如何合并haven标签向量层级以适配polychoric函数分析？

1. 为什么fct_collapse报错？ #

fct_collapse是forcats包中专门处理因子/字符向量的函数，但你从Stata导入的变量是haven_labelled类型（带标签的数值向量），直接调用会触发类型不匹配错误。需要用haven包的工具修改标签和值，同时保留原变量类型。

2. 合并未知类别并保留标签向量类型 #

针对那两个包含98(Refuse)、99(Don't Know)的变量，先将这两个值替换为1(DNA)，再统一更新标签为"Not known"，全程保留haven_labelled类型：

单变量处理示例 #

# 加载必要包
library(haven)
library(psych)

# 你的示例标签化变量
match <- labelled(c(7, 6, 4, 6, 3, 3, 2, 1, 3, 5, 99, 1, 3, 2, 2, 4, 5, 7, 8, 5, 98, 4, 6, 7, 4, 8, 4, 3, 4, 6, 7), 
                  c("DNA" = 1, "Never" = 2, "Rarely" = 3, "Less than half" = 4, 
                    "About half" = 5, "More than half" = 6, "Lots" = 7, "Always" = 8, 
                    "Refuse" = 98, "Don't know" = 99))

# 步骤1：将98、99替换为1
match[match %in% c(98, 99)] <- 1

# 步骤2：更新标签，移除98/99的标签，将1的标签改为"Not known"
match <- set_value_labels(match, 
                          "Not known" = 1,
                          "Never" = 2,
                          "Rarely" = 3,
                          "Less than half" = 4,
                          "About half" = 5,
                          "More than half" = 6,
                          "Lots" = 7,
                          "Always" = 8)

批量处理多个变量 #

如果有多个变量需要处理，写批量函数更高效：

# 定义批量处理函数
collapse_unknowns <- function(x) {
  # 替换98、99为1
  x[x %in% c(98, 99)] <- 1
  # 更新标签
  x <- set_value_labels(x, 
                        "Not known" = 1,
                        "Never" = 2,
                        "Rarely" = 3,
                        "Less than half" = 4,
                        "About half" = 5,
                        "More than half" = 6,
                        "Lots" = 7,
                        "Always" = 8)
  return(x)
}

# 假设需要处理的变量是var1和var2，应用函数到数据集df
df[, c("var1", "var2")] <- lapply(df[, c("var1", "var2")], collapse_unknowns)

3. 重新运行polychoric函数 #

处理完成后，所有变量的类别数都不超过8个，此时可以正常运行多重共线性分析：

cor_matrix <- polychoric(df)

内容的提问来源于stack exchange，提问作者VegetationLife