Sama Circular Model on Forecasting Tourist Arrivals to Sri Lanka
Konarasinghe, W.G.S (2018). Sama Circular Model on Forecasting Tourist Arrivals to Sri Lanka. Proceedings of the International Conference on Advances in Pure & Applied Mathematics 2018, Madurai Kamaraj University, Madurai, Tamil Nadu, India. 19.
5 Pages Posted: 26 Jun 2019
Date Written: January 10, 2018
The Circular Model (CM) is univariate statistical technique, which is applied in modeling wave like patterns. Development of the CM was based on; Newton’s Law of Circular Motion, Fourier Transformation and Multiple Regression Analysis. Most important property of the CM is that; the model is capable in capturing both seasonal and cyclical patterns of a time series. However, applicability of the CM is restricted to trend free series. As such, the differencing technique was used to mitigate the limitation of the CM. The improved Circular Model, named as the "Sama Circular Model (SCM)” is tested on forecasting tourist arrivals to Sri Lanka. Time Series plots were used for pattern recognition. The Auto Correlation Functions of residuals and Ljung-Box Q statistics (LBQ) were used to test the independence of residuals. The Anderson Darling test was used to test the normality of residuals. Forecasting ability of the models was assessed by Mean Square Error and Mean Absolute Deviation. Forecasting ability of SCM was compared with the Decomposition models and Seasonal Auto Regressive Moving Average models. It is concluded that the SCM is capable in forecasting tourist arrivals to Sri Lanka and the SCM is superior to the other tested models for the purpose. It is recommended to test the SCM for various fields of study, such as; Agriculture, Meteorology, Economics, Finance etc. for optimum benefits.
Keywords: Circular Model, Fourier Transformation, Differencing
Suggested Citation: Suggested Citation