Mathematical Sciences: Topics in Nonparametric and Semiparametric Regression and Correlation Analysis

当非参数或半参数模型取代熟悉的参数模型时，常用的关联度量，如相关系数，需要扩展定义或重新表述。一种扩展的定义使用曲线来表达这些关系。这项研究将发展一种估计这类曲线的渐近理论。将考虑进一步扩展到几个协变量的情况。

Common measures of association such as the correlation coefficient need expanded definitions or reformulations when nonparametric or semiparametric models replace familiar parametric ones. One expanded definition uses curves to express these relationships. This research will develop an asymptotic theory of estimates of such curves. Further extensions to the case of several covariates will be considered.