이원 이항 계수치 자료의 로지스틱 회귀 분석

• 영문명: A logistic regression analysis of two-way binary attribute data
• 발행기관: 한국산업경영시스템학회
• 저자명: 안해일(Haeil Ahn)
• 간행물 정보: 『한국산업경영시스템학회 학술대회』2012년 춘계학술대회 논문집, 129~136쪽, 전체 8쪽
• 주제분류: 공학 > 산업공학
• 파일형태: PDF
• 발행일자: 2012.05.12

영문 초록

In this paper, an analysis of two-way binary attribute data is performed using the logistic regression model in order to find a sound statistical methodology. It is demonstrated that the ANOVA may not be enough, especially for the case that the proportion is very low or high. The logistic transformation of proportion data could be a help, but not sound in the statistical sense. The adoption of generalized least squares(GLS) method entails much to estimate the variance-covariance matrix. On the other hand, the logistic regression methodology provides sound statistical background in estimating model parameters and related confidence intervals. The efficiencies of estimates are ensured with a simulated data with a view to demonstrate the usefulness of the methodology.

목차

Abstract

1. 서론

2. 백분비 자료의 분석

3. 계수치 자료의 분석

4. 결론 및 제언

참고문헌

키워드

logistic regression binary attribute data logit model ANOVA link function