ANALISIS KEMISKINAN DI JAWA TIMUR MENGGUNAKAN MODEL CONDITIONAL AUTOREGRESSIVE (CAR)

Abstract

ABSTRACT

Poverty is one of the biggest problems in Indonesia. An approach to overcome this problem is determining the factors that affect poverty usually using ordinary least square regression model. This research aims at answering the question as to what are the factors of poverty in East Java, Indonesia. The research shows that poverty is not only influenced by explanatory variables but poverty is also influenced by surrounding locations. Therefore, this research employed spatial autoregressive models, conditional autoregressive (CAR). Spatial weighting matrix used in this study is the contiguity matrix. The statistics used for selection criteria model are the Akaike Information Criterion (AIC), the significancy of coefficient regression and variance parameters. The purposes of this research are to find the factors of poverty as well as to map the hotspot of poverty. The results show that they have same quality for spatial autoregressive models. The factors that affect poverty are the percentage of people who did not complete primary school (SD), the percentage of people who drink unclean water, and the percentage of people that get health insurance, the percentage of people that get subsidized rice, and the percentage of people that have poverty letter from local government. The Location Interaction Spatial Analysis (LISA ) shows the hotspot of poverty on the island of Madura in East Java.

KeyWords: Poverty, Conditional Autoregressive (CAR) and Local Indicator of Spatial Association (LISA)