作者: Jonathan P. Prasad
DOI:
关键词:
摘要: ZERO-INFLATED CENSORED REGRESSION MODELS: AN APPLICATION WITH EPISODE OF CARE DATA Jonathan P. Prasad Department of Statistics Master Science The objective this project is to fit a sequence increasingly complex zeroinflated censored regression models known data set. It quite common find count in statistical analyses health-related data. Modeling such while ignoring the censoring, zero-inflation, and overdispersion often results biased parameter estimates. This develops various that can be used predict response variable affected by predictor variables. parameters are estimated with Bayesian analysis using Markov chain Monte Carlo (MCMC) algorithm. tests for model adequacy discussed applied an observed