1st Edition

Fundamentals of Causal Inference
With R

  • Available for pre-order. Item will ship after November 29, 2021
ISBN 9780367705053
November 29, 2021 Forthcoming by Chapman and Hall/CRC
250 Pages 32 B/W Illustrations

USD $69.95

Prices & shipping based on shipping country


Book Description

One of the primary motivations for clinical trials and observational studies of humans is to infer cause and effect. Disentangling causation from confounding is of utmost importance. Fundamentals of Causal Inference explains and relates different methods of confounding adjustment in terms of potential outcomes and graphical models, including standardization, difference-in-differences estimation, the front-door method, instrumental variables estimation, and propensity score methods. It also covers effect-measure modification, precision variables, mediation analyses, and time-dependent confounding. Several real data examples, simulation studies, and analyses using R motivate the methods throughout. The book assumes familiarity with basic statistics and probability, regression, and R and is suitable for seniors or graduate students in statistics, biostatistics, and data science as well as PhD students in a wide variety of other disciplines, including epidemiology, pharmacy, the health sciences, education, and the social, economic, and behavioral sciences.

Beginning with a brief history and a review of essential elements of probability and statistics, a unique feature of the book is its focus on real and simulated datasets with all binary variables to reduce complex methods down to their fundamentals. Calculus is not required, but a willingness to tackle mathematical notation, difficult concepts, and intricate logical arguments is essential. While many real data examples are included, the book also features the Double What-If Study, based on simulated data with known causal mechanisms, in the belief that the methods are best understood in circumstances where they are known to either succeed or fail. Datasets, R code, and solutions to odd-numbered exercises are available at www.routledge.com.

Table of Contents

1. Introduction

A Brief History

Data Examples

Mortality rates by country

National Center for Education Statistics

Reducing Alcohol Consumption

The What-If? Study

The Double What-If? Study

General Social Survey

A Cancer Clinical Trial


2. Conditional Probability and Expectation

Conditional Probability

Conditional Expectation and the Law of Total Expectation


Sampling Distributions and the Bootstrap


3. Potential Outcomes and the Fundamental Problem of Causal Inference

Potential Outcomes and the Consistency Assumption

Circumventing the Fundamental Problem of Causal Inference


4. Effect-Measure Modification and Causal Interaction

Effect-Measure Modification and Statistical Interaction

Qualitative Agreement of Effect Measures in Modification

Causal Interaction



5. Causal Directed Acyclic Graphs




6. Adjusting for Confounding: Backdoor Method via Standardization

Standardization via Outcome Modeling

Average Effect of Treatment on the Treated

Standardization with a Parametric Outcome Model

Standardization via Exposure Modeling

Average Effect of Treatment on the Treated

Standardization with a Parametric Exposure Model

Doubly Robust Standardization


7. Adjusting for Confounding: Difference-in-Differences Estimators

Difference-in-Differences (DiD) Estimators with Linear, Loglinear, and Logistic Models

DiD Estimator Estimator with a Linear Model

DiD Estimator with a Loglinear Model

DiD Estimator with a Logistic Model

Comparison with Standardization


8. Adjusting for Confounding: Front-Door Method


Theory and Method

Simulated Example


9. Adjusting for Confounding: Instrumental Variables

Complier Average Causal Effect and Principal Stratification

Average Effect of Treatment on the Treated and Structural

Nested Mean Models



10. Adjusting for Confounding: Propensity-Score Methods


Using the Propensity Score in the Outcome Model

Stratification on the Propensity Score

Matching on the Propensity Score


Contents ix

11. Gaining Efficiency with Precision Variables




12. Mediation


Traditional Parametric Methods

More Examples


Adjusting for Time-Dependent Confounding

Marginal Structural Models

Structural Nested Mean Models

Optimal Dynamic Treatment Regimes



View More



Babette A. Brumback is Professor and Associate Chair for Education in the Department of Biostatistics at the University of Florida; she won the department’s Outstanding Teacher Award for 2020-2021. A Fellow of the American Statistical Association, she has researched and applied methods for causal inference since 1998, specializing in methods for time-dependent confounding, complex survey samples and clustered data.


"I would definitely consider adopting this book for my class, especially for the introduction to the history of causal inference, the fundamental problem of causal inference, and graphical models. I think it compares favorably to competing books, particularly in that I think it does a nice job referencing different causal inference frameworks." (Edward Kennedy, Carnegie Mellon University)

"This textbook would be ideal for our department’s introductory course in causal methods which targets MS students in Epidemiology and Health Policy. I would even consider using this textbook in my PhD level Causal Inference course for Biostatistics students as a supplement because of its great R code and excellent data examples...The text is very clear and presents concepts in an accessible way. It is in fact much more accessible than current textbooks I’ve used. It is well organized and builds on concepts nicely throughout. Again, I think the R code is a huge plus. There is also very little reliance on any advanced math. Understanding probabilities and conditional expectations is all that is needed to fully appreciate this textbook." (Nandita Mitra, University of Pennsylvania)

"This is a timely book on a topic that’s becoming ever more popular, for both methodological and applied researchers. the book would be a good one for undergrad majors in statistics and related fields, and at the same time some graduate students and researchers etc." (Ronghui Xu, University of California San Diego)