ESTIMASI MODEL REGRESI SEMIPARAMETRIK SPLINE TRUNCATED MENGGUNAKAN METODE MAXIMUM LIKELIHOOD ESTIMATION (MLE)

Regression modeling with a semiparametric approach is a combination of two approaches, namely the parametric regression approach and the nonparametric regression approach. The semiparametric regression model can be used if the response variable has a known relationship pattern with one or more of the predictor variables used, but with the other predictor variables the relationship pattern cannot be known with certainty. The purpose of this research is to examine the estimation form of the semiparametric spline truncated regression model. Suppose that random error is assumed to be independent, identical, and normally distributed with zero mean and variance , then using this assumption, we can estimate the semiparametric spline truncated regression model using the Maximum Likelihood Estimation (MLE) method. Based on the results, the estimation results of the semiparametric spline truncated regression model were obtained p=(inv(M'M)) M'y

Download Full-text

Estimasi Model Regresi Binomial Negatif Bivariat (BNBR) Pada Penderita Kusta di Jawa Timur

Unisda Journal of Mathematics and Computer Science (UJMC) ◽

10.52166/ujmc.v5i2.1696 ◽

2019 ◽

Vol 5 (2) ◽

pp. 29-38

Author(s):

WIGID HARIADI ◽

Sulantari Sulantari

Keyword(s):

Maximum Likelihood ◽

Maximum Likelihood Estimation ◽

Regression Model ◽

Negative Binomial ◽

Likelihood Estimation ◽

Negative Binomial Regression ◽

Predictor Variables ◽

Negative Binomial Regression Model ◽

Variable Ratio ◽

Newton Raphson

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.

Download Full-text