Modeling Age at Onset and Progression of Disability in Longitudinal Studies

• Activity Number: 571
• Type: Contributed
• Date/Time: Wednesday, August 3, 2011 : 2:00 PM to 3:50 PM
• Sponsor: Biometrics Section
• Author(s): Kumar B. Rajan *+
• Companies: Rush University
• Keywords: Two-part model ; survival and progression ; disability study ; longitudinal data analysis

Abstract

Two-part models has been frequently used to study the onset and progression of severity in disability among older adults. However, the effect of risk factors on age at onset and progression are not well established. The focus of this study is to investigate the effect of cognitive and physical functions on the age at onset and the progression of disability after onset. Disability was assessed using the activities of daily living (ADL) measured annually over a 10-year period. The risk factors associated with the age at onset and progression of the disability were studied using a two-part latent model with a Weibull survival model for age at onset and a negative binomial model for trajectory of severity, with random effects from a jointly normal distribution. The marginal likelihood after integrating the random effects did not have a closed form; therefore, we integrated the joint likelihood using Gaussian-Hermite quadrature. The results showed that black males with low education, low cognitive and physical functions had a lower age at onset of disability. Additionally, cognitive and physical functions were negatively associated with the progression of severity after onset.