变系数Logistic模型估计及其应用

Varying-Coefficient Logistic Model Estimation and Its Application

以线性Logistic模型为基础,通过假定其中的回归变量系数是某一度量空间中点的任意函数,提出了一类有广泛应用背景的变系数Logistic模型.该模型提高了线性Logistic模型的灵活性和适应性.基于局部加权最大似然估计方法,系统讨论了变系数Logistic模型的拟合,以及与之相关的局部权系统和其中光滑参数的确定.最后,探讨了本模型在判别分析中的应用.

Based on linear Logistic model and by assuming the coefficients of the regressors to be arbitrary functions of the points in some metric space, a new type of regression model, called varying-coefficient Logistic model, was proposed. The local maximum likelihood approach was suggested to fit the model and the related issues such as the determination of the local weights and the smoothing parameter were studied. The model was applied for distinguishing analysis. The proposed model has higher flexibility and adaptability.