Question

这是follow up question。上一个问题的答案是进行随机抽样和替换。如何更改代码，以便将每个观察分配到J＆＃34; urn＆＃34;没有将观察结果放回＆＃39;彩票＆＃39;

这是我现在的代码：

set.seed(9782)
I <- 500
g <- 10
library(dplyr)

anon_id <- function(n = 1, lenght = 12) {
  randomString <- c(1:n)
  for (i in 1:n)
  {
    randomString[i] <- paste(sample(c(0:9, letters, LETTERS),
                                    lenght, replace = TRUE),
                             collapse = "")
  }
  return(randomString)
}

df <- data.frame(id = anon_id(n = I, lenght = 16),
                 group = sample(1:g, I, T))

J <- 3
p <- c(0.25, 0.5, 0.25)

randomize <- function(data, urns=2, block_id = NULL, p=NULL, seed=9782) {
  if(is.null(p)) p <- rep(1/urns, urns) 
  if(is.null(block_id)){
    df1 <- data %>% 
      mutate(Treatment = sample(x = c(1:urns), 
                                size = n(), 
                                replace = T, 
                                prob = p))
    return(df1)
  }else{
    df1 <- data %>% group_by_(block_id) %>% 
      mutate(Treatment = sample(x = c(1:urns), 
                                size = n(), 
                                replace = T, 
                                prob = p))
  }
}    

df1 <- randomize(data = df, urns = J, block_id = "group", p = p, seed = 9782)

如果我将replace = T更改为replace = F，我会收到以下错误：

 Error: cannot take a sample larger than the population when 'replace = FALSE'

澄清我的目标：

假设我有10个教室（或村庄，或类似的东西）。为了简单起见，假设每个教室有20名学生（实际上他们将有N_j）。每个教室的课堂，我想将每个学生分配给J个小组中的一个，例如J=3。 P表示将分配给每个组的分数。例如25％到1组40％到组2,35％到组3。

Answer 1

此解决方案基于@Frank的评论。我创建了一个函数来执行块j的随机化，另一个函数为每个块调用该函数。

randomize_block <- function(data, block=NULL, block_name=NULL, urns, p, seed=9782) {
  set.seed(seed)
  if(!is.null(block)) {
    condition <- paste0(block_name,"==",block)
    df <- data %>% filter_(condition)
  } else df <- data
  if(is.null(p)) p <- rep(1/urns, urns) 
  N <- nrow(df)
  Np <- round(N*p,0)
  if(sum(Np)!=N) Np[1] <- N - sum(Np[2:length(Np)])
  Urns = rep(seq_along(p), Np)
  Urns = sample(Urns)
  df$urn <- Urns
  return(df)
}   

randomize <- function(data, block_name=NULL, urns, p, seed=9782) {
  if(is.null(p)) p <- rep(1/urns, urns)
  if(!is.null(block_name)){
    blocks <- unique(data[,block_name])
    df <- lapply(blocks, randomize_block, 
                 data = data, 
                 block_name=block_name, 
                 urns = urns, 
                 p = p, 
                 seed=seed)
    return(data.table::rbindlist(df))
  }else {
    df <- randomize_block(data = data,  
                          urns = urns, p = p, 
                          seed=seed)
  }
}

test <- randomize(data = df, block_name = "group", 
                  urns = 3, p = c(0.25, 0.5, 0.25), 
                  seed=4222016)

我试图弄清楚是否可以使用dplyr来执行此操作，实施该功能的替代解决方案非常受欢迎！

Answer 2

My answer to your other question无法替换，如下所示：


block_rand <-  as.tibble(randomizr::block_ra(blocks = df$group, conditions = c("urn_1","urn_2","urn_3")))

df2 <- as.tibble(bind_cols(df, block_rand))

df2 %>% janitor::tabyl(group, value) 

df2 %>%
  group_by(id) %>% 
  filter(n()>1) %>%
  str()

按组（块）随机化观察，无需替换

2 个答案: