使用purrr::map()调用lmer()正常，调用nlme::lme()报".x未找到"错误

运行nlme::lme()时收到如下错误：

Error in `map()`:
ℹ In index: 1.
ℹ With name: p_h.
Caused by error:
! object '.x' not found

测试数据 #

testdata <- structure(list(subject = c("B001", "B001", "B001", "B001", "B001", 
"B002", "B002", "B002", "B002", "B002", "B003", "B003", "B003", 
"B003", "B003", "B004", "B004", "B004", "B004", "B004", "B005", 
"B005", "B005", "B005", "B005"), time_point = structure(c(1L, 
2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L, 1L, 2L, 
3L, 4L, 5L, 1L, 2L, 3L, 4L, 5L), levels = c("Wk0", "Wk4", "Wk8", 
"Wk12", "Wk16"), class = "factor"), sfa = c(62.895, 84.705, 83.49, 
66.64, 72.19, 56.195, 93.945, 92.635, 88.51, 83.505, 92.67, 90.81, 
83.37, 90.205, 84.195, 88.065, 53.69, 93.14, 52.57, 95.995, 63.505, 
92.59, 80.87, 89.125, 67.305), mufa = c(14.455, 11.71, 12.58, 
21.135, 26.175, 13.285, 4.91, 6.08, 6.735, 12.745, 7.325, 7.605, 
15.735, 7.985, 12.32, 7.92, 42.045, 4.57, 24.305, 4.505, 18.585, 
5.955, 14.815, 8.775, 20.295), pufa = c(22.65, 3.58, 3.935, 12.23, 
1.635, 30.525, 1.135, 1.275, 4.76, 3.75, 0, 1.595, 0.885, 1.82, 
3.495, 4.01, 4.26, 2.29, 23.125, 0, 17.905, 1.455, 4.305, 2.1, 
12.4)), row.names = c(NA, -25L), class = c("tbl_df", "tbl", "data.frame"
))

可正常运行的lmer()代码 #

library(lme4)
library(nlme)
library(lmerTest)
library(broom.mixed)

testdata |>
  dplyr::select(sfa, mufa, pufa) |>
  purrr::map(~ lmer(.x ~ time_point + (1| subject), data = testdata)) 

出错的nlme::lme()代码 #

library(lme4)
library(nlme)
library(lmerTest)
library(broom.mixed)

testdata |>
  dplyr::select(sfa, mufa, pufa) |>
  purrr::map(~ lme(.x ~ time_point, random = ~ 1 | subject, 
            data = testdata, method = 'ML'))  

问题原因 #

lme()和lmer()的公式解析逻辑存在差异：

• lmer()允许直接引用环境中的对象（比如map()传入的.x向量）
• lme()会严格在data参数指定的数据框内查找变量，无法识别环境中的.x

解决方案 #

方法1：用reformulate()动态构建公式 #

针对每个因变量生成对应的公式，确保lme()能在数据框中找到变量：

testdata |>
  dplyr::select(sfa, mufa, pufa) |>
  purrr::imap(function(.x, .y) {
    lme(reformulate("time_point", response = .y),
        random = ~1 | subject, data = testdata, method = "ML")
  })

方法2：临时重命名因变量 #

遍历变量名，将当前因变量重命名为统一名称后再建模：

c("sfa", "mufa", "pufa") |>
  purrr::map(function(var) {
    testdata |>
      dplyr::mutate(y = .data[[var]]) |>
      lme(y ~ time_point, random = ~1 | subject, data = _, method = "ML")
  }) |>
  purrr::set_names(c("sfa", "mufa", "pufa"))

方法3：传递变量名而非向量 #

直接遍历变量名字符串，在公式中使用变量名：

testdata |>
  dplyr::select(sfa, mufa, pufa) |>
  names() |>
  purrr::map(function(var) {
    lme(as.formula(paste(var, "~ time_point")),
        random = ~1 | subject, data = testdata, method = "ML")
  }) |>
  purrr::set_names(c("sfa", "mufa", "pufa"))

内容的提问来源于stack exchange，提问作者KIM