METODE REGRESI TRANSFORMASI LOGARITMIK NATURAL PADA VARIABEL NILAI EKSPOR DI PROVINSI RIAU

Abstract

Riau's export is dominated by non-oil and gas, especially in agriculture. Export in agriculture is a commodity of crude palm oil and its derivatives. Natural rubber is also one of the export commodities in Riau Province. The factors tested in this study are plantation sectors that become export commodities such as the amount of palm oil production, the amount of dry rubber production, and other factors namely foreign exchange rates. The method used is the logarithmic transformation regression method. In the evaluation of the forecasting results used mape value (Mean Absolute Percentage Error). The MAPE value in the multiple regression method is 46.91366 %, and the MAPE value on the regression method is multiple with a logarithmic transformation of the response variable of 52.69479%. The smaller the MAPE value, the smaller the forecast error rate. At the level of forecasting error that multiple regression is better than multiple regression with logarithmic transformation of the response variable