Die nachfolgend beschriebene Methode ist die in Abschnitt 6.3.3 von Davidson und Hinckley (1997),
Bootstrap Methods and Their Application beschriebene . Vielen Dank an Glen_b und seinen Kommentar hier . Angesichts der Tatsache, dass es zu diesem Thema mehrere Fragen zu Cross Validated gab, hielt ich es für wert, darüber zu schreiben.
Yi=Xiβ+ϵi
i=1,2,…,Nβ
β^OLS=(X′X)−1X′Y
YXXXN+1YYN+1ϵiX
YpN+1=XN+1β^OLS
epN+1=YN+1−YpN+1
YN+1=YpN+1+epN+1
YpN+1YN+15th95thepN+1e5,e95[YpN+1+e5,YpN+1+e95]
epN+1
epN+1=YN+1−YpN+1=XN+1β+ϵN+1−XN+1β^OLS=XN+1(β−β^OLS)+ϵN+1
epN+1epN+15th95th500th9,500th
XN+1(β−β^OLS)Nϵ∗iY∗i=Xiβ^OLS+ϵ∗i(Y∗,X)β∗rXN+1(β−β^OLS)XN+1(β^OLS−β∗r)
ϵϵN+1{e∗1,e∗2,…,e∗N}{s1−s¯¯¯,s2−s¯¯¯,…,sN−s¯¯¯}si=e∗i/(1−hi)−−−−−−√hii
YN+1XXN+1
- YpN+1=XN+1β^OLS
- {s1−s¯¯¯,s2−s¯¯¯,…,sN−s¯¯¯}si=ei/(√1−hi)
- r=1,2,…,R
- N{ϵ∗1,ϵ∗2,…,ϵ∗N}
- Y∗=Xβ^OLS+ϵ∗
- β∗r=(X′X)−1X′Y∗
- e∗r=Y∗−Xβ∗r
- s∗−s∗¯¯¯¯¯
- ϵ∗N+1,r
- epN+1ep∗r=XN+1(β^OLS−β∗r)+ϵ∗N+1,r
- 5th95thepN+1e5,e95
- YN+1[YpN+1+e5,YpN+1+e95]
Hier ist R
Code:
# This script gives an example of the procedure to construct a prediction interval
# for a linear regression model using a bootstrap method. The method is the one
# described in Section 6.3.3 of Davidson and Hinckley (1997),
# _Bootstrap Methods and Their Application_.
#rm(list=ls())
set.seed(12344321)
library(MASS)
library(Hmisc)
# Generate bivariate regression data
x <- runif(n=100,min=0,max=100)
y <- 1 + x + (rexp(n=100,rate=0.25)-4)
my.reg <- lm(y~x)
summary(my.reg)
# Predict y for x=78:
y.p <- coef(my.reg)["(Intercept)"] + coef(my.reg)["x"]*78
y.p
# Create adjusted residuals
leverage <- influence(my.reg)$hat
my.s.resid <- residuals(my.reg)/sqrt(1-leverage)
my.s.resid <- my.s.resid - mean(my.s.resid)
reg <- my.reg
s <- my.s.resid
the.replication <- function(reg,s,x_Np1=0){
# Make bootstrap residuals
ep.star <- sample(s,size=length(reg$residuals),replace=TRUE)
# Make bootstrap Y
y.star <- fitted(reg)+ep.star
# Do bootstrap regression
x <- model.frame(reg)[,2]
bs.reg <- lm(y.star~x)
# Create bootstrapped adjusted residuals
bs.lev <- influence(bs.reg)$hat
bs.s <- residuals(bs.reg)/sqrt(1-bs.lev)
bs.s <- bs.s - mean(bs.s)
# Calculate draw on prediction error
xb.xb <- coef(my.reg)["(Intercept)"] - coef(bs.reg)["(Intercept)"]
xb.xb <- xb.xb + (coef(my.reg)["x"] - coef(bs.reg)["x"])*x_Np1
return(unname(xb.xb + sample(bs.s,size=1)))
}
# Do bootstrap with 10,000 replications
ep.draws <- replicate(n=10000,the.replication(reg=my.reg,s=my.s.resid,x_Np1=78))
# Create prediction interval
y.p+quantile(ep.draws,probs=c(0.05,0.95))
# prediction interval using normal assumption
predict(my.reg,newdata=data.frame(x=78),interval="prediction",level=0.90)
# Quick and dirty Monte Carlo to see which prediction interval is better
# That is, what are the 5th and 95th percentiles of Y_{N+1}
#
# To do it properly, I guess we would want to do the whole procedure above
# 10,000 times and then see what percentage of the time each prediction
# interval covered Y_{N+1}
y.np1 <- 1 + 78 + (rexp(n=10000,rate=0.25)-4)
quantile(y.np1,probs=c(0.05,0.95))