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

Abstract Details

Activity Number: 530
Type: Contributed
Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
Sponsor: Section on Statistics in Epidemiology
Abstract - #308480
Title: Adjustment of Regional Differences Using Generalized Additive Mixed Model to Estimate Health Effect of PM2.5
Author(s): Ayano Takeuchi*+ and Yutaka Matsuyama and Hiroshi Nitta and Masaji Ono
Companies: The University of Tokyo and The University of Tokyo and National Institute for Environmental Studies and National Institute for Environmental Studies
Address: 7-3-1 Hongo Bunkyo-ku, Tokyo, 1130033, Japan
Keywords: Generalized Additive Mixed Model ; PM2.5 Air Pollution ; Time Series Study ; Regional Difference

Last decade, many time series studies have indicated that ambient particulate matter(PM2.5) exposure is associated with daily mortality. But these effect size is different according to the region. Because it is well known that weather conditions have great influence in the effect of PM2.5, most studies use generalized additive model(GAM) with spline function for adjusting these effects. There are some studies that adjuste regional difference using meta-analytic method or hierarchical model, but there is no study using mixed-effect model. In this paper, we apply generalized additive mixed model(GAMM) to Japanese 20 cities data using R, and adjust regional difference with random effect. Time series data contain daily count of death and daily concentration of air pollutants from 2001 to 2007. We will show the health effect of PM2.5 using GAMM and compare it with the result of other methods.

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.