Forecasting accuracy evaluation of tourist arrivals

This paper evaluates the use of several parametric and nonparametric forecasting techniques for predicting tourism demand in selected European countries. We find that no single model can provide the best forecasts for any of the countries in the short-, medium- and long-run. The results, which are tested for statistical significance, enable forecasters to choose the most suitable model (from those evaluated here) based on the country and horizon for forecasting tourism demand. Should a single model be of interest, then, across all selected countries and horizons the Recurrent Singular Spectrum Analysis model is found to be the most efficient based on lowest overall forecasting error. Neural Networks and ARFIMA are found to be the worst performing models.     

Asymmetric effects of tourist arrivals on the hospitality industry

This study makes a unique contribution to the hospitality literature by examining the asymmetric effects of total tourist arrivals in six segments of tourist arrivals (pleasure, business, visiting relatives, conference, study, and others) on Taiwan’s hospitality industry. Regression test results confirm that the contribution of the overall tourist arrivals and both pleasure and visiting relatives segments to hospitality industry growth is not asymmetric, as it is found in periods of expansion and contraction. The beneficial effect of the business segment on hospitality industry growth is asymmetric, existing only in periods of business cycle expansion. However, the conference, study, and other segments make no significant contribution to hospitality industry growth. The study’s valuable policy implications offer guidance to Taiwan’s tourism authorities, hospitality business owners, and managers.     

Dynamic relationships between tourist arrivals,immigrants, and crimes in the United States

This paper investigates the dynamic relationships between tourist arrivals, immigrants, and crimes in the United States (U.S.) from 1984 to 2013. Our findings affirm the social structural perspectives (i.e. Merton's Strain theory and Social Disorganization theory), which contain a popular perception about the immigration and crime that they both go hand in hand. Results of bivariate analysis revealed that immigrants admitted by Europe, Mexico, and North America to U.S. are positively correlated with key crimes. Tourist arrivals positively influence crime rate only in short-run, which affirms the Opportunity Structural perspectives (i.e. Routine Activity and Hot Spot theories). Furthermore, immigrants positively influence tourist arrivals, which supports the Visiting Friends and Relatives (VFR) empirical perspective. Therefore, concerned authorities can focus on environmental design initiative in concerned areas (i.e. immigrants' communities and tourists' cities). Furthermore, future research and implications are discussed.     

Analysis of international tourist arrivals in China: The role of World Heritage Sites

This paper analyzes the determinants of international tourist arrivals in China, especially for World Heritage Sites and various kinds of travel spots. Utilizing annual provincial panel data over the 2000–2005 period, the empirical results suggest that key determinants include the relative income, population in the original country, cost of travel, and tourism infrastructure. In addition, World Heritage Sites are also found to be significant in explaining the numbers of international tourists and have a greater tourist-enhancing effect. Other famous tourist sites rated 4A- and 3A-class are also attractive to foreign tourism. Moreover, cultural rather than natural sites attract more interest among foreign tourists, because China is internationally renowned for its long-standing historical and cultural assets. Finally, the importance of the determinants of the demand for tourism varies from country to country.     

Dynamic relationships among tourist arrivals,crime rate,and macroeconomic variables in Taiwan

This article uses Granger causality test and multivariate threshold model’s causality to test the existence of dynamic nonlinear relationship among tourist arrival, the crime rate, and macroeconomic variables 2001–2016 in Taiwan. The empirical result shows that tourist arrival has a negative effect on the crime rate and there is two-way causality between the exchange rate and tourist arrival. Where the CPI or the exchange rate as the threshold variables in the multivariate threshold model, the Regime 1 and linear results are same, but the Regime 2 results are different, which shows that not all variables have the same dynamic relation.     

Forecasting tourism demand with denoised neural networks

The automated Neural Network Autoregressive (NNAR) algorithm from the forecast package in R generates sub-optimal forecasts when faced with seasonal tourism demand data. We propose denoising as a means of improving the accuracy of NNAR forecasts via an application into forecasting monthly tourism demand for ten European countries. Initially, we fit NNAR models on both raw and denoised (with Singular Spectrum Analysis) tourism demand series, generate forecasts and compare the results. Thereafter, the denoised NNAR forecasts are also compared with parametric and nonparametric benchmark forecasting models. Contrary to the deseasonalising hypothesis, we find statistically significant evidence which supports the denoising hypothesis for improving the accuracy of NNAR forecasts. Thus, it is noise and not seasonality which hinders NNAR forecasting capabilities.