Analysis of tourism demand serial dependence structure for forecasting
This study aims to extend knowledge of serial dependence structure in tourism demand modelling and make a contribution to tourism forecasting with the use of copula method. Analysis of serial dependence can reveal the impact of current tourism demand on the future. This is important for tourism dema...
Saved in:
| Main Authors: | , , , |
|---|---|
| 其他作者: | |
| 格式: | Article |
| 語言: | English |
| 出版: |
2017
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/86535 http://hdl.handle.net/10220/44037 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | This study aims to extend knowledge of serial dependence structure in tourism demand modelling and make a contribution to tourism forecasting with the use of copula method. Analysis of serial dependence can reveal the impact of current tourism demand on the future. This is important for tourism demand forecasting, as the prediction of future tourism demand relies highly on the historical demand information. However, serial dependence, especially its structure, has received very little attention in previous tourism research. The copula method is flexible as it provides various functions to specify different serial dependence structures and allows arbitrary distributions of tourism demand. We used five types of copulas to analyse two-dimensional serial dependence structure for 10 arrivals series to Singapore. The empirical findings show that serial dependence structures of arrivals can be non-linear. Additionally, the Student-t copula generates forecasts of tourism demand with higher accuracy than the autoregressive integrated moving average (ARIMA) and seasonal ARIMA models. |
|---|