This is the program for the 2010 Joint Statistical Meetings in Vancouver, British Columbia.

Abstract Details

Activity Number: 360
Type: Contributed
Date/Time: Tuesday, August 3, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biometrics Section
Abstract - #308815
Title: Instrument Variable Analysis of Prostate Cancer Treatments for Clustered Binary Data
Author(s): Anjun Cao* and Dirk F. Moore+
Companies: NovoNordisk and University of Medicine and Dentistry of New Jersey
Address: Biostatistics, 685 Hoes Lane West, Piscataway, NJ, 08854,
Keywords: instrument variable analysis ; prostate cancer ; SEER/Medicare ; clustered data

Knowing which of competing treatment options is best for prostate cancer is of critical interest to patients and physicians. But in elderly men, it is often difficult to set up randomized clinical trials. Instrument variable analysis (IVA) is a method that can be applied to observational data that captures many of the advantages that randomized trials offer for inferring causation. We use two-stage regression combined with generalized estimating equations to adapt IVA to the special case of clustered binary data in the SEER / Medicare database. The effect of the distribution of an unobserved confounder on the bias of IVA estimates with a non-identity link function is discussed. We illustrate the method with data comparing hormone therapy to active surveillance in prostate cancer patients.

The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.

Back to the full JSM 2010 program

2010 JSM Online Program Home

For information, contact or phone (888) 231-3473.

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