The Bias of Estimating Equations with Application to the Error Rate of Logistic Discrimination
推导了由估计方程定义的向量估计量偏差的便捷表达式，并用于分析逻辑回归分类在模型假设不成立时的偏差和错误率，发现逻辑回归对某些偏离非常稳健。
Abstract The logistic regression classification method uses parameter estimates that are the solution of an estimating equation. This article derives a convenient expression for the bias of a vector estimator defined by estimating equations. The expression and the results of O'Neill are used to derive the bias and the error or misclassification rate of logistic regression classification in two examples where the assumed model for logistic regression does not hold. Logistic regression classification is found to be very robust for the departures considered. Key Words: ClassificationNon-BayesNonnormal