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

Activity Details

CE_22C Tue, 8/3/2010, 1:00 PM - 5:00 PM CC-8 (East)
Design and Analysis of Count and Zero-Inflated Data — Continuing Education Course
Instructor(s): Mani Lakshminarayanan, Merck & Co., Inc., Madhuja Mallick, Merck & Co., Inc.
In many areas of research, experimental data are collected and analyzed as counts that are referred to as the number of times an event occurs. For example, in clinical trials, endpoints based on count data are most common in trials designed to study chronic diseases where the counts are done within an interval in time, usually resulting in a number 0 or 1 (eg, survival). Some common examples of count data include the number of heart attacks, the number of hospitalizations, number of trips to recreation sites, number of cigarette consumption etc. Poisson regression is a general framework for analyzing count data. However, count data with excessive zeros relative to a Poisson distribution is also commonly encountered that could result in an over-dispersion of the data. Common approaches for treating such data include negative binomial and zero-inflated Poisson models. In this course, the audience will be introduced to both design and analysis considerations of count data with examples in support of the underlying discussion. The audience will also be exposed to some of the software tools such as the SAS procedure, PROC COUNTREG, as part of the overall illustration of various approaches. This course will also introduce the framework for analyzing the zero inflated continuous data (for e.g., average inpatient costs among heart patients) using software tools.



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.