MODEL GEOGRAPHICALLY WEIGHTED PANEL REGRESSION (GWPR) DENGAN FUNGSI KERNEL FIXED GAUSSIAN PADA INDEKS PEMBANGUNAN MANUSIA DI JAWA TIMUR

Abstract

The Geographically Weighted Panel Regression (GWPR) model is a com-
bination of panel data and GWR. The GWPR model is a development of the global
regression model where ideas are taken from non-parametric regression. This model is a
linear regression model that is local (local linear regression) which produces an estima-
tor of the model parameters that affects local for each point or location where the data
is collected. The purpose of this study is form a GWPR model with a fixed gaussian
kernel weighting function in overcoming the problem of spatial effects and geographical
factors that affect an area to another region. The data used in this study is secondary
data taken from the Central Statistics Agency (BPS) website consisting of the Human
Development Index in East Java 2013-2016. This study produces data for the making of
the Human Development Index using the GWPR method in the formation of the model,
where the coefficient of determination generated is 98,74%.Factors that increase HDI es-
pecially Mojokerto Regency are average length of school (RLS), life expectancy (AHH),
and the construction expensiveness index (IKK).

Keywords: GWPR, Fixed Gaussian, Human Development Index, East Java.