A comparison of count data models with an application to daily cigarette consumption of young persons


Tuzen M. F. , Erbas S.

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, vol.47, no.23, pp.5825-5844, 2018 (Journal Indexed in SCI) identifier identifier

  • Publication Type: Article / Review
  • Volume: 47 Issue: 23
  • Publication Date: 2018
  • Doi Number: 10.1080/03610926.2017.1402050
  • Title of Journal : COMMUNICATIONS IN STATISTICS-THEORY AND METHODS
  • Page Numbers: pp.5825-5844
  • Keywords: Count data, cigarette consumption, negative binomial regression, Poisson regression, zero-inflated, POISSON REGRESSION, HURDLE MODELS, SELECTION, ZEROS, SMOKING

Abstract

The objective of this study is providing a comparative assessment for researchers to deal with the challenges of analyzing count data and examining the factors associated with daily cigarette consumption among the young people in Turkey. We fitted Poisson (P), negative binomial (NB), zero-inflated Poisson (ZIP), zero-inflated negative binomial (ZINB), Poisson hurdle (PH) and negative binomial hurdle (NBH) regressions to cigarette consumption count data by using the 2014 Turkey Health Survey. Our results showed that the ZINB and NBH models should be preferred. We also found that, gender, employment and tobacco use at home are more effective factors for smokers and nonsmokers in the 15-24 age group in Turkey.