Online Books

Quarto books on econometrics, causal inference, and applied research methods.

Four online books, written and revised as I work through methods. The two systematic causal books cover the same material in parallel — pick the language you actually use. The classical guide is foundations, and the notes book is the messier working companion.

Foundations

Econometrics Guide R + Stata

A study guide to the workhorse estimators of applied econometrics — OLS, MLE, GLS, IV, GMM, and models for censored, discrete, count, panel, and survival data. 14 chapters, side-by-side R and Stata code. Best read before the causal volumes.

Systematic treatment of causal inference

Introduction to Causal Econometrics with Observational Data R

A working guide to modern causal inference in R, organized in the order an applied project actually runs: identification, estimation, designs (DiD, IV, RDD, shift-share), longitudinal causal inference, survival, mediation, and causal discovery. The causal-discovery chapter now pairs PC and GES algorithms with a real-data example on survey-weighted PISA 2022 data. 24 chapters.

Causal Econometrics with Julia Julia

The same ground in Julia, with several heavier estimators (TMLE on large samples, distributional DiD, Bayesian g-computation) where Julia is genuinely faster. Built alongside a stack of small Julia packages — CausalEstimate.jl, CausalGraphs.jl, Lavaan.jl, Crumble.jl, TASC.jl, and more — whose source is short enough to read. The causal-discovery chapter applies PC and RSL-D to survey-weighted PISA 2022. 27 chapters. Cross-linked with the R book.

Working notebook companion

Topics on Econometrics and Causal Inference R

A working notebook rather than a textbook: 48 chapters of posts written while reading, teaching, and consulting on applied econometrics. Each one stands alone. The same topic sometimes appears more than once as my thinking evolved. Useful when you want to see how a specific method behaves on a specific problem, rather than the systematic treatment.