|
|
| |
| Geographically Weighted Polynomial Regression: Application to Poverty Modeling in East Java Province, Indonesia |
Toha Saifudin, Fatmawati, Nur Chamidah
|
Abstract:
Geographically weighted regression (GWR) is a regression method for exploring spatial nonstationarity by allowing different relationships at different locations. In the GWR, the response at each location is locally fitted by a linear function of a set of explanatory variables. In fact, it may have nonlinear relationship with one or more explanatory variables. Thus, the GWR model may not be able to accommodate the fact. In dealing with the problem, we attempt to introduce a geographically weighted polynomial regression (GWPolR) model. In this study, the GWPolR model is performed to explore spatially varying relationships between poverty and its factors in East Java Province, Indonesia. The factors studied here are the percentage of people educated less than elementary school, the percentage of people aged at least 10 years who cannot read and write, and the percentage of people working in the trading sector. Factually, the first and third factors tend to have nonlinear relationships with the poverty. Compared with the previous models in such condition, the GWPolR model gives a significant improvement and more complete understanding of how each explanatory variable was related to the poverty. This should allow improved planning of poverty alleviation strategies.
|
|
|
| | |