Tessera

Noah Greifer

@noahgreifer.bsky.social

Statistical consultant and programmer at Harvard IQSS. Author/maintainer of the #Rstats packages 'MatchIt', 'WeightIt', and 'cobalt' for causal inference, among many others | He/him ngreifer.github.io

524 Posts3918 Follower 201 Folgt

Noah Greifer @noahgreifer.bsky.social · 2d ago

I'm so happy to announce version 2.0.0 of my #Rstats package WeightIt is out on CRAN! New features: censoring weights, multilevel propensity scores, improved weights for continuous treatments, bias-reduced ordinal and multinomial models, M-estimation in subgroups Check out the website below!

Weighting for Covariate Balance in Observational Studies

Generates balancing weights for causal effect estimation in observational studies with binary, multi-category, or continuous point or longitudinal treatments by easing and extending the functionality ...

ngreifer.github.io

Noah Greifer @noahgreifer.bsky.social · 2d ago

Exciting new updates to #Rstats WeightIt coming soon... 👀 Any guesses? Here are two clues in emoji form: 1. 💀 2. 🏫 (Read separately! no death in schools please)

Noah Greifer @noahgreifer.bsky.social · 2d ago

Fascinating and clear paper by @corymccartan.com and @melodyyhuang.bsky.social, greatly enhancing our understanding of how Bayesian Additive Regression Trees (BART) works and why it is so effective. A must-read for my fellow BART enthusiasts. #statssky #causalinference

ArXiv Paperboy (Stat.ME+Econ.EM)@paperposterbot.bsky.social · 3d ago

arXiv📈🤖 Seeing the Forest for the Trees: The Gaussian Process Limit of BART By McCartan, Huang

Bayesian Additive Regression Trees (BART) have shown state-of-the-art performance in both prediction and causal inference problems. Previous theoretical work has attempted to explain BART's superior performance by establishing posterior contraction rates for standard BART models, but these rates depend strongly on the number of covariates. Here, we take a different approach and study the behavior of BART as the number of trees grows towards infinity. We show that in this regime, BART converges to a Gaussian process (GP) with a particular kernel. The kernel and its corresponding reproducing kernel Hilbert space (RKHS) have favorable inferential properties that help explain BART's excellent performance. We introduce *random tree features* as an approximation to this limiting GP, and establish minimax-optimal learning rates for ridge regression on these random features that depend only logarithmically on dimension. In addition to providing insight into the empirical success of BART, random tree features offer a computational benefit over traditional MCMC estimation. The random-features approximation also allows practitioners to easily incorporate BART into any model which has a linear predictor, expanding the applicability and flexibility of BART.

Noah Greifer @noahgreifer.bsky.social · 3w ago

nursingclio.org/2026/07/15/s...

Seductions of the Transparent Body: X-Rays, A.I. Body Scans, and Cancer

There is no escaping cancer in the algorithm. In the months after finishing chemotherapy, targeted ads for A.I.-powered body scans filled my social media feed with stories about lurking malignancie…

nursingclio.org

Noah Greifer @noahgreifer.bsky.social · last mo.

This made me very happy to see :) www.nytimes.com/interactive/...

Noah Greifer @noahgreifer.bsky.social · 2mo ago

New version of #Rstats {fwb} is out! {fwb} implements the fractional weighted bootstrap, aka the Bayesian bootstrap, which is an alternative to the traditional bootstrap that draws a set of weights for each bootstrap replication instead of sampling with replacement from the original sample.

Fractional Weighted Bootstrap

An implementation of the fractional weighted bootstrap to be used as a drop-in for functions in the boot package. The fractional weighted bootstrap (also known as the Bayesian bootstrap) involves draw...

ngreifer.github.io

Noah Greifer @noahgreifer.bsky.social · 3mo ago

This is the clearest and most accessible introduction to DML I've ever read: arxiv.org/abs/2504.08324 Congrats to the authors @aahrens.bsky.social, @markeschaffer.bsky.social, et al on this amazing paper and great accompanying R package! I'm now DML-pilled.

An Introduction to Double/Debiased Machine Learning

This paper provides an introduction to Double/Debiased Machine Learning (DML). DML is a general approach to performing inference about a target parameter in the presence of nuisance functions: objects...

arxiv.org

Noah Greifer @noahgreifer.bsky.social · 4mo ago

This is a must-read by two of my research idols!

Julia M. Rohrer@dingdingpeng.the100.ci · 4mo ago

Good news everyone 🥳 Our (w @vincentab.bsky.social) primer on models as prediction machines (with the marginaleffects package) is finally officially published!> journals.sagepub.com/doi/10.1177/...

Noah Greifer @noahgreifer.bsky.social · 4mo ago

arg! I wish R packages had better error messages! Now they can, thanks to my newest #Rstats package, {arg}! 😉 {arg} produces clean, simple, error messages for checking function arguments, similar to {checkmate}, {dreamerr}, and {chk}, using {cli} formatting.

Clean and Simple Argument Checking

Checks function arguments, ideally for use in R packages. Uses a simple interface and produces clean, informative error messages using cli.

ngreifer.github.io

Noah Greifer @noahgreifer.bsky.social · 4mo ago

I'm teaching this 3-day seminar on matching and weighting in R next week! I'd love to see you there!

Statistical Horizons@stathorizons.bsky.social · 4mo ago

Join "Causal Inference in R Using MatchIt and WeightIt" with @noahgreifer.bsky.social on April 15-17. Gain hands-on #causalinference experience in #Rstats and learn matching and weighting methods for estimating and interpreting treatment effects.

Michael Wiebe @michaelwiebe.bsky.social · 5mo ago

🚨Replication alert🚨 I'm pleased to announce that my replication of Moretti (2021) is now accepted as a comment at AER. I find ten issues in the paper. My comment focuses on two major problems; in the appendix, I document eight (relatively) minor problems. 1/

Noah Greifer @noahgreifer.bsky.social · 5mo ago

But what if... I were to purchase propensity scores and disguise them as my own randomized trial? Delightfully devilish Seymour!

a cartoon character is looking out a window at krusty krabbs

ALT: a cartoon character is looking out a window at krusty krabbs

media.tenor.com

Noah Greifer @noahgreifer.bsky.social · 6mo ago

Some more details on the omnibus test for whether the ADRF is flat, as I mention in this test. We have an estimate for the ADRF at each treatment value `a`, and jointly they have a multivariate normal distribution. This makes the ADRF estimate a Gaussian Process. 1/8

Noah Greifer@noahgreifer.bsky.social · 6mo ago

I developed a new test for whether the ADRF is flat. If H0 is rejected, we can claim there is an effect of the treatment on the outcome. This test can be used with any model because it doesn't test any parameters in the model; it tests the difference between the ADRF itself and a flat line: 6/10

Omnibus test for whether the ADRF is flat.

Noah Greifer @noahgreifer.bsky.social · 6mo ago

I'm so excited to announce the first release of my newest #Rstats package, {adrftools}! This package facilitates estimation, visualization, and testing for the causal effect of a continuous (i.e., non-discrete) treatment. 🧵 1/10 #statssky #episky #causalinference

adrftools: Estimating, Visualizing, and Testing Average Dose-Response Functions

Facilitates estimating, visualizing, and testing average dose-response functions (ADRFs) for characterizing the causal effect of a continuous (i.e., non-discrete) treatment or exposure. Includes suppo...

cran.r-project.org

Noah Greifer @noahgreifer.bsky.social · 7mo ago

Bringing this back now that @marcratkovic.bsky.social is on Bluesky!

Noah Greifer@noahgreifer.bsky.social · last yr.

A nice paper by Mark Ratkovic on double machine learning (DML) oriented toward political scientists, with some advancements to accommodate interference and clustering. Definitely a worthwhile read, especially if the foundational papers on this topic intimidate you (as they do me).

Noah Greifer @noahgreifer.bsky.social · 8mo ago

the oily macaroni constant

Andrew Heiss @andrew.heiss.phd · 8mo ago

Some closing thoughts for my students this semester on LLMs and learning #rstats datavizf25.classes.andrewheiss.com/news/2025-12...

Will you incorporate LLMs and AI prompting into the course in the future?
No.

Why won’t you incorporate LLMs and AI prompting into the course?
These tools are useful for coding (see this for my personal take on this).

However, they’re only useful if you know what you’re doing first. If you skip the learning-the-process-of-writing-code step and just copy/paste output from ChatGPT, you will not learn. You cannot learn. You cannot improve. You will not understand the code.

In that post, it warns that you cannot use it as a beginner:

…to use Databot effectively and safely, you still need the skills of a data scientist: background and domain knowledge, data analysis expertise, and coding ability.

There is no LLM-based shortcut to those skills. You cannot LLM your way into domain knowledge, data analysis expertise, or coding ability.

The only way to gain domain knowledge, data analysis expertise, and coding ability is to struggle. To get errors. To google those errors. To look over the documentation. To copy/paste your own code and adapt it for different purposes. To explore messy datasets. To struggle to clean those datasets. To spend an hour looking for a missing comma.

This isn’t a form of programming hazing, like “I had to walk to school uphill both ways in the snow and now you must too.” It’s the actual process of learning and growing and developing and improving. You’ve gotta struggle.

This Tumblr post puts it well (it’s about art specifically, but it applies to coding and data analysis too):

Contrary to popular belief the biggest beginner’s roadblock to art isn’t even technical skill it’s frustration tolerance, especially in the age of social media. It hurts and the frustration is endless but you must build the frustration tolerance equivalent to a roach’s capacity to survive a nuclear explosion. That’s how you build on the technical skill. Throw that “won’t even start because I’m afraid it won’t be perfect” shit out the window. Just do it. Just start. Good luck. (The original post has disappeared, but here’s a reblog.)

It’s hard, but struggling is the only way to learn anything.

You might not enjoy code as much as Williams does (or I do), but there’s still value in maintaining codings skills as you improve and learn more. You don’t want your skills to atrophy.

As I discuss here, when I do use LLMs for coding-related tasks, I purposely throw as much friction into the process as possible:

To avoid falling into over-reliance on LLM-assisted code help, I add as much friction into my workflow as possible. I only use GitHub Copilot and Claude in the browser, not through the chat sidebar in Positron or Visual Studio Code. I treat the code it generates like random answers from StackOverflow or blog posts and generally rewrite it completely. I disable the inline LLM-based auto complete in text editors. For routine tasks like generating {roxygen2} documentation scaffolding for functions, I use the {chores} package, which requires a bunch of pointing and clicking to use.

Even though I use Positron, I purposely do not use either Positron Assistant or Databot. I have them disabled.

So in the end, for pedagogical reasons, I don’t foresee me incorporating LLMs into this class. I’m pedagogically opposed to it. I’m facing all sorts of external pressure to do it, but I’m resisting.

You’ve got to learn first.

Noah Greifer @noahgreifer.bsky.social · 9mo ago

Any #rstats advice for writing mathematical expressions in ggplot2 axis labels? Dying not to have to use the insanity that is bquote()

Noah Greifer @noahgreifer.bsky.social · 9mo ago

What do you mean my Bayesian logistic regression on a moderate sample took 3 minutes to run

Dan Lewer @danlewer.bsky.social · 9mo ago

We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?

A "methods primer" article in the journal "BMJ Medicine", titled "Factors associated with: problems of using exploratory multivariable regression to identify causal risk factors"

Pausal Zivference @pausalz.bsky.social · 10mo ago

For years I had trouble following some of the discussion about confidence bands, but at ACIC this year @noahgreifer.bsky.social pointed me to a helpful paper So you don't have to be as perplexed as I once was, we have a new pre-print introducing the key ideas arxiv.org/abs/2510.07076

Confidence Regions for Multiple Outcomes, Effect Modifiers, and Other Multiple Comparisons

In epidemiology, some have argued that multiple comparison corrections are not necessary as there is rarely interest in the universal null hypothesis. From a parameter estimation perspective, epidemio...

arxiv.org

Noah Greifer @noahgreifer.bsky.social · 10mo ago

My hot take is that "fixed effects" has a single, clear meaning that is equivalent across all subdisciplines of statistics.

Noah Greifer @noahgreifer.bsky.social · 11mo ago

A new paper I worked on is out in Justice Quarterly! I won't speak on the substantive nature of the paper as I worked solely as the methodologist, but I developed a new matching method not otherwise described in the literature, and I want to tell you about it! #statssky #casualsky

The Effects of a Place-Based Intervention on Resident Reporting of Crime and Service Needs: A Frontier Matching Approach

Prior research has found that reporting of crime incidents and service needs remain low in many U.S. cities. This study employs a matching strategy using observational data from a large public repo...

doi.org

Low Carpe Diet @lowcarpdiet.bsky.social · last yr.

opossum my possum

Noah Greifer @noahgreifer.bsky.social · 11mo ago

I recently updated my #Rstats package {optweight} for the first time in 6 years(!), and I want to give it the attention it deserves with an announcement and mini thread. In short, {optweight} uses optimization to estimate balancing weights in observational studies. #episky #statssky #causalsky 1/

Optimization-Based Stable Balancing Weights

Use optimization to estimate weights that balance covariates for binary, multi-category, continuous, and multivariate treatments in the spirit of Zubizarreta (2015) <doi:10.1080/01621459.2015.1023805>...

ngreifer.github.io

Cameron Patrick @cameronpat.bsky.social · 11mo ago

I could have sworn I created this before on our Previous Parish, but couldn't find it so made it fresh. I present: OUR BLESSED mixed models // THEIR BARBAROUS fixed effects

OUR BLESSED mixed models vs THEIR BARABAROUS fixed effects
OUR GLORIOUS Mundlak device vs THEIR WICKED demeaning
OUR GREAT variance components vs THEIR PRIMITIVE dummy variables
OUR NOBLE partial pooling vs THEIR BACKWARD unbiased estimates
OUR HEROIC maximum likelihoos vs THEIR BRUTISH least squares

Low Carpe Diet @lowcarpdiet.bsky.social · 12mo ago

cowboy depop

Noah Greifer @noahgreifer.bsky.social · last yr.

I'm teaching this workshop in two weeks! It's going to be great!

Statistical Horizons@stathorizons.bsky.social · last yr.

Looking to strengthen your #causalinference skills? Join @noahgreifer.bsky.social on Aug. 12-15 for "Causal Inference in R Using MatchIt and WeightIt" to gain the skills to apply these #Rstats packages to estimate and interpret treatment effects.

Noah Greifer @noahgreifer.bsky.social · last yr.

These course notes on nonparametric regression (including kernel density estimation) by Eduardo García Portugués are *fantastic*. So clear, with great visuals and clear code.

Chapter 6 Nonparametric regression | Notes for Predictive Modeling

<p>Notes for Predictive Modeling. MSc in Big Data Analytics. Carlos III University of Madrid.</p>

bookdown.org

Statistical Horizons @stathorizons.bsky.social · last yr.

Causal Inference in R | Online Workshop | Statistical Horizons

This online seminar taught by Noah Greifer, Ph.D., will introduce using the MatchIt and WeightIt packages in R for causal inference.

statisticalhorizons.com