期刊名称:Journal of Modern Applied Statistical Methods
出版年度:2017
卷号:16
期号:1
页码:29
出版社:Wayne State University
摘要:The performance of several models under different conditions of zero-inflation and dispersion are evaluated. Results from simulated and real data showed that the zero-altered or zero-inflated negative binomial model were preferred over others (e.g., ordinary least-squares regression with log-transformed outcome, Poisson model) when data have excessive zeros and over-dispersion.