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

Abstract Details

Activity Number: 127
Type: Contributed
Date/Time: Monday, August 2, 2010 : 8:30 AM to 10:20 AM
Sponsor: Biometrics Section
Abstract - #307597
Title: Analysis of Constrained Generalized Linear Models with Missing Data
Author(s): Karelyn Davis*+ and Sanjoy Sinha and Chul Gyu Park
Companies: Carleton University/Health Canada and Carleton University and Carleton University
Address: Health Canada, Ottawa, ON, K1A 0K9, Canada
Keywords: Constrained inference ; EM algorithm ; Generalized linear model ; Maximum likelihood
Abstract:

Statisticians often encounter data that is non-normally distributed, and includes some missing observations. For the former case, generalized linear models (GLM) are typically considered in the statistical analysis; whereas missing data are commonly analyzed through imputation or the Expectation-Maximization (EM) algorithm. While many procedures have been proposed for these models, only a few researchers have studied estimation and hypothesis testing in the presence of parameter constraints. The presentation will discuss maximum likelihood inference for such models under linear inequality constraints, using a gradient projection version of the EM algorithm. Simulation results and an application to detection of blood contaminants for an environmental study will also be discussed.


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 jsm@amstat.org or phone (888) 231-3473.

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