eprintid: 59649
rev_number: 12
eprint_status: archive
userid: 12460
dir: disk0/00/05/96/49
datestamp: 2023-07-07 01:37:19
lastmod: 2023-07-07 01:37:19
status_changed: 2023-07-07 01:37:19
type: thesis
metadata_visibility: show
contact_email: muh.khabib@uin-suka.ac.id
creators_name: Silvy Mumayya, NIM.: 19106010039
title: PEMODELAN GEOGRAPHICALLY WEIGHTED REGRESSION DAN MIXED GEOGRAPHICALLY WEIGHTED REGRESSION DENGAN FUNGSI PEMBOBOT GAUSSIAN KERNEL  (STUDI KASUS: FAKTOR-FAKTOR YANG MEMENGARUHI INDEKS PEMBANGUNAN MANUSIA PADA SETIAP KABUPATEN/KOTA PROVINSI JAWA BARAT TAHUN 2021)
ispublished: pub
subjects: Matematika
divisions: jur_mat
full_text_status: restricted
keywords: RUNTUN WAKTU, MULTIVARIAT, NEURAL NETWORK, 
GWR, MGWR, Fixed Gaussian, Adaptive Gaussian, WLS, AIC, IPM
note: Pembimbing: Mohammad Farhan Qudratullah, S.Si., M.Si.
abstract: The Geographically Weighted Regression (GWR) model is a development of the global regression model to address the problem of spatial heterogeneity. The resulting parameter estimates are local at each observation location. In testing the parameters of the GWR model, variables are sometimes found that have no effect locally, causing the development of the GWR model to become a Mixed Geographically Weighted Regression (MGWR) model.
The MGWR model is a combined modeling of global regression and GWR with the results of parameter estimates that are local and some are global at each observation location. The estimation of GWR and MGWR model parameters uses the Weighted Least Square (WLS) method by assigning weights to each observation location. The spatial weights used are fixed gaussian and adaptive gaussian kernels, selecting the optimum bandwidth using the Cross Validation (CV) method and measuring the goodness of the model using the Akaike Information Criterion (AIC).
This study discusses GWR and MGWR modeling on human development index data in West Java Province in 2021. Based on the GWR modeling testing process that is better than the MGWR model, the GWR model with adaptive gaussian kernel weights has the most optimum AIC value of 8.870221. The factors that influence HDI vary locally in each observation including the number of schools, the rate of population growth, the percentage of poor people, the open unemployment rate and the percentage of gross regional domestic product growth.
date: 2023-05-19
date_type: published
pages: 150
institution: UIN SUNAN KALIJAGA YOGYAKARTA
department: FAKULTAS SAINS DAN TEKNOLOGI
thesis_type: skripsi
thesis_name: other
citation:   Silvy Mumayya, NIM.: 19106010039  (2023) PEMODELAN GEOGRAPHICALLY WEIGHTED REGRESSION DAN MIXED GEOGRAPHICALLY WEIGHTED REGRESSION DENGAN FUNGSI PEMBOBOT GAUSSIAN KERNEL (STUDI KASUS: FAKTOR-FAKTOR YANG MEMENGARUHI INDEKS PEMBANGUNAN MANUSIA PADA SETIAP KABUPATEN/KOTA PROVINSI JAWA BARAT TAHUN 2021).  Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.   
document_url: https://digilib.uin-suka.ac.id/id/eprint/59649/1/19106010039_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf
document_url: https://digilib.uin-suka.ac.id/id/eprint/59649/2/19106010039_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf