alex hayes
@alexpghayes.com
postdoc @ stanford econ + incoming assistant prof @ oregon state statistics. networks, causal inference, contagion, measurement error, #rstats. he/him
https://www.alexpghayes.com
https://www.alexpghayes.com
Keith and I strengthened our lower bounds for randomized experiments in the linear-in-means model to a general minimax result
Updated results available at arxiv.org/abs/2410.10772
Updated results available at arxiv.org/abs/2410.10772
November 25, 2025 at 9:55 PM
Keith and I strengthened our lower bounds for randomized experiments in the linear-in-means model to a general minimax result
Updated results available at arxiv.org/abs/2410.10772
Updated results available at arxiv.org/abs/2410.10772
Reposted by alex hayes
A new release of the mgcv #RStats 📦 is out on CRAN and Simon Wood (U Edinburgh) has added some significant new features despite the small bump in version number:
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
November 12, 2025 at 11:28 AM
A new release of the mgcv #RStats 📦 is out on CRAN and Simon Wood (U Edinburgh) has added some significant new features despite the small bump in version number:
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
What are your favorite books/articles/resources about graphic design for academic posters and presentations?
November 4, 2025 at 1:44 AM
What are your favorite books/articles/resources about graphic design for academic posters and presentations?
Reposted by alex hayes
Now I'm also looking for a research software engineer to implement a pile of research results to R packages loo, posterior, bayesplot, projpred, priorsense, brms or/and Python packages ArviZ, Bambi and Kulprit. Apply by email with no specific deadline (see contact info at users.aalto.fi/~ave/)
I'm now also looking for a postdoc with strong Bayesian background and interest in developing Bayesian cross-validation theory, methods and software. Apply by email with no specific deadline (see contact information at users.aalto.fi/~ave/).
Others, please share
Others, please share
I'm looking for a doctoral student with Bayesian background to work on Bayesian workflow and cross-validation (see my publication list users.aalto.fi/~ave/publica... for my recent work) at Aalto University.
Apply through the ELLIS PhD program (dl October 31) ellis.eu/news/ellis-p...
Apply through the ELLIS PhD program (dl October 31) ellis.eu/news/ellis-p...
November 3, 2025 at 11:13 AM
Now I'm also looking for a research software engineer to implement a pile of research results to R packages loo, posterior, bayesplot, projpred, priorsense, brms or/and Python packages ArviZ, Bambi and Kulprit. Apply by email with no specific deadline (see contact info at users.aalto.fi/~ave/)
this thread nicely describes the epistemology of a decent portion of modern meta-science, and i think also explains why it lost steam
Simonsohn has now posted a blog response to our recent paper about the poor statistical properties of the P curve. @clintin.bsky.social and I are finishing up a less-technical paper that will serve as a response. But I wanted to address a meta-issue *around* this that may clarify some things. 1/x
Would p-curve work if you dropped a piano on it?
datacolada.org/129
datacolada.org/129
October 24, 2025 at 5:29 AM
this thread nicely describes the epistemology of a decent portion of modern meta-science, and i think also explains why it lost steam
I missed that an expanded version of Philip Stark's "Pay No Attention to the Model Behind the Curtain" was published a few years back
Needless to say it's very good and worth a read
link.springer.com/10.1007/s000...
Needless to say it's very good and worth a read
link.springer.com/10.1007/s000...
October 18, 2025 at 5:25 PM
I missed that an expanded version of Philip Stark's "Pay No Attention to the Model Behind the Curtain" was published a few years back
Needless to say it's very good and worth a read
link.springer.com/10.1007/s000...
Needless to say it's very good and worth a read
link.springer.com/10.1007/s000...
Reposted by alex hayes
This may just be the best CS paper I’ve read this year. Just read the abstract and first para of the intro! The rest of the intro is really wild too, but very very good:
dl.acm.org/doi/pdf/10.1...
dl.acm.org/doi/pdf/10.1...
October 14, 2025 at 1:12 PM
This may just be the best CS paper I’ve read this year. Just read the abstract and first para of the intro! The rest of the intro is really wild too, but very very good:
dl.acm.org/doi/pdf/10.1...
dl.acm.org/doi/pdf/10.1...
Just read a referee report clearly generated by AI and I really hope journals start requiring Gen AI disclosures in referee reports
October 12, 2025 at 5:21 PM
Just read a referee report clearly generated by AI and I really hope journals start requiring Gen AI disclosures in referee reports
Reposted by alex hayes
I was loving Claude Code... until I tried it with #rstats. Constant errors, wouldn't use the tidyverse even when asked, "optimized" functions were slower.
Frustrated, I started a session just to teach R to Claude and summarize what it learned into a CLAUDE.md file gist.github.com/sj-io/3828d6...
Frustrated, I started a session just to teach R to Claude and summarize what it learned into a CLAUDE.md file gist.github.com/sj-io/3828d6...
Claude R Tidyverse Expert
Claude R Tidyverse Expert. GitHub Gist: instantly share code, notes, and snippets.
gist.github.com
August 21, 2025 at 10:18 AM
I was loving Claude Code... until I tried it with #rstats. Constant errors, wouldn't use the tidyverse even when asked, "optimized" functions were slower.
Frustrated, I started a session just to teach R to Claude and summarize what it learned into a CLAUDE.md file gist.github.com/sj-io/3828d6...
Frustrated, I started a session just to teach R to Claude and summarize what it learned into a CLAUDE.md file gist.github.com/sj-io/3828d6...
nice guide to making github profiles (especially academic ones) legible to others!
🧵 Skytorial 2 – Your profile on @github.com
1/ 🌟 The first thing on GitHub is your profile: your cover letter to the academic and scientific world.
This is how colleagues, collaborators, and potential reviewers of your projects find you.
Let's create it step by step 👇
1/ 🌟 The first thing on GitHub is your profile: your cover letter to the academic and scientific world.
This is how colleagues, collaborators, and potential reviewers of your projects find you.
Let's create it step by step 👇
August 31, 2025 at 3:47 PM
nice guide to making github profiles (especially academic ones) legible to others!
Reposted by alex hayes
Subhankar Bhadra, Michael Schweinberger
Causal Inference Under Network Interference
https://arxiv.org/abs/2508.06808
Causal Inference Under Network Interference
https://arxiv.org/abs/2508.06808
August 12, 2025 at 6:09 AM
Subhankar Bhadra, Michael Schweinberger
Causal Inference Under Network Interference
https://arxiv.org/abs/2508.06808
Causal Inference Under Network Interference
https://arxiv.org/abs/2508.06808
Reposted by alex hayes
Also, we think people should stop using forensic meta-analytic techniques that have not been adequately vetted by experts in statistics. The p curve papers have very little statistical detail, and were published in psych journals. They did not get scrutiny appropriate to their popularity. 15/?
August 8, 2025 at 6:56 PM
Also, we think people should stop using forensic meta-analytic techniques that have not been adequately vetted by experts in statistics. The p curve papers have very little statistical detail, and were published in psych journals. They did not get scrutiny appropriate to their popularity. 15/?
Reposted by alex hayes
This workshop is going to be great fun, and I really look forward to meeting everyone!
It would mean a lot to me if you signed up!
It would mean a lot to me if you signed up!
❗️Our next workshop will be on August 14, 6 pm CEST, on marginaleffects package by
@vincentab.bsky.social !
Register or sponsor a student by donating to support Ukraine!
Details: bit.ly/3wBeY4S
Please share! #AcademicSky #EconSky #RStats
@vincentab.bsky.social !
Register or sponsor a student by donating to support Ukraine!
Details: bit.ly/3wBeY4S
Please share! #AcademicSky #EconSky #RStats
August 2, 2025 at 12:58 PM
This workshop is going to be great fun, and I really look forward to meeting everyone!
It would mean a lot to me if you signed up!
It would mean a lot to me if you signed up!
Reposted by alex hayes
Technical writing is hard bcs "writing is thinking" but we often should tell our story not in the order we worked. Solution? I wrote a quick post on how @quarto.org 's embed shortcodes can reframe technical writing as reproducible evidence curation
www.emilyriederer.com/post/quarto-...
🧵 (1/n)
www.emilyriederer.com/post/quarto-...
🧵 (1/n)
How Quarto embed fixes data science storytelling | Emily Riederer
Literate programming excels at capturing our stream of conscience. Our stream of conscience does not excel at explaining the impact of our work. Notebooks enable some of data scientists’ worst tendenc...
www.emilyriederer.com
July 27, 2025 at 1:14 PM
Technical writing is hard bcs "writing is thinking" but we often should tell our story not in the order we worked. Solution? I wrote a quick post on how @quarto.org 's embed shortcodes can reframe technical writing as reproducible evidence curation
www.emilyriederer.com/post/quarto-...
🧵 (1/n)
www.emilyriederer.com/post/quarto-...
🧵 (1/n)
Do folks know about A/B testing datasets where information about guardrail metrics is released alongside outcomes? #rstats #datascience #kaggle
July 23, 2025 at 3:58 PM
Do folks know about A/B testing datasets where information about guardrail metrics is released alongside outcomes? #rstats #datascience #kaggle
boosting for the weekend crowd
~~ making sense of academic statistics ~~
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
July 19, 2025 at 2:01 PM
boosting for the weekend crowd
Any tips and tricks for @typst.app <-> LaTeX translations?
Pandoc is struggling with custom macros for notation and I'm weary of LLMs for technical writing (plus context window issues)
Pandoc is struggling with custom macros for notation and I'm weary of LLMs for technical writing (plus context window issues)
July 18, 2025 at 3:05 PM
Any tips and tricks for @typst.app <-> LaTeX translations?
Pandoc is struggling with custom macros for notation and I'm weary of LLMs for technical writing (plus context window issues)
Pandoc is struggling with custom macros for notation and I'm weary of LLMs for technical writing (plus context window issues)
~~ making sense of academic statistics ~~
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
July 15, 2025 at 8:15 PM
~~ making sense of academic statistics ~~
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
i wrote about the confusing relationship between statistics and data analysis, and also about how statistics relates to science
#statistics #rstats #datascience
www.alexpghayes.com/post/making-...
I've invested a lot into LaTeX in the last few years and didn't feel a strong desire to pivot, but I just tried @typst.app and I'm an immediate convert
The compilation speed is so nice and it's so much easier to understand
The compilation speed is so nice and it's so much easier to understand
July 11, 2025 at 3:52 PM
I've invested a lot into LaTeX in the last few years and didn't feel a strong desire to pivot, but I just tried @typst.app and I'm an immediate convert
The compilation speed is so nice and it's so much easier to understand
The compilation speed is so nice and it's so much easier to understand
The more I do multiverse data analysis, the more I find that conclusions vary dramatically with model specification. This makes me quite hesitant to trust empirical results using network models
June 21, 2025 at 3:54 PM
The more I do multiverse data analysis, the more I find that conclusions vary dramatically with model specification. This makes me quite hesitant to trust empirical results using network models
Reposted by alex hayes
Hamilton, Tawn, Firth (2023) "The many routes to the ubiquitous Bradley-Terry model": arxiv.org/abs/2312.13619 Very cool! I've considered writing notes on how BT models can be motivated in myriad ways, with diff motivations leading to diff generalizations. This looks like a fantastic crack at that.
The many routes to the ubiquitous Bradley-Terry model
The rating of items based on pairwise comparisons has been a topic of statistical investigation for many decades. Numerous approaches have been proposed. One of the best known is the Bradley-Terry mod...
arxiv.org
June 3, 2025 at 12:35 AM
Hamilton, Tawn, Firth (2023) "The many routes to the ubiquitous Bradley-Terry model": arxiv.org/abs/2312.13619 Very cool! I've considered writing notes on how BT models can be motivated in myriad ways, with diff motivations leading to diff generalizations. This looks like a fantastic crack at that.
I'm looking for methods to visualize signed graphs with ~100 nodes and lots of negative edges
So far the best I've come across is in {signnet} but I'm hoping I can find some other options github.com/schochastics...
So far the best I've come across is in {signnet} but I'm hoping I can find some other options github.com/schochastics...
Does this package include layout methods for signed networks? · Issue #21 · schochastics/signnet
Hey there! I have a signed network that I'm trying to visualize with ggraph, and I'm not sure what kind of layouts I should be using, or if relevant methods are implemented in this package. Got any...
github.com
April 19, 2025 at 3:08 PM
I'm looking for methods to visualize signed graphs with ~100 nodes and lots of negative edges
So far the best I've come across is in {signnet} but I'm hoping I can find some other options github.com/schochastics...
So far the best I've come across is in {signnet} but I'm hoping I can find some other options github.com/schochastics...