Statistical Methods for Improving Confounder Adjustment For Emergent Treatment Comparison

Project Title Statistical Methods for Improving Confounder Adjustment For Emergent Treatment Comparison
Date Posted
Tuesday, April 22, 2014
Status
Complete
Deliverables
Description

This report describes a sequential framework for monitoring newly marketed treatments while balancing measured confounders, and then uses this framework to guide decisions on selecting optimal confounder adjustment methods.  The report applies the framework to monitor the safety of newly marketed molecular entities using the Mini-Sentinel Distributed Database.  It also provides codes for measuring the strength of the association between treatment and confounders, calculating time-varying Disease Risk Scores (DRS) and Propensity Scores (PS), score matching, stratification, and sequential analyses.

Workgroup Leader(s)

Stanley Xu PhD; The Institute for Health Research, Kaiser Permanente Colorado, Denver, CO

Workgroup Members

Susan Shetterly MS; Marsha A. Raebel PharmD; The Institute for Health Research, Kaiser Permanente Colorado, Denver, CO

Andrea J. Cook PhD; Biostatistics Unit, Group Health Research Institute, Seattle, WA

Sunali Goonesekera MS; Department of Population Medicine, Harvard Pilgrim Health Care Institute and Harvard Medical School, Boston, MA

Azadeh Shoaibi MS, MHS; Eric Frimpong PhD; Brad McEvoy PhD; Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, MD

Jason Roy PhD; Department of Biostatistics and Epidemiology, University of Pennsylvania, Philadelphia, PA

Bruce Fireman MS, Division of Research, Kaiser Permanente Northern California, Oakland, CA

Data Sources
Mini-Sentinel Distributed Database (MSDD)