PEMODELAN PRODUKSI PADI DI INDONESIA DENGAN PENDEKATAN MIXED GEOGRAPHICALLY WEIGHTED REGRESSION

No Thumbnail Available

Date

2021-03

Journal Title

Journal ISSN

Volume Title

Publisher

Abstract

This paper discusses about rice production modeling in Indonesia with Mixed Geographically Weighted Regression (MGWR) approach. The MGWR model is a combination of multiple linear regression models and Geographically Weighted Regression (GWR), which model variables that are global and local. The estimated parameters of the MGWR model are obtained using the Weighted Least Square (WLS) method. The optimum bandwidth is selected by using the Cross Validation (CV) method. Rice production in Indonesia is influenced by factors such as harvest area, rainfall, fertilizer, and farmers. MGWR model produces variables of local nature is the area of harvest, while the variables that are global are rainfall, fertilizer and farmers. MGWR model is a best model used to model rice production data in Indonesia based on Akaike Information Criteria Corrected value

Description

Keywords

Rice production, Mixed Geographically Weighted Regression, Weighted Least Square, Cross Validation, Akaike Information Criterion Corrected

Citation

Collections