Bayesian Analysis of Doubly Inflated Poisson Regression for Correlated Count Data: Application to DMFT Data

被引：0

作者：

Chaboki, B. Gholami ^{[1
]}

Baghban, A. Akbarzadeh ^{[2
]}

Baghfalaki, T. ^{[3
]}

Khoshnevisan, M. ^{[4
]}

Meymeh, M. Heydarpour ^{[5
]}

机构：

[1] Shahid Beheshti Univ Med Sci, Sch Allied Med Sci, Dept Biostat, Tehran, Iran

[2] Shahid Beheshti Univ Med Sci, Sch Allied Med Sci, Dept Biostat, Prote Res Ctr, Tehran, Iran

[3] Tarbiat Modares Univ, Fac Math Sci, Dept Stat, Tehran, Iran

[4] Shahid Beheshti Univ Med Sci, Prevent Dent Res Ctr, Res Inst Dent Sci, Tehran, Iran

[5] Shahid Beheshti Univ Med Sci, Sch Allied Med Sci, English Language Dept, Tehran, Iran

来源：

EPIDEMIOLOGY BIOSTATISTICS AND PUBLIC HEALTH | 2019年 / 16卷 / 04期

关键词：

Bayesian analysis; Doubly inflated; DMFT data; Poisson regression; Random effects; MODELS;

D O I：

10.2427/13224

中图分类号：

R1 [预防医学、卫生学];

学科分类号：

1004 ; 120402 ;

摘要：

Outcome variables in clinical studies sometimes include count data with inflation in two points (usually zero and k (k>0)). Doubly inflated models can be adopted for modeling these types of data. In statistical modeling, the association among subjects due to longitudinal or cluster study designs is considered by random effects models. In this article, we proposed a doubly inflated random effects model using the Bayesian approach for correlated count data with inflation in two values, and compared this model with Bayesian zero-inflated Poisson and Bayesian Poisson models. The parameters' estimates by these models were obtained by Markov Chain Monte Carlo method using OpenBUGS software. Bayesian models were compared using the deviance information criterion. To this end, we utilized the total number of decayed, missed, and filled teeth of 12-year-old children and also conducted a simulation study. Results of real data and the simulation study revealed that the proposed model is fitted better than previous models.

引用

页数：11