Open AccessApplication of Nonparametric Geographically Weighted Spline Regression Model for Spatial Mapping of Open Unemployment Rate in Kalimantan
Author(s) -
Sifriyani Sifriyani,
Hillidatul Ilmi,
Zakiyah Mar’ah
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2123/1/012038
Subject(s) - statistics , econometrics , regression analysis , nonparametric statistics , kernel density estimation , weighting , geography , mathematics , regression , nonparametric regression , medicine , estimator , radiology
This study was conducted specifically to GIS mapping based on Nonparametric-Geographically Weighted Spline Regression (NGWSR) Estimation Model for the factors that affect the open unemployment rate (OUR) in Kalimantan. Observational data in this study were categorized into 56 regions based on the Regency/City scale in Kalimantan. The variables used in this study consisted of the open unemployment rate, the labor force participation rate, population density, human development index, expected years of schooling, and regional minimum wage. This study utilized the spatial analysis of the NGWSR model with the geographic weighting of the Gaussian and Bisquare kernel functions. The NGWSR model was considered capable of providing a solution to the geographically weighted spatial regression for the unknown regression curve. Regarding to the result of this study, NGWSR with geographic weighting of the Bisquare kernel function was considered as the best model. The model criteria were based on the coefficient of determination and RMSE. The results of the significance test of model parameters for 56 Regencies/Cities data in Kalimantan had succeeded in mapping the area into 14 categories based on the significant variables of each region.