Estimasi Model Regresi Binomial Negatif Bivariat (BNBR) Pada Penderita Kusta di Jawa Timur
Abstract
Abstract. One of the methods used to overcome overdispersion in poisson regression model is a bivariate negative binomial regression model also known as BNBR Model. Leprosy is a dangerous infectious disease, because it can cause paralysis. Leprosy is divided into 2 types, namely is a leprosy Pausibasilier(PB) type and leprosy Multibasilier (MB) type. Where PB type leprosy is a dry leprosy and MB type leprosy is a wet leprosy. Analysis of the data used to model the number of PB leprosy and MB leprosy cases and find out what factor influence it in East Java, the writer uses the BNBR models. Parameter estimation of the BNBR model uses to Maximum likelihood estimation (MLE) methods with Newton-Raphson iteration as well as testing the hypothesis using MLRT methods. After regression analysis, the results are obtained that of the 10 predictor variables tested, both in PB leprosy and MB leprosy, there are 3 predictor variables that are not significant in the model, namely are: variable percentage of poor population, variable ratio of population who did not graduated SMA, and variable ratio of health facilities.
Abstrak. Salah satu metode yang digunakan untuk mengatasi overdispersi dalam regresi Poisson yakni dengan regresi binomial negatif bivariat atau dikenal juga dengan model regresi BNBR. Penyakit Kusta adalah salah satu penyakit menular yang berbahaya, karena dapat menyebabkan kelumpuhan. Jenis penyakit kusta terbagi menjadi 2, yakni Kusta tipe Pausibasiler (PB) dan tipe Multibasiler.(MB). Dimana kusta tipe PB merupakan Kusta kering, dan kusta tipe MB adalah kusta basah. Analisis data yang digunakan untuk memodelkan besarnya jumlah kasus kusta tipePB dan tipe MB, kemudian untuk mengetahui faktor apa saja yang mempengaruhinya di Jawa Timur, penulis menggunakan model BNBR. Penaksiran parameter model BNBR menggunakan Maximum Likelihood Estimation (MLE) dengan iterasi Newton-Raphson serta melakukan pengujian hipotesis menggunakan metode MLRT. Setelah dilakukan analisis regresi, diperoleh hasil bahwa dari 10 variabel prediktor yang diujikan, baik pada kusta tipe PB maupun tipe MB, terdapat 3 variabel prediktor yang tidak signifikan dalam model, yakni: variabel presentase penduduk miskin, variabel rasio penduduk yang tidak tamat SMA, dan variabel rasio sarana kesehatan.
References
[2] Famoye, F. 2010. On the Bivariate Negative Binomial Regression Model. Journal of Applied Statistics. Vol 37, No. 6,.hal.969-981.
[3] Gurmu, S. 1991. Test of Detecting Overdispersion in the Positive Poisson Regression Model. Journal of Business and Economics Statistics .Vol.9, No. 2, pp. 215-222.
[4] Hilbe, J. M. 2011. Negative Binomial Regression (Edisi kedua). Cambridge University Press. UK.
[5] Hiswani. 2001. Kusta Salah Satu Penyakit Menular Yang Masih Di Jumpai Di Indonesia. Universitas Sumatera Utara Press. Medan.
[6] Norlatifah, Sutomo. A.H., dan Solikhah. 2010. Hubungan Kondisi Fisik Rumah, Sarana Air Bersih Dan Karakteristik Masyarakat Dengan Kejadian Kusta Di Kabupaten Tapin Kalimantan Selatan. Jurnal KES MAS. Vol 3. No. 1 ISSN : 1978-0575.
[7] Park, B.J., dan Lord, D. 2008. Adjusment for The Maximum Likelihood Estimate of The Negative Binomial Dispersion Parameter. Texas University Press. USA.
[8] Simunati, 2013.Faktor-Faktor Yang Mempengaruhi Kejadian Penyakit Kusta Di Poliklinik Rehabilitasi Rumah Sakit Dr.Tadjuddin.Chalid Makassar.Jurnal Poltekkes Kemenkes Makassar. Vol 3. No. 1. ISSN : 2302-1721.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish in UJMC (Unisda Journal of Mathematics and Computer Science) agree to the following terms:
1.Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC BY-SA 4.0) that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
