Understanding and Tackling Measurement Error: A Review of Modern Practical Methods

Measurement error and misclassification of variables are frequently encountered in epidemiological and clinical research, and involve variables of considerable importance in public health such as dietary intakes, physical activity, smoking, and environmental pollutants. Further, the rising interest in research with electronic health records has brought new challenges and renewed interest in robust and practical methods to address error prone exposures and outcomes. The overall objective of this course is to introduce the issues raised by measurement error and the implementation of practical analysis approaches to mitigate its effects. The course will begin with a discussion of the effects of measurement error in regression analyses, then move to techniques for mitigating those effects via statistical analysis and study design. Analytical methods discussed include regression calibration, simulation extrapolation (SIMEX), likelihood-based methods, and Bayesian methods. The emphasis will be on practical application and worked examples will be used throughout. The course will incorporate formal lectures as well as practical sessions in which participants will work through a series of real data examples using R software.