A Semi‐parametric Regression Model with Errors in Variables

From MaRDI portal





The model under consideration is a semi-parametric regression model such that the conditional expectation of the univariate \(Y\) is \(E(Y\mid t_0,X_0)=X_0^T (\theta)+g(t_0)\), where \(X_0\) and \(t_0\) are \(p\)- and 1-dimensional, respectively, \(\theta\) is an \(p\times1\) unknown parameter vector, \(g(\cdot)\) is an unknown function, and both \(X_0\) and \(t_0\) are measured with errors, i.e., \(X=X_0+u\), \(t=t_0+v\). The authors propose a combination of the method of moments and deconvolution to construct a new class of parametric estimates together with a nonparametric kernel estimator. Strong convergence, optimal rate of weak convergence and asymptotic normality are proved, and simulation study results are presented.




Cited in
(49)








This page was built for publication: A Semi‐parametric Regression Model with Errors in Variables

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4828210)