Beyond point forecasting: Evaluation of alternative prediction intervals for tourist arrivals

Jae Kim, Kevin Wong, George Athanasopoulos, Shen Liu

Research output: Contribution to journalArticleResearchpeer-review

Abstract

This paper evaluates the performances of prediction intervals generated from alternative time series models, in the context of tourism forecasting. The forecasting methods considered include the autoregressive (AR) model, the AR model using the bias-corrected bootstrap, seasonal ARIMA models, innovations state space models for exponential smoothing, and Harveya??s structural time series models. We use thirteen monthly time series for the number of tourist arrivals to Hong Kong and Australia. The mean coverage rates and widths of the alternative prediction intervals are evaluated in an empirical setting. It is found that all models produce satisfactory prediction intervals, except for the autoregressive model. In particular, those based on the bias-corrected bootstrap perform best in general, providing tight intervals with accurate coverage rates, especially when the forecast horizon is long.
Original languageEnglish
Pages (from-to)887 - 901
Number of pages15
JournalInternational Journal of Forecasting
Volume27
Issue number3
DOIs
Publication statusPublished - 2011

Cite this

@article{2aa5f47dd5fa4c818494f10ee0a38a3a,
title = "Beyond point forecasting: Evaluation of alternative prediction intervals for tourist arrivals",
abstract = "This paper evaluates the performances of prediction intervals generated from alternative time series models, in the context of tourism forecasting. The forecasting methods considered include the autoregressive (AR) model, the AR model using the bias-corrected bootstrap, seasonal ARIMA models, innovations state space models for exponential smoothing, and Harveya??s structural time series models. We use thirteen monthly time series for the number of tourist arrivals to Hong Kong and Australia. The mean coverage rates and widths of the alternative prediction intervals are evaluated in an empirical setting. It is found that all models produce satisfactory prediction intervals, except for the autoregressive model. In particular, those based on the bias-corrected bootstrap perform best in general, providing tight intervals with accurate coverage rates, especially when the forecast horizon is long.",
author = "Jae Kim and Kevin Wong and George Athanasopoulos and Shen Liu",
year = "2011",
doi = "10.1016/j.ijforecast.2010.02.014",
language = "English",
volume = "27",
pages = "887 -- 901",
journal = "International Journal of Forecasting",
issn = "0169-2070",
publisher = "Elsevier",
number = "3",

}

Beyond point forecasting: Evaluation of alternative prediction intervals for tourist arrivals. / Kim, Jae; Wong, Kevin; Athanasopoulos, George; Liu, Shen.

In: International Journal of Forecasting, Vol. 27, No. 3, 2011, p. 887 - 901.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Beyond point forecasting: Evaluation of alternative prediction intervals for tourist arrivals

AU - Kim, Jae

AU - Wong, Kevin

AU - Athanasopoulos, George

AU - Liu, Shen

PY - 2011

Y1 - 2011

N2 - This paper evaluates the performances of prediction intervals generated from alternative time series models, in the context of tourism forecasting. The forecasting methods considered include the autoregressive (AR) model, the AR model using the bias-corrected bootstrap, seasonal ARIMA models, innovations state space models for exponential smoothing, and Harveya??s structural time series models. We use thirteen monthly time series for the number of tourist arrivals to Hong Kong and Australia. The mean coverage rates and widths of the alternative prediction intervals are evaluated in an empirical setting. It is found that all models produce satisfactory prediction intervals, except for the autoregressive model. In particular, those based on the bias-corrected bootstrap perform best in general, providing tight intervals with accurate coverage rates, especially when the forecast horizon is long.

AB - This paper evaluates the performances of prediction intervals generated from alternative time series models, in the context of tourism forecasting. The forecasting methods considered include the autoregressive (AR) model, the AR model using the bias-corrected bootstrap, seasonal ARIMA models, innovations state space models for exponential smoothing, and Harveya??s structural time series models. We use thirteen monthly time series for the number of tourist arrivals to Hong Kong and Australia. The mean coverage rates and widths of the alternative prediction intervals are evaluated in an empirical setting. It is found that all models produce satisfactory prediction intervals, except for the autoregressive model. In particular, those based on the bias-corrected bootstrap perform best in general, providing tight intervals with accurate coverage rates, especially when the forecast horizon is long.

U2 - 10.1016/j.ijforecast.2010.02.014

DO - 10.1016/j.ijforecast.2010.02.014

M3 - Article

VL - 27

SP - 887

EP - 901

JO - International Journal of Forecasting

JF - International Journal of Forecasting

SN - 0169-2070

IS - 3

ER -