It is a method employed in the analysis of categorical data. Multinomial probit regression can be utilized when the dependent variable has more than two categories. If assumption of independence of irrelevant alternatives is unavailable for the multinomial logistic regression model, the alternative multinomial probit regression model is recommended.
Published in Chapter:
Investigation of Alcohol Consumption Determinants in Turkey With Multinomial Probit Model
Ömer Alkan (Atatürk University, Turkey) and İkram Yusuf Yarbaşı (Erzurum Technical University, Turkey)
Copyright: © 2020
|Pages: 28
DOI: 10.4018/978-1-5225-9787-2.ch008
Abstract
The main objective of this study is to determine key factors that may have a significant effect on alcohol consumption in Turkey. For this purpose, the cross-sectional data obtained from the Turkish Health Survey conducted in 2010 and 2012 by the Turkish Statistical Institute were analyzed through the multinomial probit model. Results revealed that several key variables were found to be a significant determinant of alcohol consumption, such as gender, age, education, marital status, income, general health status, tooth brushing frequency, situation of violence, fruit consumption frequency, tobacco use, exposure to tobacco smoke, and survey year. It is apparent that alcoholics need help to get rid of an addiction. Therefore, it would be inevitable for governments to intervene through national and international public health authorities. In particular, the ability of governments to design and implement comprehensive prevention strategies that combine the strengths of different policy approaches is critical to success.