for (i in 1:m){ x <-sort(rnorm(n)) tmean[1]<-sum(x[2:(n-1)])/(n-2) mse <-mean(tmean"2) mse sqrt(sum((tmean mean(tmean))2))/m #s日 Code 截尾均值的MSE的估计为0.0504531(se÷0.007).样本均值的MSE为Var(X)/n= 1/20=0.05.另一方面，中位数本质上也是一种截尾均值，其截掉了除中间的 一个或两个点外的所有点.样本中位数的MSE估计如下 TCode n<-20 m<-1000 tmean <-numeric(m) for (i in 1:m){ x <-sort(rnorm(n)) tmean[i]<-median(x) ] Previous Next First Last Back Forward 7for (i in 1:m) { x <- sort(rnorm(n)) tmean[i] <- sum(x[2:(n-1)]) / (n-2) } mse <- mean(tmean^2) mse sqrt(sum((tmean - mean(tmean))^2)) / m #se ↓Code ó˛äMSEOè0.0504531( ˆse .= 0.007). ˛ä MSEèV ar(X)/n = 1/20 = 0.05. ,òê°, •†Íü˛è¥ò´ó˛ä, ŸK ÿ•m òὸá: §k:. •†ÍMSEOXe ↑Code n <- 20 m <- 1000 tmean <- numeric(m) for (i in 1:m) { x <- sort(rnorm(n)) tmean[i] <- median(x) } Previous Next First Last Back Forward 7