Same! Looking forward to meeting you, Jan, and Mona, and to seeing Issa Dahobrah!

An excellent story that shines a bright light on the devastation in my field.

‘Back to the Dark Ages’: Education Research Staggered by Trump Cuts With contracts severed and grants rescinded, experts say Washington’s hit to K–12 research will set back the field for years. @the74.bsky.social www.the74million.org/article/back...

This is a great article about what's happening in education research right now. (As my quotes show - I'm really rather annoyed and angry these days...) www.the74million.org/article/back...

Ever since the former commissioner of the National Center for Education Statistics was dismissed by the Trump administration in February, I wanted to hear her story. Peggy Carr was among a string of Black senior officials fired in early 2025. (1/3)

"Federal statistics, one of the United States’ premier public goods, differ from privately provided data because they are privacy protected, aggregated to address relevant questions for decision-makers, constructed transparently, and widely available without a subscription"

Starting to look like I might not be able to work at Harvard anymore due to recent funding cuts. If you know of any open statistical consulting positions that support remote work or are NYC-based, please reach out! 😅

Education researchers sue Trump administration, testing executive power

Cuts to the Institute of Education Sciences threaten decades of progress in independent education research. We need more evidence—not less. Our case for strengthening IES: 🔗 www.brookings.edu/articles/how... With @statstipton.bsky.social & Jessaca Spybrook #EdResearch #IES #EduSky

Quick question for the hive mind - What are some prominent public policy decisions or big curricular changes that have resulted from IES-funded research or data?

“Everyone’s entitled to their own policy ideas, but no one’s entitled to their own facts. You have to share the truth in order to make any kind of improvement, no matter what direction you want to go.” #StatsSky hechingerreport.org/proof-points...

The Social Statistics Section (SSS) of the American Statistical Association (ASA) invites nominations for the Social Statistics Section Mid-Career Award.

Put another way, scientists need to find allies, not engage audiences.

"But opposition movements always seem hopeless until they’re not. Apartheid existed for decades and then came crashing down rapidly..." www.motherjones.com/politics/202...

I'm looking forward to this WiDS event tomorrow - if you're interested in hearing about my path into the field, the role of statistics in evidence, and so on - feel free to join. Sign up link here: www.virtu.com/wids-2025/

In this op-ed, we - the presidents of SREE and AEFP - joined forces to argue for the importance of evidence on "what works" and how cutting such funding is not "efficient" - it is wasteful. www.brookings.edu/articles/cut...

1/7. Public discourse about racial equity has changed a lot over the years. At @commhsp.bsky.social we’ve been monitoring those changes and their consequences. In a new 538 article, @efranklinfowler.bsky.social and I share what we’ve been seeing and why it matters. abcnews.go.com/538/national...

Many of us in academic science will default to “business as usual” as our response. We will feel that our power should be used to maintain a semblance of normalcy. To live to fight another day.

Musing I've gotten myself stuck in - what is the role of a statistician in a society / government that does not believe in empirical evidence? I'm feeling very lost here ... my whole career is focused on the evidence ecosphere.

Friends, #SREE folks, and more: If we helped organize in-person, community meetings in areas where there are many of you, would you be interested? And if so, would you want to help organize? I think we're all in need of community right now (myself included). Feel free to dm me instead.

Termination notices going out this afternoon to more than 300 employees of the National Cancer Institute. Access likely ends today. Four weeks paid leave and that’s it. Strong power move for Team Cancer.

Do you know a US-based researcher who wants to update their meta-analysis skills? #MATI2025 is accepting applications for our one-week training workshop in Chicago from July 28th – August 1st. Apply by March 2nd: www.meta-analysis-training-institute.com/application-...

CMU Stats & Data Science is hiring! www.cmu.edu/dietrich/sta... forms.stat.ufl.edu/statistics-j...

Bah and I should've mentioned AERA Open means the article is open access so anyone can read and I didn't have to pay for color so you get to see the wonderful figures I toiled over as I intended!

My fav starter packs so far, a thread: stats: go.bsky.app/Ki7PjpS stats: go.bsky.app/7TBN5rX causal inference: go.bsky.app/FdemGAZ package devs: go.bsky.app/N1569Qh data peeps: go.bsky.app/8TdEfdK medical stats: go.bsky.app/ArqEz36 bioinformatics: go.bsky.app/Ha64Gmv r-ladies: go.bsky.app/Vgxwa2F

This is a great thread and a question I've wondered about a lot. In MA, we see some studies report 10 ES and others only 1 or 2. Presumably those reporting 1 or 2 collected more and are choosing to report only these? But what is the general mechanism?

Unlikely things happen all the time but most are utterly unremarkable. What makes an observation interesting is not the low probability of observing it but a plausible alternative causal hypothesis. 🧪 #stats (Originally from Feynman but got to me in Aubrey Clayton's book Bernoulli's Fallacy.)

#StatsSky Something I keep mulling over: Statistics, as a field, started with a focus on social science / welfare (unfortunately, i.e., eugenics) but now has largely ejected social statistics from the "core" of the field. Instead, it is researched and taught within social science depts. Why?

Keep thinking about this. Why don't we have a similar "total experiment error" framework as a default setting for inference from social science experiments? Oftentimes we pretend all we need to account for is sampling error even though we know our measurements, treatments, etc. are full of error.

#StatsSky #EduSky I have been on a reading spree, deeply trying to understand the role of eugenics in the history of statistics. I just thought I'd share this paper which has helped me understand Fisher a bit. www.nature.com/articles/s41...

#StatsTwitter : My department is hiring! Assistant Professor of Instruction in Data Science opening at Northwestern https://statistics.northwestern.edu/about/faculty-search-.html

#StatsSky : My department is hiring! Assistant Professor of Instruction in Data Science opening at Northwestern statistics.northwestern.edu/about/facult...

Attn #StatsSky: We are seeking nominations for leadership in the Social Statistics Section of the ASA, including Chair Elect/ Chair, Program Chair Elect, and Treasurer/Secretary. If you are interested in learning more about these positions, dm me!

#jsm2024 Another reason to attend our Social Statistics Section meeting (Tuesday, 6pm-7pm in CC-C123): Come hear *David Banks*, our inaugural winner of the Social Statistics Section Distinguished Scholar Award, give remarks on "The Future of Social Statistics."

For those who program, where do you find info on best practices for creating an R package? Shiny app? I'm particularly interested in how to consider the user experience.

Are you attending #JSM2024 and interested in Social Statistics? Please join us at one of these great events! Our business meeting is on Tuesday 6-7pm - come, have a drink with us before the 8pm Presidential Address.

Does anyone have papers or chapters to recommend on equitable research practices in evaluations / RCTs? I'm struggling to find things written (I've been to workshops, seen webinars, talks) and I'd very much like to be able to read and cite this work. Thank you!

My (former) student @fitzgerald_kg and I wrote a paper outlining a framework for knowledge mobilization studies, with an example based on our work as statisticians. If you're interested, here's a link to a free copy (first 50 are free from publisher):...

Does anyone in #education research know any examples of intervention (causal) studies in which moderation / subgroup effects were a really important part of the findings? e.g., that it works under X but not Z conditions and contexts?

Generalizability, transportability, data exploitation, data fusion, and data integration. If you are interested in one or all of these, hold June 22-26, 2026(!) on your calendar for this very cool workshop. ...

Data science is often said to be the intersection of CS, Stats, and a Domain. If that's true - what part of Statistics is NOT data science? (I'm truly struggling with this).

What is the systems solution here? Yes, students in the social sciences need more statistics - but their departments don't have expertise or the courses. Sending them to the statistics department helps - but many of these classes assume stronger math backgrounds.

As a statistician, this is the highest of the honors - to be recognized by a field for contributing to their science. And in education, in particular, this means contributing to improving lives for children and to addressing longstanding societal inequities. I'm truly honored.

If you're interested in learning about immigration in the US, I found this article and graphics incredibly informative. www.cato.org/blog/why-leg...

If you are in the US and want to learn about meta-analysis, join us at the NSF-funded MMARI workshop! Learn more here: www.meta-analysis-research-institute.com

I'm giving a talk at the Online Causal Inference Seminar tomorrow at noon - see here if you're interested:https://sites.google.com/view/ocis/home The title is "Designing Randomized Trials to Predict Treatment Effects" and Andrew Gelman will be the discussant.

Blog post about the ugly resentment dynamics in academia that this week has been such a reminder of: statmodeling.stat.columbia.edu/2024/01/04/i...