Statistical Methods for Drug Safety: 1st Edition (Hardback) book cover

Statistical Methods for Drug Safety

1st Edition

By Robert D. Gibbons, Anup Amatya

Chapman and Hall/CRC

308 pages | 36 B/W Illus.

Purchasing Options:$ = USD
Hardback: 9781466561847
pub: 2015-07-21
SAVE ~$22.00
eBook (VitalSource) : 9780429099687
pub: 2015-07-28
from $28.98

FREE Standard Shipping!


Explore Important Tools for High-Quality Work in Pharmaceutical Safety

Statistical Methods for Drug Safety presents a wide variety of statistical approaches for analyzing pharmacoepidemiologic data. It covers both commonly used techniques, such as proportional reporting ratios for the analysis of spontaneous adverse event reports, and newer approaches, such as the use of marginal structural models for controlling dynamic selection bias in the analysis of large-scale longitudinal observational data.

Choose the Right Statistical Approach for Analyzing Your Drug Safety Data

The book describes linear and non-linear mixed-effects models, discrete-time survival models, and new approaches to the meta-analysis of rare binary adverse events. It explores research involving the re-analysis of complete longitudinal patient records from randomized clinical trials. The book discusses causal inference models, including propensity score matching, marginal structural models, and differential effects, as well as mixed-effects Poisson regression models for analyzing ecological data, such as county-level adverse event rates. The authors also cover numerous other methods useful for the analysis of within-subject and between-subject variation in adverse events abstracted from large-scale medical claims databases, electronic health records, and additional observational data streams.

Advance Statistical Practice in Pharmacoepidemiology

Authored by two professors at the forefront of developing new statistical methodologies to address pharmacoepidemiologic problems, this book provides a cohesive compendium of statistical methods that pharmacoepidemiologists can readily use in their work. It also encourages statistical scientists to develop new methods that go beyond the foundation covered in the text.


"Gibbons and Amatya’s book Statistical Methods for Drug Safety provides an overview of the core statistical methodology used in pharmacoepidemiology and drug safety. The authors draw on considerable experience in drug safety research to describe many of the key methods used in this field. The book is directed at two distinct groups of readers: statisticians with a good grasp of core concepts in applied statistics who are interested in pharmacoepidemiology, and pharmacoepidemiologists with a strong quantitative background who wish to learn more about the statistical tools in use in the field. Chapter 2 leads off with an overview of core statistical concepts used in epidemiology and clinical research. This brief section is very well done and helps orient the broad readership with a common language. This section would be helpful for either a nonstatistician needing an overview or for a statistician unfamiliar with some of the epidemiology-specific concepts used in the field. … The book is technically quite detailed and provides a solid grounding on each of the tools used. Many of the chapters could stand alone as a solid introduction to the area in question. …. This book would be a useful addition to the library of a drug safety researcher, whether a statistician or an epidemiologist, who is interested in the statistical methods underlying the field."

—Robert W. Platt, McGill University, in The American Statistician, October 2017

"With the growing emphasis and regulation of product safety evaluation and benefit–risk evaluation, the publication of this safety statistics book has been a great addition to the Chapman and Hall/CRC biostatistics series in 2015. Comparing to the other well-written books on quantitative evaluation of drug safety, this book focuses on the advanced statistical methodologies and practice in pharmacoepidemiologic problems. The book covers a wide variety of statistical methodologies to various types of drug safety data, including spontaneous adverse event reporting database, medical claim database, longitudinal observational studies, and randomized clinical trials (RCTs). Throughout these book chapters, real case studies on the safety evaluation, for which authors either have served as a statistical consultation or have done applied methodology research, have been used to illustrate the relevant methods. Their real experiences with their humorous and story-telling styles have made the reading captivating….Drug safety evaluation is becoming an international and increasingly important priority. As Bob Oneil pointed out, statistical methodology for safety monitoring has not been well developed to match that for efficacy. This book provides a great resource for a wide variety of statistical methods that are useful for pharmacoepidemiologists and safety physicians in their work. It should also motivate biostatisticians to innovate and contribute to this important field."

—William Wang in Journal of Biopharmaceutical Statistics, September 2016

Table of Contents


Randomized Clinical Trials

Observational Studies

The Problem of Multiple Comparisons

The Evolution of Available Data Streams

The Hierarchy of Scientific Evidence

Statistical Significance


Basic Statistical Concepts

Relative Risk

Odds Ratio

Statistical Power

Maximum Likelihood Estimation

Non-Linear Regression Models

Causal Inference

Multi-Level Models


Issues Inherent in Longitudinal Data

Historical Background

Statistical Models for the Analysis of Longitudinal and/or Clustered Data

Causal Inference


Propensity Score Matching

Marginal Structural Models

Instrumental Variables

Differential Effects

Analysis of Spontaneous Reports

Proportional Reporting Ratio

Bayesian Confidence Propagation Neural Network (BCPNN)

Empirical Bayes Screening

Multi-Item Gamma Poisson Shrinker

Bayesian Lasso Logistic Regression

Random-Effect Poisson Regression



Fixed-Effect Meta-Analysis

Random-Effect Meta-Analysis

Maximum Marginal Likelihood/Empirical Bayes Method

Bayesian Meta-Analysis

Confidence Distribution Framework for Meta-Analysis


Ecological Methods

Time Series Methods

State Space Model

Change Point Analysis

Mixed-Effects Poisson Regression Model

Discrete-Time Survival Models


Discrete-Time Ordinal Regression Model

Discrete-Time Ordinal Regression Frailty Model


Competing Risk Models


Research Synthesis


Three-Level Mixed-Effects Regression Models

Analysis of Medical Claims Data


Administrative Claims

Observational Data

Experimental Strategies

Statistical Strategies



Methods to Be Avoided


Spontaneous Reports

Vote Counting

Simple Pooling of Studies

Including Randomized and Non-Randomized Trials in Meta-Analysis

Multiple Comparisons and Biased Reporting of Results

Immortality Time Bias

Summary and Conclusions

Final Thoughts



About the Authors

Robert D. Gibbons, PhD, is a professor of biostatistics in the Departments of Medicine, Public Health Sciences, and Psychiatry and director of the Center for Health Statistics at the University of Chicago. He is a fellow of the American Statistical Association (ASA) and a member of the Institute of Medicine of the National Academy of Sciences. He has been a recipient of the ASA’s Outstanding Statistical Application Award and two Youden Prizes.

Anup Amatya, PhD, is an assistant professor in the Department of Public Health Sciences at New Mexico State University. His current research focuses on meta-analysis of sparse binary data and sample size determination in hierarchical non-linear models.

About the Series

Chapman & Hall/CRC Biostatistics Series

Learn more…

Subject Categories

BISAC Subject Codes/Headings:
MATHEMATICS / Probability & Statistics / General
MEDICAL / Pharmacology
MEDICAL / Biostatistics