A Simple Method to Obtain Maximum Likelihood Estimates for Identity Poisson Regression Models

• 발행기관: 한국자료분석학회
• 저자명: 최현집(Hyunjip Choi)
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.17 No.2, 613~622쪽, 전체 10쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2015.04.30

영문 초록

This paper aims to propose a simple method for obtaining MLE for identity link Poisson regression models. In order to estimate parameters of the models, fully parameterized models are suggested. An iterative fitting algorithm is then proposed for estimating parameters of the models. Through suitable reparameterization of the parameters in the models, the estimates of parameters in identity link Poisson regression models can be obtained easily. Because the method does not consider the subsets of the parameter space, computational burden is less intensive than the other methods. An example and simulation results are given to evaluate the performance of the suggested method.

목차

1. Introduction

2. Estimation Method by Fully Parameterized Models

3. Example and Simulation Results

4. Discussion

References

키워드

count data fully parameterized models Poisson regression models reparameterization