Seasonal ARIMA forecasting of inbound air travel arrivals to Taiwan

Ching Fu Chen, Yu Hern Chang, Yu Wei Chang

Research output: Contribution to journalArticlepeer-review

44 Citations (Scopus)


This article uses the Holt-Winters method, the seasonal ARIMA (SARIMA) model, and the GM(1,1) grey forecasting model to replicate monthly inbound air travel arrivals to Taiwan and to compare the models' forecasting performance. It uses the mean absolute percent error (MAPE) for the measurement of forecast accuracy and implements turning point analysis (TPA) to compare the model performance between the direct and indirect forecast methods. Based on the out- of-sample forecasts, all fitted models have good forecasting performance in terms of the MAPE criterion, and the SARIMA model is the best one for forecasting inbound air travel arrivals to Taiwan. According to the TPA results, this article supports the out-performance of the indirect forecast method.

Original languageEnglish
Pages (from-to)125-140
Number of pages16
Issue number2
Publication statusPublished - 2009

All Science Journal Classification (ASJC) codes

  • Transportation
  • Engineering(all)


Dive into the research topics of 'Seasonal ARIMA forecasting of inbound air travel arrivals to Taiwan'. Together they form a unique fingerprint.

Cite this