Statistical modelling for prediction of rice production in Indonesia using semiparametric regression based on three forms of fourier series estimator

The primary food for Indonesian is rice. The rice production in Indonesia tends to decrease that influencing the increase of rice's price. The increase of rice's price has a big influence for inflation, like as noted by Indonesia Central Bureau of Statistics, in January 2018 inflation happened with rate 0,62% as the number 0,24% from increase of rice's price. Thus, the availability of rice must be controlled with make prediction for developing sustainable agriculture in Indonesia. In this study, we compared three forms of semiparametric regression method based on Fourier series estimator to make prediction of rice production for every province in Indonesia. The result is the best model for predict of rice production is modeled based on the best semiparametric regression based on Fourier cosine series estimator. The model met goodness criteria like the smallest MSE equals to 0,0000194 and the biggest determination coefficient near to 100%.