A comparative study of univariate forecasting methods for predicting tuberculosis incidence on human

The negative impact of zoonosis has stimulated study into a prediction system that able to estimate the future number of zoonosis, especially in human being. Zoonosis refers to any infectious disease that is able to be transmitted from animals to humans. This empirical paper compares three univariate methods for zoonosis forecasting up to one year. Regression analysis, decomposition, and Holt-Winter's were selected as the simple and quick techniques for this purpose. The methods were compared using a time series of monthly number for tuberculosis incidence in human. Different error measures were used to determine the best model among them. It was found that the Holt-Winter's method produced better prediction than the rest of the methods with MAPE was 6.301 and Theil U value was 0.037.