COMPARISON OF SPATIAL AUTOREGRESSIVE (SAR) AND GEOGRAPHICALLY WEIGHTED REGRESSION (GWR) BASED ON SIMULATION STUDY

Hilda Venelia, 2027031011 (2022) COMPARISON OF SPATIAL AUTOREGRESSIVE (SAR) AND GEOGRAPHICALLY WEIGHTED REGRESSION (GWR) BASED ON SIMULATION STUDY. Masters thesis, Universitas Lampung.

[img]
Preview
File PDF
1. ABSTRACT.pdf

Download (4Kb) | Preview
[img] File PDF
2. FULL THESIS.pdf
Restricted to Hanya staf

Download (3281Kb)
[img]
Preview
File PDF
3. FULL THESIS WITHOUT RESULT AND DISCUSSION.pdf

Download (1778Kb) | Preview

Abstrak

Spatial regression is an analysis that evaluates the relationship between one variable and several other variables that have spatial effects on several locations. There are two basic spatial concepts, namely spatial dependency and spatial heterogeneity. There are supervised learning techniques for regression that model spatial dependency, one of them is Spatial Autoregressive (SAR). In contrast to SAR, Geographically Weighted Regression (GWR) is a spatial regression method commonly used in data containing spatial heterogeneity. This study will compare which method is better between SAR and GWR for modeling spatial data if the data contains both spatial aspects, namely spatial dependency and spatial heterogeneity using simulation study. The simulation results of this study, based on bias, MSE and AIC of each model, it has been obtained that the SAR method is better than the GWR method for modeling data containing these two spatial aspects (spatial dependency and heterogeneity).

Jenis Karya Akhir: Tesis (Masters)
Subyek: 500 ilmu pengetahuan alam dan matematika > 510 Matematika
Program Studi: FAKULTAS MIPA > Prodi Magister Ilmu Matematika
Pengguna Deposit: 2203564086 . Digilib
Date Deposited: 12 Aug 2022 00:29
Terakhir diubah: 12 Aug 2022 00:29
URI: http://digilib.unila.ac.id/id/eprint/64628

Actions (login required)

Lihat Karya Akhir Lihat Karya Akhir