Adeliana, Adeliana (2017) Estimasi parameter Geographically Weighted Zero Inflated Poisson Regression (GWZIPR) dengan pembobot fixed bisquare kernel. Undergraduate thesis, Universitas Islam Negeri Maulana Malik Ibrahim.
|
Text (Fulltext)
13610049.pdf - Accepted Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (3MB) | Preview |
Abstract
INDONESIA:
Regresi Poisson merupakan suatu bentuk analisis regresi yang digunakan untuk memodelkan data yang berbentuk count (jumlah). Metode regresi poisson mensyaratkan adanya equidispersi yaitu kondisi dimana nilai mean dan varians dari variabel respon bernilai sama. Namun adakalanya terjadi fenomena overdispersi dalam data yang dimodelkan dengan distribusi poisson. Overdispersi berarti data memiliki varians yang lebih besar daripada mean. Overdispersi menunjukkan bahwa terdapat heterogenitas populasi. Akibatnya estimasi parameter pada data dengan kondisi yang demikian menjadi tidak tepat. Salah satu metode untuk mengatasi overdispersi adalah dengan model Zero Inflated Poisson Regression. Kemudian pengembangan dari regresi ZIP yang telah memperhitungkan faktor spasial disebut Geographically Weighted Zero Inflated Poisson Regression (GWZIPR). Penaksiran parameter model GWZIPR dilakukan dengan metode Maximum Likelihood Estimation (MLE) dan diselesaikan menggunakan algoritma Ekspektasi-Maksimalisasi (EM). Pembobot fungsi yang digunakan adalah fixed bisquare kernel. Penelitian ini menunjukkan bahwa penyakit Tetanus Neonatorum di seluruh kabupaten/kota di provinsi Jawa Timur paling banyak dipengaruhi oleh empat faktor yang signifikan yaitu cakupan imunisasi TT2+ terhadap jumlah ibu hamil, ibu bersalin ditolong tenaga kesehatan, cakupan kunjungan neonatal lengkap terhadap jumlah bayi, dan penanganan komplikasi neonatal terhadap jumlah ibu hamil.
ENGLISH:
Poisson regression is a form of regression analysis used to model data in the form of count (amount). Poisson regression method requires existence of equidispersion that is condition where the mean value equals the variance of response variable. But sometimes there is an overdispersion phenomenon in the data modeled with the poisson distribution. Overdispersion means that data has a variance greater than the mean. Overdispersion shows that there is a population heterogeneity. Consequently, the estimation of the parameters on the data under such conditions becomes imprecise. One method to overcome the overdispersion is the Zero Inflated Poisson (ZIP) Regression model. Then the development of the ZIP regression that has taken into account the spatial factor is called Geographically Weighted Zero Inflated Poisson Regression (GWZIPR). The parameter estimation of the GWZIPR model is carried out by the Maximum Likelihood Estimation (MLE) method and completed using the Expectation-Maximization (EM) algorithm. Weighting function used is fixed bisquare kernel. This study shows that Tetanus Neonatorum disease in all districts/cities in East Java province is mostly influenced by four significant factors, namely TT2+ immunization coverage on the number of pregnant women, maternity assisted by health personnel, coverage of complete neonatal visit to infant number, and complication management neonatal to the number of pregnant women.
Item Type: | Thesis (Undergraduate) | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Supervisor: | Harini, Sri and Jamhuri, Mohammad | |||||||||
Contributors: |
|
|||||||||
Keywords: | Geographically Weighted Zero Inflated Poisson Regression; Maximum Likelihood Estimation; Tetanus | |||||||||
Departement: | Fakultas Sains dan Teknologi > Jurusan Matematika | |||||||||
Depositing User: | Durrotun Nafisah | |||||||||
Date Deposited: | 08 Aug 2018 09:39 | |||||||||
Last Modified: | 08 Aug 2018 09:42 | |||||||||
URI: | http://etheses.uin-malang.ac.id/id/eprint/11964 |
Downloads
Downloads per month over past year
Actions (login required)
View Item |