JSM Activity #CE2003_17C

This is the preliminary program for the 2003 Joint Statistical Meetings in San Francisco, California. Currently included in this program is the "technical" program, schedule of invited, topic contributed, regular contributed and poster sessions; Continuing Education courses (August 2-5, 2003); and Committee and Business Meetings. This on-line program will be updated frequently to reflect the most current revisions.

To View the Program:
You may choose to view all activities of the program or just parts of it at any one time. All activities are arranged by date and time.

The views expressed here are those of the individual authors
and not necessarily those of the ASA or its board, officers, or staff.

Back to main JSM 2003 Program page
Legend: = Applied Session, = Theme Session, = Presenter
Hotels: H = Hilton San Francisco, R = Reniassance Parc Hotel 55, N = Nikko San Francisco
Add To My Program
CE2003_17C Tue, 8/5/03, 8:00 AM - 4:00 PM N-Monterey Room I
Generalized Linear and Nonlinear Models for Clustered Data and Repeated Measurements - Continuing Ed
ASA
Instructor(s): Edward Vonesh, Baxter Healthcare Corp.
There is a wide range of applications (e.g., population pharmacokinetics and pharmacodynamics, bioassay, studies of biological or agricultural growth, clinical trials, epidemiology, psychometrics and econometrics) that require fitting continuous and/or discrete correlated data to generalized linear and nonlinear models. This course provides some of the more advanced tools and theory needed to conduct a comprehensive analysis of clustered data and/or repeated measurements in those settings where linear models are no longer appropriate. Although the emphasis of this course will be on nonlinear applications, we start with a brief overview of the linear mixed-effects (LME) model since many of its techniques can be adapted to the nonlinear mixed-effects (NLME) setting. We extend the LME model to include NLME models for normally distributed data. In this setting, a careful assessment is given to the advantages and disadvantages of using marginal or population-averaged (PA) models versus mixed-effects or subject-specific (SS) models. We then extend the NLME model to a broader class of generalized linear and nonlinear mixed-effects models. Such models are useful for jointly modeling continuous and discrete data. Various methods for estimating the parameters of interest will be presented as will an assessment of their relative strengths and weaknesses. In addition, inferential techniques and both likelihood and non-likelihood based techniques for evaluating model goodness-of-fit will be presented. The final segment of the course will focus on various methods for analyzing clustered data and/or repeated measurements in the presence of missing data. Particular attention will be paid to applications where missing data are non-ignorable. Numerous examples from a variety of disciplines will be used throughout the course to illustrate various concepts and techniques. Participants are expected to have a working knowledge of linear models and matrix algebra. Fees: M- $325 ($430 after July 18), NM- $415 ($520 after July 18), SM- $200 ($325 after July 18)
 

JSM 2003 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 2003