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.

Abstract
 1. 서 론
 2. 백분비 자료의 분석
  2.1 수율자료
  2.2 로지스틱 변환
 3. 계수치 자료의 분석
  3.1 부적합률 자료
  3.2 로짓 변환
  3.3 일반화 최소제곱법
  3.4 이항 로지스틱 회귀
  3.5 모형의 적합
 4. 결론 및 제언
 참고문헌

• 안해일(서경대학교 산업공학과) | Haeil Ahn