Topics on econometrics and causal inference

Preface

This is a working notebook rather than a textbook. The chapters are posts I have written over the years while reading, teaching, and consulting on applied econometrics — usually because a colleague or a student asked a question that did not have a tidy answer in the books I had on the shelf. Each one is meant to stand on its own. They are loosely organised under the headings in the sidebar, but the order in which they were written did not follow any plan, and the same topic sometimes reappears in different guises as my understanding shifted.

The unifying interest is causal inference with observational data, and the recurring question is the one Angrist and Pischke called what is being identified, by what variation, under what assumptions. The posts work through that question in different settings: interactions and marginal effects, fixed and correlated random effects, matching and balancing weights, modern difference-in-differences (TWFE, ETWFE, synthetic control, TASC, shift-share), count and rare-event models, doubly robust estimators (TMLE, AIPW, longitudinal modified treatment policies), mediation, and a handful of more specialised topics — proximal causal inference, partial interference, conjoint and list experiments, uplift modelling, policy trees.

Most examples are in R, with Stata appearing where a procedure is more naturally implemented there, and occasional Python or Julia where the package ecosystem makes it the better choice. Code is reproducible: source files are in the repository linked above, and the “Edit this page” link at the foot of each chapter goes straight to the corresponding .qmd. Two companion books — Introduction to Causal Econometrics (R) and Causal Econometrics with Julia — give the same material a more systematic treatment; this collection is the longer, messier counterpart, useful when you want to see how a specific method behaves on a specific kind of problem.