Abstract:

The author considers semiparametric regression model under fixed design: y_i = x_iβ+g(t_i)+e_i,i=1,…,n, where e_i,1≤i≤n, be independent random error sequence with Ee_i=0 and Ee²_i=σ²_i>0. He estimates β and g(·) from completed and censored data by [2]. In this paper, the author prove that these estimations of β and g(·) have strong consistency.

Key words: Semiparametric regression model, Strong consistency, Fixed design, Censored data.