Reposted by Michael SchomakerCTML - Center for Targeted Machine Learning and Causal Inference @berkeleyctml.bsky.social · 6hCTML GSR Nick Williams to present at Berkeley Causal Lab Seminar next week! Join the seminar on Wednesday, October 14 for his talk, “Two Attempts at Improving Finite Sample Performance of Doubly-Robust Estimators with Resampling” 📅 Wednesday, October 14, 2026 🕑 2:00–3:30 PM 📍 Gateway 3355 021
Reposted by Michael SchomakerDarren Dahly @statsepi.bsky.social · 06/10/2026Many papers I see: A global problem Search for modifiable "risk factors" A cohort study sorry I mean real-world data "Multivariate" regression Some associations Can't say cause Residual confounding Policy must change in ways having nothing to do with our findings More research is needed 86611
Reposted by Michael SchomakerAchim Zeileis @zeileis.org · 07/10/2026🚨 After 20 years of service, the R-Forge code-sharing platform will be retired. #rstats Timeline: - Until end of 2026: Normal operations. - Jan 2027: Switch to read-only, but SVN continues to work. - Jan 2028: SVN also read-only. Reason: The underlying FusionForge software is no longer maintained. 1129
Reposted by Michael SchomakerSpotlight @spotlightnsp.bsky.social · 30/09/2026JUST PUBLISHED | All medicines and treatments have to go through lengthy safety and efficacy testing, but this is particularly tricky – and often delayed – for babies. These complexities are worth exploring and grappling with. www.spotlightnsp.co.za/2026/09/30/t...spotlightnsp.co.zaThe case for including more babies and young children in medical researchAll medicines and treatments have to go through lengthy safety and efficacy testing, but this is particularly tricky - and often delayed - for one important age group. Elna Schütz explores the complex... 002
Reposted by Michael SchomakerBrennan Kahan @brennankahan.bsky.social · 15/09/2026***JOB ALERT*** We are seeking to appoint 3 Statistical Methodologists to work on methods related to the statistical analysis of clinical trials, or innovative design methodology. The posts will be based within the UCL Institute of Clinical Trials and Methodology. www.ucl.ac.uk/work-at-ucl/...ucl.ac.ukUCL – University College LondonUCL is consistently ranked as one of the top ten universities in the world (QS World University Rankings 2010-2022) and is No.2 in the UK for research power (Research Excellence Framework 2021). 11220
Reposted by Michael SchomakerIván Díaz @idiaz.bsky.social · 10/09/2026(1/22) Over the last few days I have been discussing the role of formal causal inference in RCTs, and in general the role of formalism and rigor in statistics in twitter with @f2harrell.bsky.social. Thread with an example for why both are fundamental for biomedical research: 3135
Reposted by Michael SchomakerLMU München @lmu.de · 09/09/2026Warum zieht uns Social Media in den Bann? Aus kurz mal online sein, wird stundenlanges Scrollen. 📲 Was bedeutet das für Kinder & Jugendliche? Sollte eingeschränkt werden, in welchem Umfang Kinder Social Media nutzen dürfen? Welche Rolle haben dabei KI-Apps? Eine Einschätzung unserer Experten!lmu.deSocial Media: „Kinder sind besonders gefährdet“LMU-Forschende erklären, worauf es bei der Nutzung von Sozialen Medien und KI-Apps durch Kinder und Jugendliche ankommt. 032
Reposted by Michael SchomakerJonathan Bartlett @jonathan-bartlett.bsky.social · 09/09/2026I am seeking to support an applicant for a PhD scholarship to pursue a PhD at LSHTM, starting October 2027, on developing machine learning methods for handling missing data in statistical analyses. For more details, and to express interest, please complete the form docs.google.com/forms/d/e/1F...docs.google.comLSHTM PhD - machine learning for missing dataI am seeking to support an applicant for a PhD scholarship from the UBEL DTP to pursue at PhD at LSHTM, starting October 2027. The topic is about developing machine learning methods for handling missi... 064
Reposted by Michael SchomakerSpotlight @spotlightnsp.bsky.social · 04/09/2026ICYMI | To Professor Salim Abdool Karim, excellence should be the only standard. In science, he says he is inspired by imaginative thinking such as that of American comic publisher Stan Lee, co-creator of Spider-Man. www.spotlightnsp.co.za/2026/06/24/f...spotlightnsp.co.zaFrom Spider-Man to Mandela, the many influences in Professor Salim Abdool Karim’s remarkable scientific careerTo Professor Salim Abdool Karim, excellence should be the only standard. In science, he says he is inspired by imaginative thinking such as that of American comic publisher Stan Lee, co-creator of Spi... 021
Reposted by Michael SchomakerDan Malinsky @danielmalinsky.bsky.social · 04/09/2026A paper @lastpositivist.bsky.social and I wrote is finally getting published... if you like it, it was all my idea. If you hate it, it was all Liam's idea. 0242
Reposted by Michael SchomakerLMU München @lmu.de · 03/09/2026🏅 ERC Grants: Sieben Forschungsprojekte der LMU ausgezeichnet 👏 Sieben Nachwuchsforschende haben je einen Starting Grant des European Research Council (ERC) für ihre Projekte eingeworben. Mehr dazu hier: www.lmu.de/de/newsroom/... 0163
Reposted by Michael SchomakerAmerican Statistical Association History of Statistics @hos-asa.bsky.social · 29/08/2026In Aug 1934 Harold Jeffreys first expresses the idea of Bayesian probability in his paper "Probability and Scientific Method". He argues that that it is not necessarily synonymous with frequency but based on a logical degree of prior belief given the data. Ronald Fisher of course rejected this idea 051
Reposted by Michael SchomakerSpotlight @spotlightnsp.bsky.social · 24/08/2026World’s largest research funder lifts ban on South Africa The United States National Institutes of Health (NIH) has lifted its ban nearly 18 months after an order to stop work with South...spotlightnsp.co.zaWorld’s largest research funder lifts ban on South AfricaThe United States National Institutes of Health (NIH) has lifted its ban nearly 18 months after an order to stop work with South Africa. The funding ban created a crisis... 014
Reposted by Michael SchomakerJess Edwards @edwardsjk.bsky.social · 21/08/2026I'm recruiting a postdoc to join a small and collaborative team at UNC focused on causal inference and measurement error in HIV research. Come work with us! unc.peopleadmin.com/postings/324... #episkyunc.peopleadmin.comPostdoctoral Research AssociateThe University of North Carolina at Chapel Hill Department of Epidemiology is recruiting a Postdoctoral Research Associate to contribute to projects related to quantitative epidemiologic methods and H... 087
Reposted by Michael SchomakerPausal Zivference @pausalz.bsky.social · 10/08/2026I've been working on developing materials for my 'research group'. Mostly it is items that I would have found helpful as a student and general recommendations (including on LLMs) I made it all publicly available in the hopes it can be useful to others. I also welcome any feedback or suggestionsgithub.comGitHub - pzivich/LabGroupMaterials: Collection of my lab group materials for students and traineesCollection of my lab group materials for students and trainees - pzivich/LabGroupMaterials 3112
Reposted by Michael SchomakerThom Volker @thomvolker.bsky.social · 01/08/2026The PI presenting the paper written entirely by the rest of their research team 0213
Reposted by Michael SchomakerAmerican Statistical Association History of Statistics @hos-asa.bsky.social · 31/07/20262/ He showed that cheap root vegetables could fed to sheep kept indoors during winter rather than costly grain. This meant meat could be available & affordable even during hard times 011
Reposted by Michael SchomakerPausal Zivference @pausalz.bsky.social · 29/07/2026A new paper on bounds for per-protocol effects in trials My motivation in writing this paper was to twofold: (1) provide a valid way to estimate per-protocol effects and (2) make the computational procedure as simple as possible to apply link.springer.com/article/10.1...link.springer.comComputing assumption-lean bounds for per-protocol effects - TrialsBackground A common approach used to estimate per-protocol effects, or the effect of perfect adherence to a defined protocol on a specified outcome, is to artificially censor individuals when they dev... 2185
Michael Schomaker @mfschomaker.bsky.social · 27/07/2026My PhD student Han Bao, who is going to graduate soon, is looking for a job (academia/industry), either immediately or later this year. He is an expert on longitudinal causal inference, both from a theoretical and practical perspective ("target trial emulation"). Please get in touch with me/him! 010
Reposted by Michael SchomakerAmerican Statistical Association History of Statistics @hos-asa.bsky.social · 22/07/20264/ Also most of you young'uns don't know about the Bad Old Days when we had to look up critical test statistics in printed tables. The tables were massive and for reasons of space were limited to 3 α levels: 0.05, 0.01, and 0.001 thresholds. 131
Reposted by Michael SchomakerAmerican Statistical Association History of Statistics @hos-asa.bsky.social · 21/07/2026Few statisticians know that Frank Yates, pioneer of experimental design, is responsible for the annoying practice of indicating 3 tiers of statistical significance by stars (*p ≤ 0.05, **p ≤0.01, ***p ≤ 0.001). He soon regretted it and “vehemently opposed its unthinking use”. And here we are. 112954
Reposted by Michael SchomakerMarcus Low @marcuslowx.bsky.social · 17/07/2026 A brief history of the Thembisa HIV model, by Leigh Johnson. A great overview of one of the most impressive infectious disease models around papers.ssrn.com/sol3/papers.cfm?abs… 022
Reposted by Michael SchomakerGary Collins @gscollins.bsky.social · 17/07/2026NEW #opensaccess paper "Evidence of unreliable data and poor data provenance in clinical prediction model research and clinical practice" link.springer.com/article/10.1... #researchintegrity #dataprovenance #predictionmodels #predictiveAI 0207
Reposted by Michael SchomakerLMU München @lmu.de · 13/07/202610 Mio. € für die #Biophysik: Das Konsortium #ALIVE um LMU-Physiker Erwin Frey erforscht die physikalische „Zeitrichtung“ lebenden Gewebes fernab des Gleichgewichts, um Zellorganisation zu verstehen. 🔬⌛ #LMUMuenchenlmu.deDie Zeitrichtung in lebendem Gewebe entschlüsselnDas internationale Forschungskonsortium ALIVE unter Beteiligung von LMU-Physiker Erwin Frey hat eine Förderung von 10 Millionen Euro eingeworben. 061
Reposted by Michael SchomakerRobin Ryder @robinryder.bsky.social · 08/07/2026I have just resigned from the board of "Statistics and Computing", along with 17 other Associate Editors. This was a difficult decision: this great journal has published many tremendous articles under the leadership of EiC Ajay Jasra, and before him David Hand, Gilles Celeux, and Mark Girolami. 713453
Reposted by Michael SchomakerTim Morris @timpmorris.bsky.social · 06/07/2026This is a lot of people’s bugbear isn’t it 1174
Reposted by Michael SchomakerDirk Eddelbuettel @eddelbuettel.com · 21/06/2026BBC article about Brian Ripley of the #RStats Core team given this week's excellent news concerning 2026 Rousseeuw Price for Statistics recognition for him and the core team. www.bbc.com/news/article...bbc.comProf Brian Ripley on developing R to manage the world's dataProf Brian Ripley has spent the past three decades working on a computer software that analyses data. 419383
Reposted by Michael SchomakerThe R Foundation @r-foundation.bsky.social · 17/06/2026The 2026 Rousseeuw Prize for Statistics has been awarded to the R Project. #RStats www.rousseeuwprize.org/2026rousseeuwprize.orgThe Rousseeuw Prize for StatisticsThe Rousseeuw Prize for Statistics is a biennial prize to celebrate outstanding contributions to statistics research. 2280106
Reposted by Michael SchomakerThe R Foundation @r-foundation.bsky.social · 17/06/2026The 2026 laureates are Brian Ripley, Martin Maechler, Kurt Hornik, Peter Dalgaard, and Luke Tierney who have made the longest sustained contribution to #RStats. Half of the $1m prize money is awarded to the laureates and half to the rest of the Core Team. 14112
Reposted by Michael SchomakerJeremy Labrecque @jeremylabrecque.bsky.social · 12/06/2026Interested in doing a PhD with me in epidemiology on causal inference and triangulation? In beautiful Rotterdam no less. www.werkenbijerasmusmc.nl/en/vacancy/1... Pro tip: if you get to the interview stage, there WILL be a question about ice hockeywerkenbijerasmusmc.nlVacature: PhD student in epidemiology to develop and apply causal triangulationMany key questions in epidemiology are fundamentally causal. Yet, we often have to rely on assumptions that cannot be directly verified to judge whether an observed association truly reflects causalit... 22724
Reposted by Michael SchomakerValentin Amrhein @vamrhein.bsky.social · 07/06/2026"a ‚significant' p-value between 0.01 and 0.05 should be interpreted with the expectation that the effect is exaggerated by more than 50% (median 1.56) and that an exact replication has about a one-in-three chance of also being significant." evidenceinthewild.com/p-value-look...evidenceinthewild.comThe P-Value Got a Lecture. It Needed a Lookup Table.Ten years after the ASA told us to stop misusing p-values, we're still arguing about thresholds. Erik van Zwet and colleagues did something different: they asked 23,000 clinical trials what a p-value ... 1157
Reposted by Michael SchomakerDavid Rügamer @davidruegamer.bsky.social · 02/06/2026We just published a blog post on AI-generated papers in the Position Paper Track. The core issue is not whether AI can be useful, but who bears the cost of verifying AI-generated text in peer review. We have desk-rejected around 30% of submissions, with roughly 60% of these w/o an appeal option. 173
Reposted by Michael SchomakerTim Morris @timpmorris.bsky.social · 02/06/2026The program is up for the first 1st Interdisciplinary Symposium on Meta Science for Methods Research and it promises to be a BANGER! crsuzh.pages.uzh.ch/msmr/program/crsuzh.pages.uzh.chindex – MSMR 2026 2136
Michael Schomaker @mfschomaker.bsky.social · 31/05/2026This is a great article which helped me a lot in preparing teaching materials for case control studies 👇 030
Reposted by Michael SchomakerJeremy Labrecque @jeremylabrecque.bsky.social · 30/05/2026It puzzled me for a long time that people acted like estimates from cc studies can simultaneously have two interpretations, eg an RR and a cc OR. So I wrote this: pubmed.ncbi.nlm.nih.gov/32889542/pubmed.ncbi.nlm.nih.govDo Case-Control Studies Always Estimate Odds Ratios? - PubMedCase-control studies are an important part of the epidemiologic literature, yet confusion remains about how to interpret estimates from different case-control study designs. We demonstrate that not al... 151
Michael Schomaker @mfschomaker.bsky.social · 28/05/20267/ For sure, some of the algos may still struggle with very specific situations. You are welcome to point them out, in case you find such cases. 000
Michael Schomaker @mfschomaker.bsky.social · 28/05/20266/ How to use it? Simply load the package and use sth. like "SL.glmnet_boost" instead of "SL.glmnet", that's it. Or run this test file for illustration, which is self-explaining: github.com/MichaelSchom...github.comSLbooster/test_SLboost.R at master · MichaelSchomaker/SLboosterContribute to MichaelSchomaker/SLbooster development by creating an account on GitHub. 100
Michael Schomaker @mfschomaker.bsky.social · 28/05/20265/ ...we added some screening algorithms that are stable (LASSO with escape strategies in case of failure, very simple Cramer's V based screening for challenging settings), or allow to screen exactly "x amount of variables".... 100
Michael Schomaker @mfschomaker.bsky.social · 28/05/20264/ We have essentially taken learners from "SuperLearner" and modified them for our analyses, in terms of printed output, stability, escape strategies when failures occur, handling of categorical variables - and added new learners as well. Additionally... 100
Michael Schomaker @mfschomaker.bsky.social · 28/05/20263/ ... troubleshooting may be difficult, internal re-coding in ltmle etc. may be problematic for some learners, there are no escape strategies for unusual errors, output messages are missing, variable selection / screening is limited and so on. 100
Michael Schomaker @mfschomaker.bsky.social · 28/05/20262/ Using "SuperLearner" (or sl3) as part of prediction tasks, for example as intermediate step for causal doubly robust effect estimation can practially often fail: in longitudinal settings data may get sparse, cross validation with categorical (factor) variables may cause problems, .... 100
Michael Schomaker @mfschomaker.bsky.social · 28/05/20261/ I have never really advertised our little Github-R-package "SLbooster": Additional and Modified Learning and Screening functions for Super Learning: github.com/MichaelSchom... What does it do? 👇github.comGitHub - MichaelSchomaker/SLboosterContribute to MichaelSchomaker/SLbooster development by creating an account on GitHub. 194
Reposted by Michael SchomakerValentin Amrhein @vamrhein.bsky.social · 22/05/2026Ich suche eine neue KollegIn als Co-RedaktorIn der Fachzeitschrift "Ornithologischer Beobachter". Es handelt sich um eine unbefristete 40%-Stelle an der Schweizerischen Vogelwarte Sempach. Bitte bewerben oder weiterleiten! www.ala-schweiz.chala-schweiz.chHome – Ala - Schweizerische Gesellschaft für Vogelkunde und VogelschutzAla Schweizerische Gesellschaft für Vogelkunde und Vogelschutz, Ornithologischer Beobachter 024
Reposted by Michael SchomakerTim Morris @timpmorris.bsky.social · 21/05/2026New post: Covariate adjustment and prediction-unbiasedness. Where I embarrass myself by asking smart people a dumb question (so you don’t have to) and get a useful answer. open.substack.com/pub/tpmorris...open.substack.comCovariate adjustment and prediction-unbiasednessThis is about covariate adjustment in RCTs (for a marginal estimand). 042
Reposted by Michael SchomakerAshley Naimi @ashleynaimi.bsky.social · 21/05/2026I would love to see more applied researchers attending and presenting at ACIC. So many interesting problems at the applied-theoretical interface. If you are an applied researcher with interests in causal inference, consider submitting a symposium proposal for the Pittsburgh conference! 051
Reposted by Michael SchomakerMarco Tosi @marco16.bsky.social · 15/05/2026JOB OFFER!! 🎉 🎉 I am looking for a postdoctoral researcher to join my team in the FIS3 KINMATTER Project on kin relationships 💑 👩👩👦 , health outcomes 🚑 , and inequalities. PhD required or close to completion in quantitative social sciences or (social)statistics. www.stat.unipd.it/procedura-se... 165
Reposted by Michael SchomakerSpotlight @spotlightnsp.bsky.social · 15/05/2026SA's LATEST HIV NUMBERS ARE IN | 7.9 million people are living with HIV. Treatment coverage has crept up by just 40 000. And 53 000 HIV-related deaths were recorded. What does it all mean? Find out in our newsletter: tinyurl.com/3a7w5kya You can join our mailing list: tinyurl.com/82jdsfjy 025