Causal Inference in Marketing: A Practical Toolkit for Panel Data : Two-Volume Set

Causal Inference in Marketing: A Practical Toolkit for Panel Data is a two-volume guide to turning messy marketing panels into credible causal evidence. It connects modern causal inference with the operational realities of advertising, pricing, loyalty, platforms, and marketing effectiveness.

Causal Inference in Marketing: A Practical Toolkit for Panel Data is a two-volume guide to turning messy marketing panels into credible causal evidence. Written for data scientists, marketing analysts, econometricians, and applied researchers, it connects modern causal inference with the operational realities of advertising, pricing, loyalty, platforms, and marketing effectiveness. The set is distinctive in its design-first treatment of panel data: it begins with estimands, assignment mechanisms, support, and diagnostics before moving to estimators. Readers should be comfortable with regression and applied statistics, but the exposition is built to make the assumptions behind causal claims explicit rather than hidden inside software defaults. Across the two volumes, readers learn how to choose, implement, diagnose, and report causal designs for marketing measurement. Volume 1 develops the foundations, including potential outcomes, design-based thinking for panels, difference-in-differences, event-study designs, synthetic control, hybrid synthetic control methods, interactive fixed effects, matrix completion, dynamic treatment effects, heterogeneity, interference, and spillovers. Volume 2 extends the toolkit to machine learning for nuisance adjustment and treatment-effect heterogeneity, high-dimensional controls, regularisation, continuous and nonlinear panel models, threats to validity, inference and uncertainty quantification, design diagnostics, and applied marketing workflows. The result is a practical framework for evaluating incrementality, media mix models, geo-experiments, platform data, pricing, promotions, customer lifetime value, retention, and reproducibility while keeping the causal target, data limitations, and business decision aligned.