| In this thesis , we explore the consistency problems under Negative Associ-ated(NA) samples . Two parts are included in the thesis as following:In the first part , we studied the strong consistency of the least square(LS) estimator β|^ of β in linear model y_i = x'_iβ + e_i for NA samples. Accordingly , we proved its strong consistency. Also, we studied the weak and strong consistency of error estimator and gave its convergency rate.In the second part , also under NA assumption, we worked on the consistency of kernel estimator of regression function in the nonparametric regression model Y_i =g(X_i)+ε_i. |
