Appropriate statistical model for zero-inflated count data: simulation based study

Ayan Chowdhury () and Soma Chowdhury Biswas ()
Additional contact information
Ayan Chowdhury: Department of Statistics, University of Chittagong, Bangladesh
Soma Chowdhury Biswas: Department of Statistics, University of Chittagong, Bangladesh

Computational Methods in Social Sciences (CMSS), 2018, vol. 6, issue 1, 5-12

Abstract: Zero-inflated count data is easily reached in real field. Over-dispersion is the consequence of zero inflation in count data. For modeling this kind of count data, several zero adjusted models such as Zero Inflated Poisson, Zero Inflated Negative Binomial, Hurdle Poisson and Hurdle Negative Binomial models are more suitable than basic statistical models. The best zero adjusted model selection is the key aim of this research. In this study, R code has been used to simulate datasets as well as to compare these models based on Akaike information criterion, Bayesian information criterion and Vuong test. The result of this study suggests that Hurdle Negative Binomial model has been preferred as the best fitted model for count data with excess of zero.

Keywords: Hurdle model; Simulation; Vuong test; Zero-inflated model. (search for similar items in EconPapers)
Date: 2018
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://cmss.univnt.ro/wp-content/uploads/vol/split ... _issue_1_art.001.pdf First version, 2018 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ntu:ntcmss:vol6-iss1-5-12

Access Statistics for this article

Computational Methods in Social Sciences (CMSS) is currently edited by Bogdan Oancea

More articles in Computational Methods in Social Sciences (CMSS) from "Nicolae Titulescu" University of Bucharest, Faculty of Economic Sciences Contact information at EDIRC.
Bibliographic data for series maintained by Stefan Ciucu ( this e-mail address is bad, please contact ).