Statistical methods for comparing stroke death rates for Suphan Buri with Bangkok in 2005

Abstract

Abstract

This study aims to compare stroke death rates between two populations using Poisson regression model. The stroke deaths for Suphan Buri and Bangkok in 2005 were analyzed after adjusting for misclassification of cause of death. Age-standardization was used to adjust for population differences in gender and age group. Standardized mortality ratio (SMR) was used to explore deaths. A Poisson model was used to compare stroke death rates after adjusting for demographic factors. The results showed that SMRs were greater than 1 for both males and females. These SMRs indicated that there were excess stroke deaths for both males and females in Suphan Buri compared to Bangkok. The Poisson model was fitted well with the stroke data. The stroke death rate was statistically significant higher in Suphan Buri than those in Bangkok after adjusting for gender-age-group. The rates were higher for males than for females in all age groups under 80 years. Therefore, increasing efforts in health care and stroke prevention should target at males in suburban areas. The statistical methods used in this study can be applied to other regions in Thailand and to other countries for comparing cause-specific mortality between populations.

Keywords: Bangkok, Poisson regression, standardization, stroke, Suphan Buri