JSM Activity #32

Back to main JSM 2001 Program page


Activity ID:  32
Title Room
! Modern Approaches to Missing Data Problems M-Amsterdam/Stockholm
Date / Time Sponsor Type
08/05/2001    4:00 PM  -  5:50 PM Biopharmaceutical Section*, Intl Indian Statistical Association, ENAR Invited
Organizer: Cyrus Mehta, Cytel Software Corp.
Chair: Cyrus Mehta, Cytel Software Corp.
Discussant: 5:20 PM - Roderick Little, University of Michigan    
Floor Discussion 5:45 PM
Description

The problem of missing data is a common one in biomedical, social and behavioral applications. It is an especially urgent problem for clinical and pre-clinical studies where the numerical values of one or more prognostic factors, and one or more repeated measures are frequently lost or unrecorded. The last 25 years has seen a virtual explosion of research into statistical methods, semi-parametric survival models, and longitudinal models with random effects. No single method appears satisfactory for handling missing data in all these settings.
  300182  By:  Donald Rubin 4:05 PM 08/05/2001
Multiple Imputation Methods for Missing Data

  300183  By:  Joseph Ibrahim 4:30 PM 08/05/2001
The EM Algorithm by Method of Weights for Missing Data Problems

  300184  By:  Dan Scharfstein 4:55 PM 08/05/2001
Frequentist and Bayesian Inference for Randomized Studies with Missing Data

JSM 2001

For information, contact meetings@amstat.org or phone (703) 684-1221.

If you have questions about the Continuing Education program, please contact the Education Department.

Revised March 2001