Application of Negative Binomial Regression Model in West Java Tourism

Abstract

Tourism is the most important sector for potential areas. One province in Indonesia that has quite potential is West Java. To be able to increase this potential, it is necessary to increase the number of tourists. This research aims to increase the number of visitors through several factors that are thought to be influential, namely the number of star hotels, number of stalls, and number of restaurants. The method used to determine the relationship between the number of visitors and these factors is regression. Because the research data is in the form of count data, it uses the Poisson distribution. If the data indicates overdispersion, it can be modeled using a Negative Binomial regression model as a comparison. The results obtained state that the Negative Binomial regression model is better than the Poisson regression model. Using the Negative Binomial regression model, it is found that increasing the number of tourists can be achieved by increasing the number of star hotels and number of restaurants. However, the number of stalls must be reduced so that visitors can increase. Thus, the aspect that must be addressed is to disband illegal stalls and increase the number of hotels and restaurants.