Resources

Books, courses, papers, and tools I actually use — not a wish list.

A curated collection of the material I go back to. Not an exhaustive list — just what has been genuinely useful for my work in causal inference, pricing, and forecasting.

If something on this page led you somewhere interesting, let me know.

Books

Causal Inference

  • Angrist & Pischke — Mostly Harmless Econometrics (2009). The classic. Read chapters 3 (regression) and 5 (DiD) at least twice.
  • Cunningham — Causal Inference: The Mixtape (2021). Free online: https://mixtape.scunning.com/. The most practitioner-friendly introduction to identification strategies.
  • Hernán & Robins — Causal Inference: What If (2020). Free online: https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/. The potential outcomes framework, done rigorously.
  • Pearl, Glymour & Jewell — Causal Inference in Statistics: A Primer (2016). The graphical / DAG side of causal inference.
  • Facure — Causal Inference for the Brave and True (2022). Free online: https://matheusfacure.github.io/python-causality-handbook/. Python-first, notebook-style walkthroughs.

Pricing, Demand & Revenue Management

  • Phillips — Pricing and Revenue Optimization (2021, 2nd ed.). The book on the subject.
  • Talluri & van Ryzin — The Theory and Practice of Revenue Management (2004). Deeper on the airline/hotel revenue management side.
  • Ariely — Predictably Irrational (2008). Behavioural side of pricing. Short, useful.

Forecasting

Experimentation

  • Kohavi, Tang & Xu — Trustworthy Online Controlled Experiments (2020). Written by people who run experiments at scale (Microsoft, Airbnb, LinkedIn). If you only read one book on A/B testing, read this one.
  • Gerber & Green — Field Experiments: Design, Analysis, and Interpretation (2012). The academic counterpart. Strong on design.

Bayesian Methods

  • McElreath — Statistical Rethinking (2020, 2nd ed.). The book that makes Bayesian inference click. Companion lectures on YouTube.
  • Gelman et al. — Bayesian Data Analysis (2013, 3rd ed.). Free online: https://sites.stat.columbia.edu/gelman/book/. The reference.

Courses

Blogs & Practitioner Sites

Econometrics & Causal Inference

Experimentation & Product Data Science

Pricing, MMM & Marketing Science

  • PyMC Labs Blog — https://www.pymc-labs.com/blog-posts/. Bayesian MMM, marketing measurement, PyMC-Marketing tutorials.
  • Google Ads Attribution & Incrementality (search “Google Ads Data Hub” and “geo experiments” documentation).

Forecasting

General

Papers I keep coming back to

DiD / Staggered Adoption

  • Callaway & Sant’Anna (2021). Difference-in-differences with multiple time periods. Journal of Econometrics. https://doi.org/10.1016/j.jeconom.2020.12.001
  • Goodman-Bacon (2021). Difference-in-differences with variation in treatment timing. Journal of Econometrics.
  • Sun & Abraham (2021). Estimating dynamic treatment effects in event studies with heterogeneous treatment effects. Journal of Econometrics.
  • Roth, Sant’Anna, Bilinski & Poe (2023). What’s trending in difference-in-differences? Journal of Econometrics.

Synthetic Control

  • Abadie, Diamond & Hainmueller (2010). Synthetic control methods for comparative case studies. JASA.
  • Abadie (2021). Using synthetic controls: feasibility, data requirements, and methodological aspects. JEL.

Regression Discontinuity

  • Cattaneo, Idrobo & Titiunik (2019). A practical introduction to regression discontinuity designs. Cambridge.

DML & Causal Forests

  • Chernozhukov et al. (2018). Double/debiased machine learning. Econometrics Journal.
  • Wager & Athey (2018). Estimation and inference of heterogeneous treatment effects using random forests. JASA.

Experimentation

  • Deng, Xu, Kohavi & Walker (2013). Improving the sensitivity of online controlled experiments by utilizing pre-experiment data — the CUPED paper.
  • Bojinov, Simchi-Levi & Zhao (2023). Design and analysis of switchback experiments. Management Science.

Marketing Mix Modeling

  • Jin, Wang, Sun, Chan & Koehler (2017). Bayesian methods for media mix modeling with carryover and shape effects. Google.

R Packages (that I actually use)

Causal Inference

Forecasting

Bayesian

  • brms — https://paul-buerkner.github.io/brms/. Bayesian regression, Stan under the hood, formula syntax.
  • rstanarm — Bayesian versions of standard R models.
  • CausalImpact — Google’s BSTS for causal inference.

General

  • tidyverse — dplyr, ggplot2, tidyr, purrr.
  • patchwork — combining ggplot2 figures.
  • scales — proper axis formatting.
  • gt and kableExtra — tables that don’t embarrass you.

Python

  • statsmodels — the basics: OLS, panel, GLM.
  • linearmodels — panel data, IV, and system estimators.
  • econml — https://econml.azurewebsites.net/. Microsoft’s DML / meta-learners / policy learning.
  • pymc — https://www.pymc.io/. Probabilistic programming, general-purpose Bayesian modelling.
  • pymc-marketing — https://www.pymc-marketing.io/. Bayesian MMM out of the box: adstock, saturation, budget optimisation.
  • causalinference — implements matching and other estimators.
  • dowhy — https://www.pywhy.org/dowhy/. Causal inference with a graphical model layer.
  • nixtla stack — statsforecast, mlforecast, neuralforecast.

Communities

  • Causal Inference Slack (invite through the Mixtape site).
  • R for Data Science online community — https://rfordatasci.com/.
  • Cross Validated (stats.stackexchange.com) — still the best place to ask sharp methodological questions.

If a link here is broken or you have a strong recommendation to add, let me know via email or LinkedIn.

Back to top