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

Abstract Details

Activity Number: 172
Type: Contributed
Date/Time: Monday, August 2, 2010 : 10:30 AM to 12:20 PM
Sponsor: Biopharmaceutical Section
Abstract - #308781
Title: Identifying Random-Effect Parameters in Nonlinear Mixed-Effect Models by Stepwise Forward Selection
Author(s): Yaming Hang*+
Companies: Merck & Co., Inc.
Address: UG1CD-44, North Wales, PA, 19454,
Keywords: Nonlinear mixed effect model ; population pharmacokinetic/pharmacodynamic model ; inter-individual variation ; stepwise forward selection
Abstract:

Nonlinear mixed effect models are often employed in the population pharmacokinetic/ pharmacodynamic modeling. It is important to identify parameters with inter-individual variability (IIV, also called random parameter). The scarce literature on this topic suggests that one starts with a model with IIV on all parameters and eliminate subsequently, but it is often unfeasible because a model with large number of parameters frequently fails to converge. In this presentation, a stepwise selection method will be introduced. The method starts with a base model with IIV on none of the parameters, utilizing the likelihood ratio test, it proceeds with selection of random parameters in a stepwise forward fashion. Simulation studies were conducted to show the capability of this method to correctly identify random parameters. The application of this method on real data will also be presented.


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.