我已经编写了下面的代码来获得平均值的bootstrap估计值。我的目标是通过boot
包中的函数boot
查看从数据集中选择的数字,最好按照选择的顺序查看。
数据集只包含三个数字:1,10和100,我只使用两个bootstrap样本。
估算的平均值为23.5
,下面的R
代码表示六个数字包括一个' 1'四个' 10'和一个' 100'但是,这些数字有30种可能的组合,平均值为23.5。
我有办法确定这30种可能组合中的哪一种是两个自举样本中实际出现的组合吗?
library(boot)
set.seed(1234)
dat <- c(1, 10, 100)
av <- function(dat, i) { sum(dat[i])/length(dat[i]) }
av.boot <- boot(dat, av, R = 2)
av.boot
#
# ORDINARY NONPARAMETRIC BOOTSTRAP
#
#
# Call:
# boot(data = dat, statistic = av, R = 2)
#
#
# Bootstrap Statistics :
# original bias std. error
# t1* 37 -13.5 19.09188
#
mean(dat) + -13.5
# [1] 23.5
# The two samples must have contained one '1', four '10' and one '100',
# but there are 30 possibilities.
# Which of these 30 possible sequences actual occurred?
# This code shows there must have been one '1', four '10' and one '100'
# and shows the 30 possible combinations
my.combos <- expand.grid(V1 = c(1, 10, 100),
V2 = c(1, 10, 100),
V3 = c(1, 10, 100),
V4 = c(1, 10, 100),
V5 = c(1, 10, 100),
V6 = c(1, 10, 100))
my.means <- apply(my.combos, 1, function(x) {( (x[1] + x[2] + x[3])/3 + (x[4] + x[5] + x[6])/3 ) / 2 })
possible.samples <- my.combos[my.means == 23.5,]
dim(possible.samples)
n.1 <- rowSums(possible.samples == 1)
n.10 <- rowSums(possible.samples == 10)
n.100 <- rowSums(possible.samples == 100)
n.1[1]
n.10[1]
n.100[1]
length(unique(n.1)) == 1
length(unique(n.10)) == 1
length(unique(n.100)) == 1
答案 0 :(得分:0)
我认为您可以使用以下代码确定采样数和采样顺序。您必须从ordinary.array
包中提取函数boot
并将该函数粘贴到R
代码中。然后指定n
,R
和strata
的值,其中n
是数据集中的观察数,R
是重复样本的数量你想要的。
我不知道这种方法有多普遍,但它适用于我尝试的几个简单示例,包括下面的示例。
library(boot)
set.seed(1234)
dat <- c(1, 10, 100, 1000)
av <- function(dat, i) { sum(dat[i])/length(dat[i]) }
av.boot <- boot(dat, av, R = 3)
av.boot
#
# ORDINARY NONPARAMETRIC BOOTSTRAP
#
#
# Call:
# boot(data = dat, statistic = av, R = 3)
#
#
# Bootstrap Statistics :
# original bias std. error
# t1* 277.75 -127.5 132.2405
#
#
mean(dat) + -127.5
# [1] 150.25
# boot:::ordinary.array
ordinary.array <- function (n, R, strata)
{
inds <- as.integer(names(table(strata)))
if (length(inds) == 1L) {
output <- sample.int(n, n * R, replace = TRUE)
dim(output) <- c(R, n)
}
else {
output <- matrix(as.integer(0L), R, n)
for (is in inds) {
gp <- seq_len(n)[strata == is]
output[, gp] <- if (length(gp) == 1)
rep(gp, R)
else bsample(gp, R * length(gp))
}
}
output
}
# I think the function ordinary.array determines which elements
# of the data are sampled in each of the R samples
set.seed(1234)
ordinary.array(n=4,R=3,1)
# [,1] [,2] [,3] [,4]
# [1,] 1 3 1 3
# [2,] 3 4 1 3
# [3,] 3 3 3 3
#
# which equals:
((1+100+1+100) / 4 + (100+1000+1+100) / 4 + (100+100+100+100) / 4) / 3
# [1] 150.25