Corresponding Author

Darol Arkum, darolarkumugm@gmail.com, Institut Pahlawan 12

Year

2025

Abstract

ABSTRACT

Introduction: A strategic method of evaluating the economic impact of tourism across regions while taking into consideration Indonesia's geographical and socioeconomic diversity is to divide tourist destinations according to the reasons for travel. Background Problems: This study introduces an integrated statistical framework to assess the economic impact of domestic tourism in Indonesia, emphasizing regional heterogeneity and evolving travel behavior. Research Methods: A novel clustering approach is developed based on travel motivations—rather than geographical proximity—utilizing hierarchical clustering in conjunction with time series analysis and ANOVA techniques. The time series analysis identifies pronounced seasonal trends and fluctuations in spending, influenced significantly by macroeconomic shocks such as the COVID-19 pandemic. Furthermore, ANOVA and Tukey HSD post-hoc tests reveal statistically significant temporal and spatial variations in average tourism expenditures. Novelty: This study focus focus on Indonesia emphasizes domestic tourism in Indonesia and the use of both econometric and cluster analysis to study domestic tourism is relatively unique. Most studies may focus on one approach, but integrating these two allows for a more comprehensive understanding—econometrics identifies causal relationships, while clustering reveals patterns among regions, which caused variations in visitor spending and arrivals. This study includes data from recent years (before and after COVID-19), it may provide fresh insights into how domestic tourism has adapted to new economic and social realities. Finding: According to the ANOVA results, average spending varies significantly between provinces and time periods; the highest average spending was found in Bali, DKI Jakarta, and DI Yogyakarta. In the meantime, regional clustering is carried out using two primary criteria: the quantity of visitors and their spending. The clustering results effectively pinpoint groups of provinces with diverse visitor patterns, which are also connected to regional macroeconomic indicators like the GRDP contribution of the tourism industry, fiscal capacity, and the provinces economic reliance on tourism. These results indicate that the economic impact of tourism is distributed differently across different regions and raise the possibility of imbalances in sectoral growth. Novelty: Conclusion: The policy implications highlight the importance of resource allocation strategies based on clusters, differentiated destination marketing, and infrastructure development tailored to the needs of each segment. This study offers empirical support for data-driven, inclusive, and equitable, sustainable regional economic growth-oriented planning of domestic tourism development.


Keywords:

keywords: impact; tourism; economic; social; econometric; cluster

Download

Share

COinS
 

Assessing The Impact of Economic and Social Dynamics on Domestic Tourism in Indonesia: An Econometric and Cluster Analysis

ABSTRACT

Introduction: A strategic method of evaluating the economic impact of tourism across regions while taking into consideration Indonesia's geographical and socioeconomic diversity is to divide tourist destinations according to the reasons for travel. Background Problems: This study introduces an integrated statistical framework to assess the economic impact of domestic tourism in Indonesia, emphasizing regional heterogeneity and evolving travel behavior. Research Methods: A novel clustering approach is developed based on travel motivations—rather than geographical proximity—utilizing hierarchical clustering in conjunction with time series analysis and ANOVA techniques. The time series analysis identifies pronounced seasonal trends and fluctuations in spending, influenced significantly by macroeconomic shocks such as the COVID-19 pandemic. Furthermore, ANOVA and Tukey HSD post-hoc tests reveal statistically significant temporal and spatial variations in average tourism expenditures. Novelty: This study focus focus on Indonesia emphasizes domestic tourism in Indonesia and the use of both econometric and cluster analysis to study domestic tourism is relatively unique. Most studies may focus on one approach, but integrating these two allows for a more comprehensive understanding—econometrics identifies causal relationships, while clustering reveals patterns among regions, which caused variations in visitor spending and arrivals. This study includes data from recent years (before and after COVID-19), it may provide fresh insights into how domestic tourism has adapted to new economic and social realities. Finding: According to the ANOVA results, average spending varies significantly between provinces and time periods; the highest average spending was found in Bali, DKI Jakarta, and DI Yogyakarta. In the meantime, regional clustering is carried out using two primary criteria: the quantity of visitors and their spending. The clustering results effectively pinpoint groups of provinces with diverse visitor patterns, which are also connected to regional macroeconomic indicators like the GRDP contribution of the tourism industry, fiscal capacity, and the provinces economic reliance on tourism. These results indicate that the economic impact of tourism is distributed differently across different regions and raise the possibility of imbalances in sectoral growth. Novelty: Conclusion: The policy implications highlight the importance of resource allocation strategies based on clusters, differentiated destination marketing, and infrastructure development tailored to the needs of each segment. This study offers empirical support for data-driven, inclusive, and equitable, sustainable regional economic growth-oriented planning of domestic tourism development.