Development of a Criterion for Assessing the Influence of the Measurement Errors in the Independent Variables on Prediction

독립변수의 측정오차가 예측에 미치는 영향을 평가하기 위한 기준개발

In developing a multiple regression relationship, independent variables are frequently measured with error. For these situations the problem of estimating unknown parameters has been extensively discussed in the literature while little attention has been given to the prediction problem. In this paper a criterion is developed for assessing the severeness of measurement errors in each independent variable on the predicted values. Using the developed criterion we can present a guideline as to which measurement error should be controlled for a more accurate prediction. Proposed methods are illustrated with a standard data system in work measurement.