A comparison of Montecarlo linear and dynamic polynomial regression in predicting dengue fever case
Mochammad Choirur Roziqin, Achmad Basuki, Tri Harsono · 2016
A prediction of dengue fever cases by using a predictor of rainfall, the rain days, the house index, and the larva-free number has been done in Jember Regency. The evaluation was done by comparing and calculating the deviation value of the predicted number of cases, as a result of the prediction, to the number of actual cases. This prediction simulation of the number of dengue fever cases is using two regression methods, those are Montecarlo linear regression and dynamic polynomial regression. The MSE (mean square error) test was done to find out which regression is the best in predicting dengue fever cases. The data processing result of the two regressions shows that the polynomial dynamic is able to predict well as compared to Montecarlo linear regression, with error level up to 1%.