Maximum Likelihood Estimation of Parameters from a Multivariate Normal Sample with 2-step Monotone Missing Pattern
2-단계 단조패턴을 가지는 다변량 정규표본으로부터 모수들의 최대가능도추정
A sample with special missing pattern called a monotone sample or a monotone missing data pattern occurs in many applications. The statistical methods for analyzing a monotone sample have been developed by several analysts. The purpose of this paper is to introduce the maximum likelihood estimation of parameters when there is a multivariate normal sample with 2-step monotone pattern, and to present the maximum likelihood estimates of parameters in closed forms. These estimates can be obtained by maximizing the overall likelihood function which is expressed in terms of the marginal and conditional likelihood functions with respect to parameters. The maximum likelihood estimates presented are expected to he used to develop statistical methods for analyzing a multivariate normal sample with 2-step monotone pattern in applications.
목차
Abstract 1. Introduction 2. The Structure of Sample with 2-step Monotone Missing Data Pattern 3. Parameter Estimation by the Method of Maximum Likehood 4. Numerical Illustration 5. Conclusion References 요약
저자
Byungjin Choi [ 최병진 | Full-time Lecture, Department of Applied Information Statistics, Kyonggi University ]