An Age-Segmented Poisson Log-Bilinear model for Sex- and Cause-Specific Mortality Rates

• Activity Number: 675
• Type: Contributed
• Date/Time: Thursday, August 4, 2011 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Jiraphan Suntornchost*+ and Eric V. Slud and Rong Wei
• Companies: Centers for Disease Control and Prevention and University of Maryland and Centers for Disease Control and Prevention
• Keywords: Smoothed Segmented Lee Carter model ; Mortality ; Poisson Log-Bilinear model ; Likelihood method ; Cancer

Abstract

In 2010, the authors proposed the Smoothed Segmented Lee Carter model (SSLC), an age-segmented Lee Carter model with spline-smoothed period effects, as an age-specific mortality model for leading causes of death. The SSLC model was shown to improve the estimation of period-effects across ages over the original model. In this paper, we apply a Poisson likelihood version of the SSLC model, the Smoothed Segmented Poisson Log-Bilinear model (SSPB), to study sex-differences in cause-specific U.S. mortality. The model is fitted by using a Penalized Poisson-Likelihood method to the 1971-2006 public-use age and sex-specific mortality rates due to Cancer released by the National Center for Health Statistics.