Mia Carolina, NIM.: 18106010025 (2022) PERBANDINGAN MODEL GEOGRAPHICALLY WEIGHTED REGRESSION (GWR) DENGAN FUNGSI PEMBOBOT FIXED GAUSSIAN KERNEL DAN ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS: ANGKA KEMISKINAN DI PROVINSI PAPUA TAHUN 2020). Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.
|
Text (PERBANDINGAN MODEL GEOGRAPHICALLY WEIGHTED REGRESSION (GWR) DENGAN FUNGSI PEMBOBOT FIXED GAUSSIAN KERNEL DAN ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS: ANGKA KEMISKINAN DI PROVINSI PAPUA TAHUN 2020))
18106010025_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (3MB) | Preview |
|
Text (PERBANDINGAN MODEL GEOGRAPHICALLY WEIGHTED REGRESSION (GWR) DENGAN FUNGSI PEMBOBOT FIXED GAUSSIAN KERNEL DAN ADAPTIVE GAUSSIAN KERNEL (STUDI KASUS: ANGKA KEMISKINAN DI PROVINSI PAPUA TAHUN 2020))
18106010025_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (5MB) | Request a copy |
Abstract
Geographically Weighted Regression (GWR) is a development of the classical regression model that takes into account the influence of location (geography). The regression model produced by the GWR method can only be used for each observation location and has different parameter values at each location. Estimating parameters using the GWR method requires a weighting matrix that represents the location of the observed data. In this study, the weighting matrix used was obtained by applying the fixed gaussian kernel and adaptive gaussian kernel weighting functions to the poverty rate in Papua Province in 2020. These two weighting functions were chosen because in determining the weighted value the distance element used at each observation location has a continuous value. Therefore, it is hoped that this research can provide better analytical results. The initial step taken was to conduct data analysis using the Ordinary Least Square (OLS) method which minimizes the sum of the squared residuals. , which produces two significant independent variables. Then proceed with the analysis using the GWR method with a fixed gaussian kernel weighting function and an adaptive gaussian kernel. The best model is obtained by taking into account the largest R2 value and the smallest AIC value for each model with the help of the R 4.1.2 Programming Language software. The results of the analysis of the GWR model with the fixed gaussian kernel weighting function have an R2 value of 87,82% and an AIC of 159,53. Meanwhile, the GWR model with the adaptive gaussian kernel weighting function has an R2 value of 79,53% and an AIC of 171,77. Therefore, the best model for modeling the poverty rate in Papua Province in 2020 is the GWR model with a fixed gaussian kernel weighting function.
Item Type: | Thesis (Skripsi) |
---|---|
Additional Information: | Pembimbing: Mohammad Farhan Qudratullah, S.Si., M.Si |
Uncontrolled Keywords: | GWR, Fixed Gaussian Kernel, Adaptive Gaussian Kernel, R2, AIC, Kemiskinan |
Subjects: | Matematika AGAMA DAN KEMISKINAN |
Depositing User: | Muh Khabib, SIP. |
Date Deposited: | 15 Feb 2023 14:16 |
Last Modified: | 15 Feb 2023 14:16 |
URI: | http://digilib.uin-suka.ac.id/id/eprint/56278 |
Share this knowledge with your friends :
Actions (login required)
View Item |