It was great to chair a panel on Veridical Data Science (vdsbook.com/) in Education at #JSM2025 with @rlbarter, @bbiinnyyuu, Andrew Bray, @jrosenberg6432, and @RuobinGong! Consider integrating VDS in your next course! The book contains examples, code, + many exercises.
3
200
Matteo Bonvini retweeted
Interested in #Bayesian analysis of #RDD ? Check this out arxiv.org/abs/2211.09099
Just accepted on the AOAS with Laura Forastiere and Alessandra Mattei!
Matteo Bonvini retweeted
Come work with us at CMU! We're hiring tenure-track asst profs in the Dept of Statistics & Data Science
cmu.edu/dietrich/statistics-…
Matteo Bonvini retweeted
I'm very proud of @AnnaGuo617 and excited to share our new manuscript on flexible #causal effect estimation in a broad class of DAGs with unmeasured confounders. #CausalTwitter
arxiv.org/pdf/2409.03962
Matteo Bonvini retweeted
Interested in data-driven covariate adjustment? I’m presenting some recent work with @ildiazm and @SVansteelandt next week!
Our next journal club is scheduled on Sep 13 at 11am EST.
Speaker: Kelly Van Lancker, Ghent University
Zoom link: umich.zoom.us/j/7573650566
Title: Automated, efficient and model-free inference for randomized clinical trials via data-driven covariate adjustment
Matteo Bonvini retweeted
there are surprisingly many open problems when it comes to theory/methods in causal inference
check out this talk by Siva Balakrishnan for an excellent & comprehensive summary of the state of the art
youtube.com/live/Mnum0Ox1f_o…
stat.cmu.edu/~siva/
Matteo Bonvini retweeted
New paper and software alert!
arxiv.org/abs/2408.14620
Interested in modern mediation analysis methods with machine learning and multivariate mediators?
Take a look at this joint work with Richard Liu, @nickWillyamz , and @kara_rudolph
Short 🧵...
Matteo Bonvini retweeted
Check out our new draft on #fair risk minimization under #causal constraints, w @biosbenk. #CausalTwitter #fairML
It provides closed-form solutions, explores risk-fairness trade-offs, offers insight into mechanisms of optimal fair prediction, & more.
➡️arxiv.org/pdf/2408.01630
Matteo Bonvini retweeted
📷
The Division of Biostatistics @UofUMedicine is building something special. Here we are at #JSM2024. We're recruiting faculty, post-docs and students. Come join us! #BiostatsElevated
@UofUBiostats
@UofUPHS
@AmstatNews
Matteo Bonvini retweeted
This is how I started my journey in #RL 5 years ago. How I started my PhD.
I put all my heart into this work and at times I hated it (especially after 4 long years w 2revisions in StatSci!).
Finally out in ISR!
This was my lesson in surviving research.
onlinelibrary.wiley.com/doi/…
Matteo Bonvini retweeted
arXiv -> alphaXiv
Students at Stanford have built alphaXiv, an open discussion forum for arXiv papers. @askalphaxiv
You can post questions and comments directly on top of any arXiv paper by changing arXiv to alphaXiv in any URL!
Matteo Bonvini retweeted
The Division of Biostatistics @UofUMedicine is recruiting faculty, postdocs & PhD students at #JSM2024 this weekend. Visit our booth or DM me to connect! #BiostatsElevated
@UofUBiostats @UofUPHS @AmstatNews
Matteo Bonvini retweeted
Very excited about this new paper by Tiger Zeng (tigerzhzeng.com/)
We study causal inference w/ high-dimensional discrete confounders
We give new bias/variance results & minimax lower bounds, which characterize fundamental limits of causal inference in high dimensions
Matteo Bonvini retweeted
this looks awesome
arxiv.org/pdf/2407.18163
Matteo Bonvini retweeted
Really excited about this paper, w/ amazing postdoc Alex Levis
awlevis.com/about/
We propose conditional potential benefit (CPB) measure, ie the improvement under optimal trt vs status quo
We describe id assumptions & propose nonparametric, robust, & efficient estimators
Matteo Bonvini retweeted
I have several exciting openings for PhD students and postdocs in the context of my advanced ERC grant #ERCAdG on Assumption-lean (Causal) Modeling and Estimation. Please spread the news! users.ugent.be/~svsteela/
@DassGhent
@UGent_fwe
@ResearchUGent
@UGent
@ERC_Research
Matteo Bonvini retweeted
I had a great time presenting on Efficient Plug-in (EP) Learning of Hetergeneous Treatment Effects at #ACIC
It turns out that the plug-in principle guiding #TMLE is especially beneficial for estimating causal functions like the CATE using orthogonal ML
arxiv.org/pdf/2402.01972
Matteo Bonvini retweeted
How and why does the highly adaptive lasso break the "curse of dimensionality"?!
1/🧵
Matteo Bonvini retweeted
I am happy to announce I have been elected to the Society for Causal Inference (sci-info.org) Board as the President-Elect!
Hope to contribute to a bright future for #causalinference
Matteo Bonvini retweeted
Exploring fairness in AI 🤖? How do we ensure statistical/ML models adhere to fairness principles?
Excited to share latest work w @nshejazi,@mark_vdlaan & @biosbenk on developing methods to tackle this question! #mlTwitter #statsTwitter #causalTwitter
➡️arxiv.org/abs/2404.09847































