在这段代码中，我想计算正态分布的修剪平均值和修剪平均值的方差(我想计算从1到13的每个阿尔法的值(，并将结果存储在数据中。帧然后打印所有结果。但问题是，新结果存储在以前的结果之上，最后我只得到最后一个结果alpha值的结果。
ProDistFun<- data.frame(matrix(nrow=91, ncol=4))
colnames(ProDistFun)<-c("x","Alpha","Trimmed Mean","Variance Of Trimmed Mean")
mu=7 # Mean Value
sigma2=4 # Variance value
for (alpha in c(0.001,0.01,0.025,0.05,0.1,0.25,0.375))
{
for(i in 1:13)
{
ProDistFun[i,1]<-i
ProDistFun[i,2]<-alpha
# The trimmed mean
a=qnorm(alpha, mean=mu, sd=sqrt(sigma2))
b=qnorm(1-alpha, mean=mu, sd=sqrt(sigma2))
fun_TM <- function(x) ((x*exp(-0.5*((x-mu)/sqrt(sigma2))^2))/((1-2*alpha)*(sqrt(2*pi*sigma2))))
MT1 <- integrate(fun_TM, a, b)
MT <-MT1$value
ProDistFun[i,3]<-MT
# The variance of trimmed mean
fun_VTM <- function(x) ((((x-MT)^2)*exp(-0.5*((x-mu)/sqrt(sigma2))^2))/(sqrt(2*pi*sigma2)))
fVTM <- integrate(fun_VTM, a, b)
fV <- fVTM$value
VT=((fV+(alpha*(a-MT)^2)+(alpha*(b-MT)^2))/((1-2*alpha)^2))
ProDistFun[i,4]<-VT
}
}
print(ProDistFun)
9月30日12:23小时编辑
我仍然不完全清楚你试图用x实现什么，因为你使用它的方式很混乱，但使用了大部分代码并大幅简化，但仍然使用for loop
创建一个没有矩阵扭曲的空数据帧。
ProDistFun <- data.frame(
x = integer(0),
Alpha = numeric(0),
Trimmed_Mean = numeric(0),
Variance_Of_Trimmed_Mean = numeric(0)
)
分配两个常量重要提示--在整个代码中，请停止将分配<-与=视为同一件事，这将导致以后出现问题。
mu <- 7 # Mean Value
sigma2 <- 4 # Variance value
将您的两个函数从循环中拉出(每次迭代都重新运行它们毫无意义(。我不知道它们是否正确，但它们似乎有效。在我看来，在这些函数中，你希望x值是i的值，所以我做了这个改变。如果你不这样做，你会得到13次相同的迭代
fun_TM <- function(x) {
((i*exp(-0.5*((i-mu)/sqrt(sigma2))^2))/((1-2*alpha)*(sqrt(2*pi*sigma2))))
}
fun_VTM <- function(x) {
((((i-MT)^2)*exp(-0.5*((i-mu)/sqrt(sigma2))^2))/(sqrt(2*pi*sigma2)))
}
现在我们运行alpha和i的嵌套循环。我们构建一行添加到空数据帧ProDist_df，然后最后一步是rbind，即newrow。注意，如integrate的帮助文件中所述，我们需要Vectorize。
for (alpha in c(0.001,0.01,0.025,0.05,0.1,0.25,0.375)) {
for (i in 1:13) {
a <- qnorm(alpha, mean = mu, sd = sqrt(sigma2))
b <- qnorm(1 - alpha, mean = mu, sd = sqrt(sigma2))
MT1 <- integrate(Vectorize(fun_TM), a, b)
MT <- MT1$value
fVTM <- integrate(Vectorize(fun_VTM), a, b)
fV <- fVTM$value
VT <- ((fV+(alpha*(a-MT)^2)+(alpha*(b-MT)^2))/((1-2*alpha)^2))
newrow <- data.frame(x = i,
Alpha = alpha,
Trimmed_Mean = MT,
Variance_Of_Trimmed_Mean = VT)
ProDist_df <- rbind(ProDist_df, newrow)
}
}
ProDist_df
#> x Alpha Trimmed_Mean Variance_Of_Trimmed_Mean
#> 1 1 0.001 0.02744577 0.2003378
#> 2 2 0.001 0.21710028 0.5148306
#> 3 3 0.001 1.00307392 1.4849135
#> 4 4 0.001 3.20833233 0.6092747
#> 5 5 0.001 7.49244239 9.4048587
#> 6 6 0.001 13.08172721 109.7134117
#> 7 7 0.001 17.29412878 262.6203021
#> 8 8 0.001 17.44230295 195.0733274
#> 9 9 0.001 13.48639629 30.3828344
#> 10 10 0.001 8.02083083 3.2269398
#> 11 11 0.001 3.67793771 18.0605860
#> 12 12 0.001 1.30260169 12.5886402
#> 13 13 0.001 0.35679506 4.5613376
#> 14 1 0.010 0.02104086 1.4856627
#> 15 2 0.010 0.16643643 1.7087503
#> 16 3 0.010 0.76899043 2.5612272
#> 17 4 0.010 2.45961619 2.3689151
#> 18 5 0.010 5.74396001 1.1324626
#> 19 6 0.010 10.02889499 28.3270524
#> 20 7 0.010 13.25826466 76.9619814
#> 21 8 0.010 13.37185999 50.5144290
#> 22 9 0.010 10.33912801 2.7851234
#> 23 10 0.010 6.14904048 9.7709433
#> 24 11 0.010 2.81963158 18.3179999
#> 25 12 0.010 0.99861856 11.4783190
#> 26 13 0.010 0.27353117 4.8704116
#> 27 1 0.025 0.01828687 3.5703608
#> 28 2 0.025 0.14465195 3.7170106
#> 29 3 0.025 0.66833905 4.3472611
#> 30 4 0.025 2.13768272 4.1121498
#> 31 5 0.025 4.99214637 1.0747081
#> 32 6 0.025 8.71623613 12.2965566
#> 33 7 0.025 11.52292107 37.4315915
#> 34 8 0.025 11.62164818 22.0916831
#> 35 9 0.025 8.98586347 1.0699878
#> 36 10 0.025 5.34420680 13.1972079
#> 37 11 0.025 2.45057652 19.1385400
#> 38 12 0.025 0.86791169 12.3691446
#> 39 13 0.025 0.23772931 6.5199633
#> 40 1 0.050 0.01619943 7.3749079
#> 41 2 0.050 0.12813995 7.4154400
#> 42 3 0.050 0.59204825 7.6768541
#> 43 4 0.050 1.89366655 6.8889173
#> 44 5 0.050 4.42229360 2.4843697
#> 45 6 0.050 7.72127906 5.6367092
#> 46 7 0.050 10.20758133 19.2763445
#> 47 8 0.050 10.29503875 10.2078727
#> 48 9 0.050 7.96012848 2.5125393
#> 49 10 0.050 4.73416638 16.5558668
#> 50 11 0.050 2.17084357 21.3087060
#> 51 12 0.050 0.76883970 15.1092609
#> 52 13 0.050 0.21059254 9.9710784
#> 53 1 0.100 0.01419911 17.3206584
#> 54 2 0.100 0.11231710 17.1281634
#> 55 3 0.100 0.51894156 16.5102647
#> 56 4 0.100 1.65983477 13.8052303
#> 57 5 0.100 3.87622451 6.3261279
#> 58 6 0.100 6.76784806 2.9011142
#> 59 7 0.100 8.94713932 9.2952208
#> 60 8 0.100 9.02379741 4.8107658
#> 61 9 0.100 6.97720412 6.0182204
#> 62 10 0.100 4.14958694 22.3456468
#> 63 11 0.100 1.90278571 28.0669010
#> 64 12 0.100 0.67390263 23.5641219
#> 65 13 0.100 0.18458837 19.4835253
#> 66 1 0.250 0.01195695 101.3283283
#> 67 2 0.250 0.09458127 99.3524957
#> 68 3 0.250 0.43699624 91.6992768
#> 69 4 0.250 1.39773265 71.1428700
#> 70 5 0.250 3.26413547 35.4870897
#> 71 6 0.250 5.69914690 7.1958771
#> 72 7 0.250 7.53430941 4.8250199
#> 73 8 0.250 7.59886254 4.6624497
#> 74 9 0.250 5.87544385 18.9156520
#> 75 10 0.250 3.49433163 57.7975362
#> 76 11 0.250 1.60231955 87.6386891
#> 77 12 0.250 0.56748763 98.7559156
#> 78 13 0.250 0.15544029 101.2808652
#> 79 1 0.375 0.01129729 591.0212507
#> 80 2 0.375 0.08936330 578.6087319
#> 81 3 0.375 0.41288753 529.2387893
#> 82 4 0.375 1.32062094 401.4184815
#> 83 5 0.375 3.08405591 197.9457725
#> 84 6 0.375 5.38472985 37.5416149
#> 85 7 0.375 7.11864801 5.0996822
#> 86 8 0.375 7.17963979 7.6766516
#> 87 9 0.375 5.55130064 59.4024907
#> 88 10 0.375 3.30155234 228.2708772
#> 89 11 0.375 1.51392096 415.5768786
#> 90 12 0.375 0.53617983 529.7332481
#> 91 13 0.375 0.14686478 575.9244272
保存循环中生成的所有原子值的一般方法是在循环之前创建一个空向量，然后将新值附加到循环内的向量中。例如，
output <- vector()
for (i in 1:5) {
newvalue <- i
output <- c(output, newvalue)
}