Consider the nonparametric median regression model Y-ni = g(x(ni)) + epsilon(ni), 1 less than or equal to i less than or equal to n, where Y-ni's are the observations at the fixed design points x(ni) is an element...Consider the nonparametric median regression model Y-ni = g(x(ni)) + epsilon(ni), 1 less than or equal to i less than or equal to n, where Y-ni's are the observations at the fixed design points x(ni) is an element of [0, 1], is an element of(ni)'s are independent identically distributed random variables with median zero, g(x) is the smooth function of interest, Suppose the local median estimate (g) over tilde(n, h)(x) of g(x) admits the Bahadur's representation. Under some regular conditions, the relative stability of the local median estimate is established in the L-2 sense.展开更多
Consider the fixed\|design nonparametric median regression model Y \{ni =g(x \{ni )+ε \{ni ,1≤i≤n, where ε \{ni are iid random variables with median zero. In estimating the regression function g(x), local...Consider the fixed\|design nonparametric median regression model Y \{ni =g(x \{ni )+ε \{ni ,1≤i≤n, where ε \{ni are iid random variables with median zero. In estimating the regression function g(x), local median estimates \{nh (x) are employed, where h is the number of neighbors of x. Under some regularity conditions, the asymptotic normality and rate of convergence of normal approximation are obtained.展开更多
This paper considers local median estimation in fixed design regression problems. The proposed method is employed to estimate the median function and the variance function of a heteroscedastic regression model. Strong...This paper considers local median estimation in fixed design regression problems. The proposed method is employed to estimate the median function and the variance function of a heteroscedastic regression model. Strong convergence rates of the proposed estimators are obtained. Simulation results are given to show the performance of the proposed methods.展开更多
M-cross-validation criterion is proposed for selecting a smoothing parameter in a nonparametric median regression model in which a uniform weak convergency rate for the M-cross-validated local median estimate, and the...M-cross-validation criterion is proposed for selecting a smoothing parameter in a nonparametric median regression model in which a uniform weak convergency rate for the M-cross-validated local median estimate, and the upper and lower bounds of the smoothing parameter selected by the proposed criterion are established. The main contribution of this study shows a drastic difference from those encountered in the classical L2-, L1- cross-validation technique, which leads only to the consistency in the sense of the average. Obviously, our results are novel and nontrivial from the point of view of mathematics and statistics, which provides insight and possibility for practitioners substituting maximum deviation for average deviation to evaluate the performance of the data-driven technique.展开更多
文摘Consider the nonparametric median regression model Y-ni = g(x(ni)) + epsilon(ni), 1 less than or equal to i less than or equal to n, where Y-ni's are the observations at the fixed design points x(ni) is an element of [0, 1], is an element of(ni)'s are independent identically distributed random variables with median zero, g(x) is the smooth function of interest, Suppose the local median estimate (g) over tilde(n, h)(x) of g(x) admits the Bahadur's representation. Under some regular conditions, the relative stability of the local median estimate is established in the L-2 sense.
基金Supported by the Doctoral Foundation of Education ofChina(No.970 0 0 139)
文摘Consider the fixed\|design nonparametric median regression model Y \{ni =g(x \{ni )+ε \{ni ,1≤i≤n, where ε \{ni are iid random variables with median zero. In estimating the regression function g(x), local median estimates \{nh (x) are employed, where h is the number of neighbors of x. Under some regularity conditions, the asymptotic normality and rate of convergence of normal approximation are obtained.
基金The first author’s research was supported by the National Natural Science Foundation of China(Grant No.198310110 and Grant No.19871003)the partly support of the Doctoral Foundation of China and the last three authors’research was supported by a gra
文摘This paper considers local median estimation in fixed design regression problems. The proposed method is employed to estimate the median function and the variance function of a heteroscedastic regression model. Strong convergence rates of the proposed estimators are obtained. Simulation results are given to show the performance of the proposed methods.
文摘M-cross-validation criterion is proposed for selecting a smoothing parameter in a nonparametric median regression model in which a uniform weak convergency rate for the M-cross-validated local median estimate, and the upper and lower bounds of the smoothing parameter selected by the proposed criterion are established. The main contribution of this study shows a drastic difference from those encountered in the classical L2-, L1- cross-validation technique, which leads only to the consistency in the sense of the average. Obviously, our results are novel and nontrivial from the point of view of mathematics and statistics, which provides insight and possibility for practitioners substituting maximum deviation for average deviation to evaluate the performance of the data-driven technique.
