Goodness-of-Fit Test for Multinomial Regression Model in NUN Study

• Activity Number: 554
• Type: Contributed
• Date/Time: Wednesday, August 12, 2015 : 10:30 AM to 12:20 PM
• Sponsor: Section on Statistics in Epidemiology
• Author(s): Zhiheng Xie* and Richard J. Kryscio
• Companies: and University of Kentucky
• Keywords: Goodness of fit test ; Multinomial logistic regression ; Discrete-time Markov chain ; Nun Study

Abstract

Discrete-time Markov chains have been used to analyze the transition of subjects from intact cognition to dementia with mild cognitive impairment and global impairment as intervening transient states, and death as competing risk. A multinomial logistic regression model is used to estimate the probability distribution in each row of the one step transition matrix that correspond to the transient states. We investigate some goodness of fit tests for a multinomial distribution with covariates to assess the fit of this model to the data. We propose a modified chi-square test statistic and a score test statistic for the multinomial assumption in each row of the transition probability matrix. We apply the test to the data from the Nun Study, a cohort of 461 participants. We incorporate presence or absence of the APOE-4 allele, education, and age as covariates in the application.