Northwestern University

Nov
19
Mon 3:00 PM

Propensity Score Matching in Randomized Clinical Trials with Two or More Arms

When: Monday, November 19, 2012
3:00 PM - 4:30 PM  

Where: 680 N. Lake Shore Drive, Ste 1400, Stamler Conference Room  
Chicago, IL 60611 map it

Audience: Faculty/Staff - Student - Public

Contact: Franz Nichols   (312) 503-1043

Group: Department of Preventive Medicine

Category: Academic

Add Event to Calendar Email Event More Events

Description:

Dr. Shenzhen Zu, PhD, Research Statistician, Abbott Lab will be speaking about:

Propensity Score Matching in Randomized Clinical Trials with Two or More Arms

 

Cluster randomization trials with relatively few clusters have been widely used in recent years for evaluation of health-care strategies. On average, randomized treatment assignment achieves balance in both known and unknown confounding factors between treatment groups, however, inpractice investigators can only introduce a small amount of stratification and cannot balance on all the important variables simultaneously. The limitation arises especially when there are many confounding variables in small studies. In this talk, we introduce a new randomization design, the balance match weighted (BMW) design, which applies the optimal matching with constraints technique to a prospective randomized design and aims to minimize the mean squared error (MSE) of the treatment effect estimator. We evaluate the properties of these extended designs in simulation studies and illustrate these methods in proposing a design for a cardiovascular trial.

 

 

Add Event To My Group:

Please sign-in