Shara, Yoeniarti (2013) Pemodelangeographically Weighted Regression Dengan Pembobot Fixed Bisquare Kernel Pada Data Spasial (Studi Kasus Balita Gizi Buruk di Provinsi Jawa Timur Tahun 2008). Sarjana thesis, Universitas Brawijaya.
Abstract
Geographically Weighted Regression (GWR) adalah metode regresi linier yang diberi bobot lokasi. Data spasial memiliki referensi ruang kebumian (koordinat geografis) sehingga metode pendugaan Ordinary Least Square (OLS) tidak tepat. Salah satu metode pendugaan parameter model GWR menggunakan metode pendugaan berbobot berupa titik koordinat lokasi yaitu Weighted Least Square (WLS). Penelitian ini bertujuan untuk menduga parameter dan memodelkan data Kejadian Balita Gizi Buruk Provinsi Jawa Timur Tahun 2008 dengan pembobot Fixed Bisquare Kernel. Peubah prediktor adalah bayi mendapat vitamin A, ibu hamil mendapat tablet Fe, pemeriksaan neonatus, pemeriksaan kehamilan, akses air bersih, pelayanan penyuluhan, pelayanan imunisasi dan rumah tangga miskin. WLS menghasilkan penduga parameter berbeda di setiap lokasi yang menyebabkan perbedaan model antar lokasi. Kejadian balita gizi buruk disebabkan oleh pengabaian pemeriksaan neonatus dan pelayanan imunisasi serta banyaknya rumah tangga miskin di Provinsi Jawa Timur tahun 2008.
English Abstract
Geographically Weighted Regression (GWR) is the linear regression method weighted by location. Spatial data has geographic coordinates so thatmethod of Ordinary Least Square (OLS) estimation is not appropriate. One of the GWR model parameter estimation methodsis in the form of point location coordinates Weighted Least Square (WLS). This research aims to estimate the parameters and to model data on Toddler Malnutrition in East Java Province(2008) with Fixed weight Bisquare Kernel. Predictor variables were infants received vitamin A, pregnant women received tablets Fe, neonatal examination, antenatal care, access to clean water, counseling services, immunization services and poor households. WLS estimators produce different parameters at each location resulting in different model between locations. The toddler malnutrition incidence is caused by the disobedience of neonatal, lack of immunization services and the number of poor households in East Java Province(2008).
| Item Type: | Thesis (Sarjana) |
|---|---|
| Identification Number: | SKR/MIPA/2013/169/051307149 |
| Subjects: | 500 Natural sciences and mathematics > 519 Probabilities and applied mathematics > 519.5 Statistical mathematics |
| Divisions: | Fakultas Matematika dan Ilmu Pengetahuan Alam > Statistika |
| Depositing User: | Hasbi |
| Date Deposited: | 28 Aug 2013 15:10 |
| Last Modified: | 25 Oct 2021 02:01 |
| URI: | http://repository.ub.ac.id/id/eprint/153427 |
Preview |
Text
2-abstrak.pdf Download (1MB) | Preview |
Preview |
Text
3-isi.pdf Download (2MB) | Preview |
Preview |
Text
1-sampul.pdf Download (1MB) | Preview |
Preview |
Text
Skripsi_Full_Yoeniarti_Shara.pdf Download (3MB) | Preview |
Actions (login required)
 |
View Item |