Indrayani, A. Fahmi (2018) Pemodelan Seasonal Difference-Geographically and Temporally Weighted Regression (SD-GTWR) (Studi Kasus Demam Berdarah Dengue di kota Malang). Magister thesis, Universitas Brawijaya.
Abstract
Seasonal Differences - Geographically and Temporally Weighted Regression (SD-GTWR) modeling have been extended to evaluate the presence of spatial heterogeneity and temporal heterogeneity with respect to seasonal characteristics, so as to analyze the association between dengue hemorrhagic fever (DHF) and influencing factors spread in poor city , Indonesia. By using monthly data 2012-2015 as repeated observation for every urban village in Malang. The subdistricts are considered spatial and the monthly units are temporal units. The SD-GTWR model is compared with Geographically and Temporally Weighted Regression (GTWR) and Geographically Weighted Regression (GWR) models using two statistical criteria R2 and Root Means Square Error (RMSE). Model SD-GTWR Indicates that the relationship between the number of patients in each kelurahan with predictor variables has different results for each kelurahan and month, and is the best model compared to GTWR and GWR with R2 of 0.799 and RMSE of 0.91, This result has important consequences in policy making for regulation in the spread of DHF infection in certain areas.
English Abstract
Seasonal Difference - Geographically and Temporally Weighted Regression (SD-GTWR) pemodelan telah diperpanjang untuk mengevaluasi kehadiran heterogenitas spasial dan heterogenitas temporal dengan memperhatikan karakteristik musiman, sehingga dapat menganalisis hubungan antara demam berdarah dengue (DBD) dan factor - faktor yang mempengaruhi tersebar di kota Malang, Indonesia. Dengan menggunakan data bulanan 2012 - 2015 sebagai pengamatan berulang untuk setiap kelurahan di Malang. Kecamatan dianggap spasial dan unit bulanan adalah unit temporal. Model SDGTWR dibandingkan dengan model Geographically and Temporal Weighted Regression (GTWR) dan Geographically Weighted Regression (GWR) menggunakan dua kriteria statistic R2 dan Root Means Square Error (RMSE). Model SD-GTWR Menunjukkan bahwa hubungan antara jumlah pasien di setiap kelurahan dengan variable – variable predikor memiliki hasil yang berbeda untuk setiap kelurahan dan bulan, dan merupakan model terbaik dibandingkan GTWR dan GWR dengan R2 sebesar 0.799 dan RMSE sebesar 0.91, hasil ini memiliki konsekuensi penting dalam pembuatan kebijakan untuk regulasi dalam penyebaran infeksi DBD di daerah tertentu.
| Item Type: | Thesis (Magister) |
|---|---|
| Identification Number: | TES/519.24/SWA/m/2018/041804766 |
| Uncontrolled Keywords: | SPATIAL ANALYSIS ( statistics ), GEOGRAPHIC INFORMATION SYSTEMS, REGRESION ANALYSIS, GEOGRAPHY - STATISTICAL METHODS |
| Subjects: | 900 History, geography and auxiliary disciplines > 910 Geography and travel > 910.2 Miscellany; world travel guides > 910.28 Auxiliary techniques and procedures; apparatus, equipment, materials > 910.285 Computer applications |
| Divisions: | S2/S3 > Magister Statistika, Fakultas MIPA |
| Depositing User: | Nur Cholis |
| Date Deposited: | 20 Mar 2019 03:52 |
| Last Modified: | 20 Mar 2019 03:52 |
| URI: | http://repository.ub.ac.id/id/eprint/165661 |
Actions (login required)
 |
View Item |