Applying Quantitative Bias Analysis to Epidemiologic Data

Part I: Introduction
1 Introduction and Objectives1 Introduction 1.2 Nonrandomized Epidemiologic Research 1.3 The Treatment of Uncertainty in Nonrandomized Research 1.4 Objective 1.5 Conclusion 2 A Guide to Implementing Quantitative Bias Analysis 2.1 Introduction 2.2 Reducing Error 2.3 Reducing Error by Design 2.4 Reducing Error in the Analysis 2.5 Quantifying Error 2.6 Evaluating the Potential Value of Quantitative Bias Analysis2.7 Planning for Bias Analysis 2.8 Creating a Data Collection Plan for Bias Analysis 2.9 Creating an Analytic Plan for a Bias Analysis 2.10 Bias Analysis Techniques 2.11 Introduction to Inference 2.12 Conclusion 3 Data Sources for Bias Analysis 3.1 Bias Parameters 3.2 Internal Data Sources 3.3 Selection Bias 3.4 Uncontrolled Confounder 3.5 Information Bias 3.6 Limitations of Internal Validation Studies 3.7 External Data Sources 3.8 Selection Bias 3.9 Uncontrolled Confounder 3.10 Information Bias 3.11 Summary
Part II: Preliminary Methods to Adjust for Systematic Errors 4 Selection Bias 4.1 Introduction 4.2 Definitions and Terms4.3 Motivation for Bias Analysis 4.4 Sources of Data 4.5 Simple Correction for Differential Initial Participation 4.6 Simple Correction for Differential Loss-to-Follow-up4.7 Sensitivity Analysis of the Bias Analysis 4.7 Signed Directed Acyclic Graphs to Estimate the Direction of Bias 5 Uncontrolled Confounders 5.1 Introduction 5.2 Definitions and Terms5.3 Motivation for Bias Analysis 5.4 Sources of Data5.5 Introduction to Simple Bias Analysis 5.6 Implementation of Simple Bias Analysis5.7 Sensitivity Analysis of the Bias Analysis 5.8 Uncontrolled Confounder in the Presence of Effect Modification 5.9 Polytomous Confounders 5.10 Bounding the Bias Limits of Uncontrolled Confounding5.10 Signed Directed Acyclic Graphs to Estimate the Direction of Bias5.11 Uncontrolled Confounding with Continuous Outcome, Exposure, or Confounder 6 Misclassification 6.1 Introduction 6.2 Definitions and Terms6.3 Motivation for Bias Analysis6.4 Sources of Data6.5 Calculating Classification Bias Parameters from Validation Data6.6 Exposure Misclassification for Dichotomous Exposures6.7 Exposure Misclassification for Polytomous Exposures6.8 Disease Misclassification 6.9 Covariate Misclassification 6.10 Dependent Misclassification6.11 Sensitivity Analysis of the Bias Analysis6.12 Adjusting Standard Errors for Corrections 7 Measurement Error for Continuous Variables7.1 Introduction7.2 Definition and Terms7.3 Motivation for Bias Analysis7.4 Exposure Measurement error7.5 Outcome Measurement error7.6 Covariate Measurement Error7.7 Correlated errors 8 Multiple Bias Modeling 8.1 Introduction 8.2 Order of Bias Analyses8.3 Multiple Bias Analysis, Simple Methods
Part III: Methods to Incorporate Systematic and Random Errors 9 Bias Analysis by Simulatio
About the Author: Timothy Lash, D.Sc., M.P.H., is professor in the Department of Epidemiology at the Rollins School of Public Health and honorary professor of cancer epidemiology in the Department of Clinical Epidemiology at Aarhus University in Aarhus, Denmark. Dr. Lash is also past-President of the Society for Epidemiologic Research (SER) for the 2014-2015 term. His research focuses on predictors of cancer recurrence, including molecular predictors of treatment effectiveness and late recurrence, and he also researches methods and applications of quantitative bias analysis.

Matthew Fox, D.Sc., M.P.H, is associate professor in the Center for Global Health & Development and in the Department of Epidemiology at Boston University. Before joining Boston University, he was a Peace Corps volunteer in the former Soviet Republic of Turkmenistan. Dr. Fox is currently funded through a K award from the National Institutes of Allergy and Infectious Diseases to work on ways to improve retention in HIV-care programs in South Africa from time of testing HIV-positive through long-term treatment. His research interests include treatment outcomes in HIV-treatment programs, infectious disease epidemiology, and epidemiological methods, including quantitative bias analysis.

Richard MacLehose, Ph.D., is associate professor in the Division of Epidemiology and Community Health at the University of Minnesota. Dr. MacLehose received his M.S. in epidemiology from the University of Washington and his Ph.D. in epidemiology from the University of North Carolina. His research interests include Bayesian statistics (including bias analysis), epidemiologic methods, applied biostatistics, and reproductive and environmental health.