Overview of Missing Data

Seminar Series

Friday, August 24, 2018 - 01:30
Hock Plaza 11110

National databases provide rich sources to identify relevant predictors for diseases and clinical outcomes. These databases, however, often lack strict guidelines on reporting of patient demographics and outcomes, leading to missing data. In this presentation, we will discuss the implications when data are missing completely at random (MCAR), at random (MAR), and not at random (MNAR), and we will introduce proposed methods of handling missing data including complete case analysis, single and multiple imputation. This will serve as an introduction for a future seminar where we will focus on multiple imputation and the use of shrinkage estimators (specifically, lasso algorithm) for model selection.

Tracy Truong, MS
Biostatistician II
Biostat Core