Forecasting accuracy of vector autoregressive model and dynamic factor model for airline passenger traffic

The choice of appropriate forecasting technique for air transport business is quite challenging and requires comprehensive analysis of empirical results. This paper compares the forecasting accuracy of Vector Autoregressive (VAR) Model and Dynamic Factor Model(DFM)in the determination of air passenger traffic. The aim is to establish through statistical principles, which of the two models outperforms the other by: fitting multivariate time series models of VAR and DFM; comparing the forecasting accuracy of the models; and determining the appropriate model for forecasting monthly passenger flow. Monthly data from January 2015 to December 2019 were utilized for the comparison. The series are trend stationary at all levels based on standard Augmented Dickey Fuller (ADF) unit root tests. Each of these series is found to be integrated of order one [I (1)] on the bases of Akaike Information Criterion (AIC) and the Hannan-Quin information criterion (HQIC). The models were further diagnosed for residual autocorrelation and normality tests followed by models fitness. The results of MAPE, RMSE, and MAD show that values of these three statistics are lower for DFM than the corresponding values for VAR. This study therefore recommends the DFM as a better forecast model for air passenger traffic.

Andreoni, A. and Postorino, M.N. (2006). A multivariate ARIMA model to forecast air
transport demand. Paper presented at the association for European transport and
contributors 2006. http://abstracts.aetransport.org/paper/ download/id/2535
Banerjee, N., Morton, A. and Akartunali, K. (2020). Passenger demand forecasting in
scheduled transportation, European Journal of Operational Research, 286(3), 797 –
810.
Bahram, A., Richard, D.G. and Kambiz, R. (2002). The long –run dynamic equilibrium
between air carrier capacity and profitability, Journal of Applied Statistics,10(5), 566-
583.
Coshall, J. (2006). Time series analyses of UK outbound travel by air, Journal of Travel
Research, 44(3), 335–347.
Coshall, J. (2009). Combining volatility and smoothing forecasts of UK demand for
international tourism, Tourism Management, 30(4), 495–511.
Doz, C. and Fuleky, P. (2019). Dynamic factor models, Prepared for Macroeconomic
Forecasting in the Era of Big Data Theory and Practice, Springer.
https://halshs.archives-ouvertes.fr/halshs-02262202.
Emiray, E. and Rodriguez, G. (2003). Evaluating time series models in short and long-term
forecasting of Canadian air passenger, working papers 0306E, University of Ottawa,
Department of Economics.

Journal of the Nigerian Statistical Association, Vol. 34, 2022 Dike et al.
72
Fildes, R., Wei, Y. and Ismail S. (2011). Performance of econometric models of air passenger
traffic flows using multiple error measures, International Journal of Forecasting, 27(3)
902-922.
Ghomi, F. and Forghani, K. (2016). Airline passenger forecasting using neural networks and
Box-Jenkins, 12th International Conference on Industrial Engineering (ICIE), 10 – 13.
GRA Inc., (2001). Effects of airline industry changes on small-and non-hub airports, GRA,
Incorporated, 2000 Duke Street, Suite 300, Alexandria, VA 22314, USA.
Hashem, S.J. and Noor, A.I. (2007). The Determination of load factors in the airline industry,
International Review of Business Research Papers, 3(3), 189–197.
https://www.researchgate.net/publication/268390961.
Kulendran, N. and Witt, S. (2003). Forecasting the demand for international business tourism,
Journal of Travel Business Research, 41, 265-271.
Lim, C. and McAleer, M. (2001). Forecasting tourist arrivals, Annals of Tourism Research,
28(4), 965-977.
Lutkepohl, H. (2006). New introduction to multiple time series analysis, Springer, Berlin.
Miranda, K., Poncela, P. and Rutz, E. (2022). Dynamic factor models: Does the specification
matter? SERIEs Journal of the Spanish Economic Association, 13, 397-428.
https://doi.org/10.1007/s13209-021-00248-2
Poncela, P. and Ruiz, E. (2020). A Comment on the dynamic factor model with dynamic
factors, Economics Discussion Papers, No 2020-7, Kiel Institute for the World
Economy. http://www.economics-journal.org/economics/discussionpapers/2020-7
Srisaeng, P., Baxter, G., Richardson, S. and Wild, G. (2015). A forecast tool for predicting
Australia’s domestic airline passenger demand using a genetic algorithm, Journal of
Aerospace Technology and Management, 7, 476 – 489.
Saheed, A.A. and Iluno, S.Z.C. (2015). Air transportation development and economic growth
in Nigeria. Journal of Economics and Sustainable Development, 6(2), 1-2.
Soloman, T. and Sharma, M.K. (2020). Vector autoregression and vector error correction
models: application to Ethiopian airline data, International Journal of Statistics:
Advances in Theory and Applications, 1(2), 201 – 256.
Zivot, E. and Wang, J. (2003). Vector autoregressive model for multivariate time series, In:
Modeling Financial Time Series with S-Plus, Springer, New York, NY.
https://doi.org/10.1007/978-0-387-21763-5_11