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: 『산업경영시스템학회지』제35권 제3호, 118~128쪽, 전체 11쪽
• 주제분류: 경제경영 > 경영학
• 파일형태: PDF
• 발행일자: 2012.09.30

영문 초록

An attempt is given to the problem of analyzing the two-way binary attribute data using the logistic regression model in order to find a sound statistical methodology. It is demonstrated that the analysis of variance (ANOVA) may not be good 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. Meanwhile, 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 means in estimating related confidence intervals and testing the significance of model parameters. Based on simulated data, the efficiencies of estimates are ensured with a view to demonstrate the usefulness of the methodology.

목차

1. 서 론

2. 백분비 자료의 분석

3. 계수치 자료의 분석

4. 결론 및 제언

참고문헌

키워드

Logistic Binary Attribute Data Logit Function Odds Ratio Dichotomous Response