Modified Method on Confidence Intervals for Variance in Two-Factor Nested Variance Components Model

• 발행기관: 한국자료분석학회
• 저자명: Kwan-Joong Kang
• 간행물 정보: 『Journal of The Korean Data Analysis Society (JKDAS)』Vol.12 No.2, 651~662쪽, 전체 12쪽
• 주제분류: 자연과학 > 통계학
• 파일형태: PDF
• 발행일자: 2010.04.30

영문 초록

The confidence intervals for σ²A/( σ²A+σ²B+σ²C) are given in various forms by many authors in two-factor nested variance components model yijk=μ+Ai+Bij+Cijk. In this model, Kimball’s(1951) method confidence intervals for σ²A/(σ²A+σ²B+σ²C) are given by an asymptotic confidence intervals. By the simulation results of this confidence coefficients are not fit exactly for the given confidence coefficients and the ranges are too wide to use for test and estimation. Thus, we would like to give one of the modified Kimball’s method confidence intervals for σ²A/(σ²A+σ²B+σ²C) in this model. And the simulation results of this modified confidence coefficients are better than those obtained by using Kimball’s method confidence coefficients, and we can use for test and estimation.

목차

1. Introduction

2. Two-Factor Nested Variance Components Model

3. Confidence Intervals

4. Simulation Results

References

키워드

Modified confidence intervals Two-factor nested variance components model Variance component