Pemodelan Geographically Weighted Regression (GWR) Dengan Fungsi Pembobot Tricube Terhadap Angka Kematian Ibu (AKI) Di Kabupaten Kutai Kartanegara Tahun 2015

Muhammad Rahmad Fadli (Mahasiswa Program Studi Statistika FMIPA Universitas Mulawarman)
Rito Goejantoro (Dosen Program Studi Statistika FMIPA Universitas Mulawarman)
Wasono Wasono (Dosen Program Studi Statistika FMIPA Universitas Mulawarman)

Eksponensial
Vol 9 No 1 (2018)

Maternal Mortality in Kutai Kartanegara is a geographical problem that suspected affected by geographical factor which the global regression cannot model the relation well between the main problem and its independent variable. Therefore, Geographically Weighted Regression (GWR) is used to solve it. Spatial statistics is a method for analyzing data that has spatial correlation. GWR Model is the locally of global regression which considering the geographical or location as the weighted function for estimating the parameters of models. The tricube weighted function is used for the weighting. From this study, the models are different from location to others with also has the independent variables. For Samboja, Muara Jawa, Sanga-Sanga, Anggana, Muara Badak, Marang Kayu, and Tabang which are not affected by the indicators. Loa Janan, Loa Kulu, Muara Muntai, Kota Bangun, Tenggarong, Sebulu, Tenggarong Seberang, Muara Kaman, and Kenohan have the Maternal Mortality affected by Hospital Ratio per 1.000 Pregnant Mothers (x1). Muara Wis, Kenohan, dan Kembang Janggut have the Maternal Mortality affected by Childbirth with Medical Help (x2). Muara Muntai, Muara Wis, Kota Bangun, Sebulu, Tenggarong, Muara Kaman, Kenohan, and Kembang Janggut have the Maternal Mortality affected by Health Care of Childbed (x4).