|
Activity Number:
|
439
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Wednesday, August 5, 2009 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Epidemiology
|
| Abstract - #304818 |
|
Title:
|
A Sequential Approach of Age-Period-Cohort Analysis
|
|
Author(s):
|
Kit Ling Yang*+
|
|
Companies:
|
The University of Hong Kong
|
|
Address:
|
Room 518, 5/F, Meng Wah Complex, Hong Kong, International, , China
|
|
Keywords:
|
Age-period-cohort models ; Poisson regression ; Sequential method ; Suicide ; Hong Kong
|
|
Abstract:
|
Age-period-cohort analysis has long been recognized as one of the most effective tools to study the temporal effects on epidemiological data. However, as cohort can be determined by subtracting age from period, the linear dependence among age, period and cohort results in an identifiability problem. In spite of the availability of diverse techniques to resolve the collinearity issue, there has been little work taking the sequential order of model fitting into consideration. This research discusses a sequential approach for fitting the age-period-cohort model with modification from previous studies. A numerical illustration using the suicide data from 1981 to 2005 in Hong Kong is presented. The analytical results are beneficial to understand the underlying suicide pattern, to identify the group of people most at risk and to provide a guide to resource allocation for suicide prevention.
|
- 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 2009 program |
