫 𝐁𝐚𝐲𝐞𝐬𝐢𝐚𝐧 𝐀𝐧𝐚𝐥𝐲𝐬𝐢𝐬 (𝐈𝐒𝐁𝐀) was founded in 1992 to promote the development and application of Bayesian analysis.

𝘐𝘚𝘉𝘈 𝘱𝘳𝘰𝘷𝘪𝘥𝘦𝘴 𝘢𝘯 𝘪𝘯𝘵𝘦𝘳𝘯𝘢𝘵𝘪𝘰𝘯𝘢𝘭 𝘤𝘰𝘮𝘮𝘶𝘯𝘪𝘵𝘺 𝘧𝘰𝘳 𝘵𝘩𝘰𝘴𝘦 𝘪𝘯𝘵𝘦𝘳𝘦𝘴𝘵𝘦𝘥 𝘪𝘯 𝘉𝘢𝘺𝘦𝘴𝘪𝘢𝘯 𝘢𝘯𝘢𝘭𝘺𝘴𝘪𝘴 𝘢𝘯𝘥 𝘪𝘵𝘴 𝘢𝘱𝘱𝘭𝘪𝘤𝘢𝘵𝘪𝘰𝘯𝘴.

Find us across the web:
linktr.ee/ISBAbayesian

Most cancer patients face comorbidities that complicate survival. We use Bayesian machine learning (BART) in a relative survival framework to estimate excess hazard, uncover vulnerable subgroups, and identify drivers of inequalities in colon cancer survival.

New paper, with P. Basak, A.R. Linero, and C. Maringe, accepted in JASA A&CS

"Understanding Inequalities in Cancer Survival Using Bayesian Machine Learning"

doi.org/10.1080/0162...

#inequalities #cancer #survival #Bayesian #MachineLearning @icon-lshtm.bsky.social @statisticsucl.bsky.social

The effect of the shape (skewness) parameter in skew-symmetric models: Part II

rpubs.com/FJRubio/Disc...

Based on a recently proposed discrepancy measures, it shows that in certain models, such as the skew-normal, the influence of the shape parameter is negligible across a broad interval around 0.

Reminder that all three books I've co-authored are freely available online for non-commercial use (and the fourth will be, too)

Approaches for modelling survival time in groups with very low risk I'm currently working on a study with a group of hematologists. Patients with PV (Polycythemia vera) have very low risk of future thromboembolism after diagnosis due to disease management. Patients

I've got 1 event in one group in which we know the risk of the outcome is very low.

This is creating enormous confidence intervals. Can I use firth penalization? Should I get more data? All ideas welcome

stats.stackexchange.com/questions/66...