PEMODELAN GEOGRAPHICALLY WEIGHTED POISSON REGRESSION (GWPR) PADA FUNGSI PEMBOBOT ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS : FAKTOR-FAKTOR YANG MEMENGARUHI PENYAKIT TUBERKULOSIS MENURUT KABUPATEN/KOTA DI PROVINSI JAWA BARAT TAHUN 2022)

Wida Silvia Fikriyana, NIM.: 19106010014 (2024) PEMODELAN GEOGRAPHICALLY WEIGHTED POISSON REGRESSION (GWPR) PADA FUNGSI PEMBOBOT ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS : FAKTOR-FAKTOR YANG MEMENGARUHI PENYAKIT TUBERKULOSIS MENURUT KABUPATEN/KOTA DI PROVINSI JAWA BARAT TAHUN 2022). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (PEMODELAN GEOGRAPHICALLY WEIGHTED POISSON REGRESSION (GWPR) PADA FUNGSI PEMBOBOT ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS : FAKTOR-FAKTOR YANG MEMENGARUHI PENYAKIT TUBERKULOSIS MENURUT KABUPATEN/KOTA DI PROVINSI JAWA BARAT TAHUN 2022)) 19106010014_BAB-I_IV-atau-V_DAFTAR-PUSTAKA-1.pdf - Published Version Download (3MB) | Preview
	Text (PEMODELAN GEOGRAPHICALLY WEIGHTED POISSON REGRESSION (GWPR) PADA FUNGSI PEMBOBOT ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS : FAKTOR-FAKTOR YANG MEMENGARUHI PENYAKIT TUBERKULOSIS MENURUT KABUPATEN/KOTA DI PROVINSI JAWA BARAT TAHUN 2022)) 19106010014_BAB-II_sampai_SEBELUM-BAB-TERAKHIR-1.pdf - Published Version Restricted to Registered users only Download (4MB) | Request a copy

Abstract

The Geographically Weighted Poisson Regression (GWPR) model is a development of the poisson regression model applied to spatial data. This model is used to predict data with poisson response variables which are influenced by spatial factors. The data used in this research are factors that influence Tuberculosis according to Districts/Cities in West Java Province in 2022. This research will discuss the use of the GWPR model in the adaptive gaussian kernel weighting function, and the results will be compared with the poisson regression model. Estimation of GWPR parameters uses the Maximum Likelihood Estimation (MLE) method, and selection of optimum bandwidth uses Cross Validation (CV) criteria. The results of the GWPR model with adaptive gaussian kernel weighting are better than the Poisson regression model because it has the most optimal AIC, BIC and adjusted R2 values. Based on testing the parameters of the GWPR model, it can be concluded that the factors that influence the number of tuberculosis cases are varied and different in the 27 observation locations, including poor residents, households with PHBS, and population density

Share this knowledge with your friends :

Actions (login required)

View Item