如何在R中基于多向量迭代运行多个fixest回归？

完全可以实现这种批量回归，下面是具体的实现思路和代码：

实现步骤 #

1. 生成所有回归组合
   通过expand.grid()生成officer_race、primary_ind、outcome三个向量的所有笛卡尔积组合，确保覆盖所有需要运行的回归场景。

2. 批量执行回归并收集结果
   用purrr包的pmap()函数遍历每个组合，针对每个组合完成：

   • 筛选对应警官种族的数据集子集
   • 检查当前回归的因变量和自变量是否存在于数据中（避免因数据缺失变量报错）
   • 若变量存在且子集非空，运行feols()回归；否则返回对应提示信息

完整代码 #

# 加载所需包
library(fixest)
library(tibble)
library(purrr)

# 用户提供的数据
analysis <- tibble(
  off_race = c("hispanic", "hispanic", "white","white", "hispanic", "white", "hispanic", "white", "white", "white","hispanic"),
  any_black_uof = c(FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE),
  any_black_arrest = c(TRUE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE, FALSE),
  prop_white_scale = c(0.866619646027524, -1.14647499712298, 1.33793539994219, 0.593565300512359, -0.712819809606193, 0.3473585867755, -1.37025501425243, 1.16596624239715, 0.104521426674564, 0.104521426674564, -1.53728347122581),
  prop_hisp_scale = c(-0.347382203637802, 1.54966785579018, 
                      -0.833021026477168, -0.211470492567308, 1.48353691981021, 
                      0.421968013870802, 2.63739845069911, -0.61002505397242, 0.66674880256898,0.66674880256898, 2.93190487813111)
)

# 需遍历的向量组
officer_race = c("black", "white", "hispanic")
primary_ind <- c("prop_white_scale","prop_hisp_scale","prop_black_scale")
outcome <- c("any_black_uof","any_white_uof","any_hisp_uof","any_black_arrest","any_white_arrest","any_hisp_arrest","any_black_stop","any_white_stop","any_hisp_stop")

# 生成所有回归组合
reg_combinations <- expand.grid(
  officer_race = officer_race,
  primary_ind = primary_ind,
  outcome = outcome,
  stringsAsFactors = FALSE
)

# 批量运行回归
reg_results <- pmap(reg_combinations, function(officer_race, primary_ind, outcome) {
  # 筛选对应种族的数据集
  data_subset <- analysis[analysis$off_race == officer_race, ]
  
  # 检查变量是否存在于数据中
  if (!all(c(outcome, primary_ind) %in% colnames(data_subset))) {
    return(paste("变量缺失：", paste(setdiff(c(outcome, primary_ind), colnames(data_subset)), collapse = ", ")))
  }
  
  # 检查子集是否非空
  if (nrow(data_subset) == 0) {
    return(paste("无对应种族数据：", officer_race))
  }
  
  # 构建公式并运行回归
  formula <- as.formula(paste(outcome, "~", primary_ind))
  feols(formula, data = data_subset)
})

# 给结果列表命名，方便识别
names(reg_results) <- with(reg_combinations, paste(outcome, "~", primary_ind, "|", officer_race))

# 查看结果示例（比如前5个）
reg_results[1:5]

注意事项 #

• 你提供的analysis数据中缺少prop_black_scale、any_white_uof等多个变量，代码中加入了变量存在性检查，避免运行报错，这类情况会返回对应的提示信息。
• 对于officer_race = "black"的情况，当前数据中没有对应行，代码会返回“无对应种族数据：black”的提示。

内容的提问来源于stack exchange，提问作者sd3184