about

I am a Postdoctoral Scholar at Stanford University in the Economics Department, where I work with Arun Chandrasekhar. I study spectral methods for network analysis, causal inference, and causal inference on networks. In September 2026, I will join Oregon State University as an Assistant Professor in Statistics.

I completed my PhD in Statistics at the University of Wisconsin-Madison, where I was co-advised by Keith Levin and Karl Rohe. During my PhD I also spent some time working on broom, a popular open-source R package in the tidyverse.

My curriculum vitae is available here. I also keep Google Scholar up to date, and you can find me on Bluesky at @alexpghayes.com.

recent updates

• 2026-04-16: vsp 0.1.4 is on CRAN. This update adds several heuristic localization metrics useful for investigating the quality of estimated embeddings.

• 2026-04-15: spectralard 0.0.0.9000 is on Github. This in-development package implements estimators for random dot product graphs from Aggregated Relational Data.

• 2026-04-11: I presented on Spectral Estimation and Trait Selection for Aggregated Relational Data at Network Science in Economics 2026.

• 2026-04-09: I have a new working paper Estimating peer effects in noisy, low-rank networks via network smoothing with Keith Levin.

• 2026-04-06: I presented Spectral Estimation and Trait Selection for Aggregated Relational Data at the Stanford Metrics Lunch.

• 2025-12-15: I presented Minimax rates for the linear-in-means model reveal an identifiability-estimability gap virtually at CMStatistics 2025.

• 2025-11-19: I presented my poster Estimating how much people influence their friends when friendship measurements are unreliable at the Stanford Causal Science Center student conference.

• 2025-11-14: I presented early work Mapping Social Networks on a Budget: Using Aggregated Relational Data in Development Economics at the UW-Madison Networks Seminar.

• 2025-11-04: I posted an updated draft Minimax rates for the linear-in-means model reveal an identifiability-estimability gap to ArXiV. This new draft generalizes our previous result loading bounding estimation error in ordinary least squares estimators for the linear-in-means model to a generic minimax lower bound that holds for all possible estimators.

• 2025-09-22: I presented Minimax rates for the linear-in-means model reveal an identifiability-estimability gap at the Stanford Metrics Lunch.

• 2025-09-01: I joined Stanford as a Postdoctoral Scholar working with Arun Chandrasekhar.

• 2025-08-07 I presented Peer effects in the linear-in-means model may be inestimable even when identified at the Joint Statistical Meetings 2025.

• 2025-05-09: I graduated from the University of Wisconsin-Madison with a PhD in Statistics.

Material from older talks, presentations, posters, etc, can be found on my Github.

working papers & pre-prints

1. Estimating peer effects in noisy, low-rank networks via network smoothing (pdf). Alex Hayes and Keith Levin. April 10, 2026

2. Minimax rates for the linear-in-means model reveal an identifiability-estimability gap. Alex Hayes and Keith Levin. arXiv. November 4, 2025. replication package

publications

1. Estimating network-mediated causal effects via principal components network regression. Alex Hayes, Mark M. Fredrickson, and Keith Levin. Journal of Machine Learning Research. 2025. replication package, code

2. Co-factor analysis of citation networks. Alex Hayes and Karl Rohe. Journal of Computational and Graphical Statistics. 2024. post-print, arXiv, replication package, code

3. Welcome to the tidyverse. Hadley Wickham, Mara Averick, Jennifer Bryan, Winston Chang, Lucy D’Agostino McGowan, Romain François, Garrett Grolemund, Alex Hayes, Lionel Henry, Jim Hester, Max Kuhn, Thomas Lin Pedersen, Evan Miller, Kirill Müller, David Robinson, Dana Paige Seidel, Vitalie Spinu, Kohske Takahashi, Davis Vaughan, Claus Wilke, Kara Woo, Hiroaki Yutani. Journal of Open Source Software. 2019. website

statistical consulting

At Stanford, I do some informal statistical consulting in the economics department, especially for grad students. Learn more.

blog

In a hobbyist capacity, I also blog about statistics, programming, and data. Some posts I enjoyed writing:

• overfitting: a guided tour
• consistency and the linear probability model
• fairness in repeated lotteries