Predict Farmer Exchange Rate in the Food Crop Sector Using Principal Component Regression

Abstract

Farmer Exchange Rate (FER) in Indonesia is very concerning. According to BPS data, there are various regions that experience increases and decreases every year. The goal of this paper is to predict Farmer Exchange Rate in the food crop sector using Principal Component Regression (PCR) since there is multicollinearity in the data. Therefore, with the PCR method using data based on 33 different provinces in Indonesia can determine the Farmer Exchange Rate with supporting factors. The model used can help farmers to be able to improve the welfare and economic growth of Indonesia as it depends on farmers. Further analysis found that the Harvest Area, production, and Human Development Index had an effect on farmer exchange rate. By using this model, it is expected that farmers in Indonesia have an increasing level of welfare and solve multicollinearity problem.