Tag Archives: SARIMA

Application of SARIMA Model and Simple Seasonal Exponential Smoothing on Diabetes Mellitus: A Case of Enugu State Teaching Hospital, Nigeria (Published)

This paper aims at obtaining better model between seasonal ARIMA and simple seasonal exponential smoothing that will be used for forecasting number of diabetes patients in a given hospital. Monthly dataset from January 2009 to December 2019 from Enugu State Teaching Hospital was used for this research. Seasonal ARIMA was modelled using the techniques of Box-Jenkins, and simple seasonal exponential smoothing modelled using the least squares method. Bayesian Information Criterion (BIC) was employed to obtain the best seasonal ARIMA model, while the Theil’s U statistics and MAPE were used to obtain the best forecast model. ARIMA (1,1,2)(0,0,0)12 was selected as the best SARIMA model with the BIC of 7.873, and  simple seasonal exponential  smoothing was considered  the best forecast model with a Theil’s U Statistic of  0.11241 and MAPE of 23.450. The fitted model was used to make out-sample forecast for the period January 2020-December 2025. The fitted model in this findings will help Enugu state government to plan efficiently, expand public sensitization, and allocate adequate resources for emergencies.

Citation: Christogonus Ifeanyichukwu Ugoh, Anyadiegwu Chinelo Ujunwa, Thomas Chinwe Urama, Ugwu Gibson Chiazortam (2022) Application of SARIMA Model and Simple Seasonal Exponential Smoothing on Diabetes Mellitus: A Case of Enugu State Teaching Hospital, Nigeria, European Journal of Statistics and Probability, Vol.10, No.1, pp., 21-32

Keywords: BIC, Diabetes Mellitus, MAPE, SARIMA, Simple Seasonal Exponential Smoothing, Theil’s U Statistic

A Suggested Approach to Artificial Neural Networks Modeling of Time Series (Published)

This research proposed a method of selecting an optimal combination of numbers of input (number of lagged values in the model) and of hidden nodes for modeling seasonal data using Artificial Neural Networks (ANN). Three data sets (rainfall, relative humidity and solar radiation) were used in assessing the proposed procedure and the resulting ANN models were compared with two traditional models (Holt-Winter’s and SARIMA). Models with large number of lagged values have shown tendency to outperform those with small number of lagged values. Selected ANN model was found to outperform the two traditional models on rainfall data; it performed better than SARIMA but worse than Holt-Winter’s model on relative humidity data and performed worse than the two methods on solar radiation data. The proposed procedure has hence, performed fairly well. Oscillatory performance recorded by ANN models that resulted from the proposed procedure in relation to the other two models only attests to the fact that no particular model is best on every data set. Rather than insist on elegance or sophistication, researchers should be guided by parsimony.

Keywords: Artificial Neural Networks, Forecasting, SARIMA, holt-winter, seasonal data