如何正確隨機化此特定數據？

Question

我想隨機化測試及其版本的順序。 我的數據最后應該像這樣：

 > # subject Test t1 t2 t3 t4 > # 1 1 PFT ABCD > # 2 1 AWT BCDA > # 3 1 BWFT (...) > # 4 1 AUT > # 5 1 DPD-WN > # 6 1 DPT-NI > # 7 2 AWT > # (...) 250 

我發現了一些對我有幫助的東西：

seed <- 42 
blocksize <- 6
N <- 250 x 6

set.seed(seed)

subject = rep(1:ceiling(N/blocksize), each = blocksize)

a1 = data.frame(subject, rand=runif(length(subject)), envelope= 1:length(subject))

a2 = a1[order(a1$subject,a1$rand),]

a2$Test = rep(c("BWFT", "DPT-NI", "DPD-WN", "AUT", "PFT", "AWT"),times = length(subject)/6)

assign = a2[order(a2$envelope),]

head(assign,12)

你能幫我休息嗎？ 非常感謝你！

我越來越近：

(versions <- replicate(10, sample(c("A","B","C","D"), 4, replace=F)))

Answer 1

您可以使用以下方法生成所需值的矩陣

tt <- t(replicate(nrow(a2), sample(LETTERS[1:4])))
colnames(tt) <- paste0("t", 1:4)

然后將其合並到您的數據框中

a2 <- cbind(a2, tt)
head(a2)
#   subject      rand envelope   Test t1 t2 t3 t4
# 3       1 0.2861395        3   BWFT  A  B  D  C
# 6       1 0.5190959        6 DPT-NI  C  B  A  D
# 5       1 0.6417455        5 DPD-WN  D  B  A  C
# 4       1 0.8304476        4    AUT  D  C  A  B
# 1       1 0.9148060        1    PFT  C  A  B  D
# 2       1 0.9370754        2    AWT  B  D  A  C