Maria Cuellar

Hi bluesky! I was wondering whether you know of any papers that discuss how much easier it is to do a replication study with agentic AI (eg Codex/Claude Code). In the absence of code, it seems like that's a great way to test whether the models reported in a paper were the ones that were fit, etc.

I’m honored and humbled to give a plenary talk at ACIC this year with such an impressive group of speakers.

Thanks for the recommendation! I'm going to read this.

An important scholarship during these challenging times for government statistics!

As Trump Goes After Universities, Students Are Now on the Chopping Block Uncertainty about how much money colleges and universities stand to lose has led some schools to reduce the number of doctoral students, in some cases reneging on offers.

Trump’s cuts to university funding mean fewer spots, rescinded offers, and grad programs slashing positions.

Students are being stranded with no backup plan.
www.nytimes.com/2025/03/06/u...

Use this form to alert the ASA-George Mason University Project on the Health of the Principal Statistical Agencies about developments that may impair fed statistical programs’ capacity to produce relevant, objective, & accurate statistics for the public good amstat.jotform.com/250561574825...

Thanks, Chris!

Who said making a tenure portfolio couldn't be fun? (or, showing off my D3 and hyperlinks skillz).

web.sas.upenn.edu/mcuellar/vis...

I don't know much about this topic, but I love the graphic and the R package name.

I agree. The more people you have in the household, the more chances you have of getting colds. I basically think we're all sick from August to May.

Methodological problems in every black-box study of forensic firearm comparisons Abstract. Reviews conducted by the National Academy of Sciences (2009) and the President’s Council of Advisors on Science and Technology (2016) concluded t

We just published an exciting paper. Due to the statistical flaws in validity studies, we don't know the error rates in firearms casework, i.e. the discipline doesn't have a scientific basis. @amandaluby.bsky.social @srvanderplas.bsky.social @mrosenblum.bsky.social

academic.oup.com/lpr/article/...

Methodological problems in every black-box study of forensic firearm comparisons Abstract. Reviews conducted by the National Academy of Sciences (2009) and the President’s Council of Advisors on Science and Technology (2016) concluded t

Excited to share our hot-off-the-presses forensics paper
@amandaluby.bsky.social @mcuellar.bsky.social @srvanderplas.bsky.social

Registration for posit conference 2025 Now open. Atlanta, Sept 16-18

We are excited to announce posit::conf(2025)! Join fellow data enthusiasts & developers for an unforgettable three days of learning, connection, and inspiration.

Learn more and register at posit.co/blog/positco...

#datascience #rstats #pydata #quarto #tidyverse #posit

Thank you!

New preprint is up! arxiv.org/abs/2312.00032

Work with Heike Hofmann (one of the best statistical programmers out there) and Sheng Gao (an expert in clustering, now working in finance). Funded by CSAFE.

I loved @bwaber.bsky.social 's comment about the work, below:

The Harvard Data Science Initiative has launched its application for the 2024–2025 Postdoctoral Fellowship. Share with anyone who is a good fit; and have them reach out if their interest aligns with mine (e.g., causal inference, fairness, model validation, anomaly detection, GenAI, etc.).

📉📈
Some thoughts about my experiment using a data editor. First, he is awesome: careful and timely. A big round of applause to Adam Spencer.

We want well-documented code and data packets. We encourage authors to follow these guidelines social-science-data-editors.github.io/template_REA...

We are searching for an Associate or Full Professor of Computational Social Science (broadly defined) to join our department at LSE

If you'd like any more information, please feel free to reach out to me.

Polisky

Hi, I’m here in the blue space. What’s going on?