projectdidact.net - Leveraging baseline covariates to improve the efficiency of randomized trials (Rosenblum)

Dr. Michael Rosenblum | ProjectDidact

Projectdidact.net Spined HTML

Dr. Michael Rosenblum | ProjectDidact Skip to main content ProjectDidact Toggle navigation Home People Investigators Advisory Board Events News Blog Dr. Michael Rosenblum Project Overview: Improving Estimator Precision and Robustness in Randomized Trials In randomized clinical trials with baseline variables that are prognostic for the primary outcome, there is potential to modernize precision and reduce sample size by thus adjusting for these variables. A major rencontre is that there are multiple statistical methods to retread for baseline variables, but little guidance on which is weightier to use in a given context. The nomination of method can have important consequences. For example, one wontedly used method leads to uninterpretable estimates if there is any treatment effect heterogeneity, which would jeopardize the validity of trial conclusions. The goal of this project (currently underway) is to requite practical guidance on how to stave this problem, while retaining the advantages of covariate adjustment. We will discuss relevant statistical methods and software (which wield to continuous, binary, and time-to-event outcomes). Data examples from stroke and Alzheimer's disease trials will be used to illustrate these methods. Software: Software in SAS and R for enhanced efficiency estimators of treatment effects in randomized trials: Enhanced Precision Estimators for Randomized Trials with Repeated Measures Using Targeted Maximum Likelihood Estimation (R and SAS code) Presentations Leveraging Prognostic Baseline Variables to Gain Precision in Randomized Trials”, Speaker, Association of Clinical and Translational Statisticians (ACTS) Annual Meeting, Baltimore, MD, July 29, 2017. Leveraging Prognostic Baseline Variables to Gain Precision in Randomized Trials”, Speaker, Translational Science, Washington, D.C., April 20, 2017. Leveraging Prognostic Baseline Variables to Gain Precision in Randomized Trials”, Speaker, Victorian Centre for Biostatistics, Department of Epidemiology and Preventive Medicine, School of Public Health and Preventive Medicine, Monash University, Melbourne, Australia, January 12, 2017. Improving Precision by Adjusting for Prognostic Baseline Variables in Randomized Trials with Binary Outcomes, without Regression Model Assumptions”, Speaker, Department of Statistics, University of Colombo, Sri Lanka, January 17, 2017. Short courses: (video-recordings misogynist here: rosenblum.jhu.edu) Adaptive Enrichment Trial Designs: Statistical Methods, Trial Optimization Software, and Four Case Studies”, Instructor of half-day course, U.S. Food and Drug Administration, Silver Spring, MD, November 20, 2017. Adaptive Enrichment Designs for Confirmatory Randomized Trials: Statistical Methods and Software Tools”, Instructor of half-day course, Institute for Clinical and Translational Research, Johns Hopkins University, August 30, 2017. (127 registered participants) Adaptive Enrichment Designs for Confirmatory Randomized Trials: Statistical Methods and Software Tools”, Instructor of half-day course, University of California Berkeley’s Forum for Collaborative Research in Washington, D.C., June 13, 2017. Working papers: IMPROVING POWER IN GROUP SEQUENTIAL, RANDOMIZED TRIALS BY ADJUSTING FOR PROGNOSTIC BASELINE VARIABLES AND SHORT-TERM OUTCOMES, Tianchen Qian, Michael Rosenblum, and Huitong Qiu Matching the Efficiency Gains of the Logistic Regression Estimator While Avoiding its Interpretability Problems, in Randomized Trials, Michael Rosenblum and Jon Arni Steingrimsson Related work: Simple, Efficient Estimators of Treatment Effects in Randomized Trials Using Generalized Linear Models to Leverage Baseline Variables.Rosenblum, M. and van der Laan, M. J. (2010), International Journal of Biostatistics, 6(1). Leveraging Prognostic Baseline Variables to Gain Precision in Randomized Trials.Colantuoni, E. and Rosenblum, M. (2015), Statistics in Medicine. 34(18), 2602-2617. Enhanced Precision in the Analysis of Randomized Trials with Ordinal Outcomes.Diaz, I., Colantuoni, E., Rosenblum, M. (2016), Biometrics. (72) 422-431. Measuring the Contribution of Genomic Predictors to Improving Estimator Precision in Randomized trials.Patil, P., Colantuoni, E., Leek, J. T., Rosenblum, M. (2016), Contemporary Clinical Trials Communications. 48-54. Improving Precision By Adjusting For Baseline Variables In Randomized Trials With Binary Outcomes, Without Regression Model Assumptions.Steingrmisson, J. A., Hanley, D. F., and Rosenblum, M., Contemporary Clinical Trials. 54. 18-24 Matching the Efficiency Gains of the Logistic Regression Estimator While Avoiding its Interpretability Problems, in Randomized Trials.Rosenblum, Michael and Steingrimsson, Jon Arni, (October 2016). Johns Hopkins University, Dept. of Biostatistics Working Papers. Working Paper 281. Lectures Video-Recording of Short-Course on Adaptive Enrichment Clinical Trial Designs (June 13, 2017) Improving Precision by Adjusting For Baseline Variables in Randomized Trials, without Regression Model Assumptions