치아우식발생예측모형개발에 관한 연구
Tree Structured Classification Model for High Risk Dental Caries
문혁수,
소속 상세정보
문혁수 ( ) - 서울대학교
KMID : 0355419950190010161
Abstract
Caries prediction by Fast and Automatic Classification Trees(FACT0 analysis is an appropriate and alternative or complement to the commonly used classification methods of logistic regression and discriminant analysis, both parametric and
nonparametric.
This binary classification tree method is designed for complex data and dose not require assumptions about the predictor variables or about the presence or absence of interactions among the predictor variables. Furthermore, the results give
insight
into
the structures and interactions in the data and are easy to interpret and apply. In application of the FACT algorithms to SNU Caries Risk Assessment data, The method produced prediction rules having sensitivity and specificity that were slightly
better
than those associated with logistic and disoriminant analyses. Tree structured classification constructured tended to involve far fewer predictor variables than required for adequate logistic and discriminant models. For example, only three
variables
were used to define a prediction rule having 70% sensivity and 78% specificity. Seven-fold cross-validation estimates for future data were 65% and 61%, respectively.
키워드
원문 및 링크아웃 정보
등재저널 정보