是否可以将线性模型的p值添加到tbl_summary中

发布于02月12日

我有非糖尿病、糖尿病前期和糖尿病患者的C-react 蛋白(CRP)值的数据.我使用tbl_summary来获取这三个组的中位数，并对差异进行统计检验.然而，我还想在这个表格中再增加一个p-value，这个表格是根据Age和Sex调整后的linear regression.有人能帮帮我吗？以下是我的代码

oxid <- c('ALT','AST', 'CRP')

sampled_df %>%  
tbl_summary(by = DiabetesStatus, 
include = oxid, 
type = all_continuous() ~ "continuous2", 
statistic = all_continuous() ~ c("{mean} ({sd})"), 
missing_text = "missing") %>% 
add_p()

这是我的线性回归模型，根据年龄、性别和BMI进行调整.

lm(ALT ~ DiabetesStatus + Age + Sex + BMI, sampled_df) |> broom::tidy() 
lm(AST ~ DiabetesStatus + Age + Sex + BMI, sampled_df) |> broom::tidy() 
lm(CRP ~ DiabetesStatus + Age + Sex + BMI, sampled_df) |> broom::tidy()

我想把p值DiabetesStatus加到上面的tbl_summary上.以下是我的数据样本.

structure(list(ALT = c(46, 49, 47, NA, 68, 66, 40, 42, 52, 30, 
47, 35, 32, 37, 42, 28, 33, 46, 17.4, 33, NA, 45, 64, 64, 32, 
NA, 33.7, 17, 32, 67, 31, 13, 35, 30, 28, 44.2, 48, 37, 33, 33, 
48, 44, 58, 18.4, 48, 28, 74, 50), AST = c(27, 24, NA, NA, 34, 
34, 17, 22, 33, 16, 19, 26, 15, 19, 19, 17, 19, 21, 19.7, 13, 
NA, 24, 31, 46, 23, NA, 19.3, 19, 19, 29, 43, 14, 22, 14, 23, 
26.5, 31, 24, 16, 17, 30, 25, 28, 17.7, 31, 18, 35, 34), CRP = c(3, 
5, 3, NA, 3, 2, 2, NA, 0.9, 2.9, 1, 1, 2, 1, 4, 1, NA, 5, 3, 
1, NA, 1, 4, 1, 8, NA, 3, 3, 2.7, 3, 3, NA, 7, 1, 2, 2, 1, 2, 
4, 3, 1, 1, 3, 3, 1, 1, 3, 3), DiabetesStatus = structure(c(1L, 
3L, 1L, 1L, 1L, 2L, 2L, 3L, 2L, 2L, 3L, 2L, 1L, 1L, 1L, 2L, 1L, 
2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 3L, 2L, 2L, 1L, 3L, 2L, 2L, 
3L, 1L, 3L, 1L, 2L, 3L, 3L, 2L, 3L, 1L, 1L, 1L, 1L, 3L, 1L), levels = c("Non-diabetic", 
"Pre-diabetic", "Diabetic"), class = "factor"), Age = c(51, 55, 
32, 52, 40, 48, 40, 57, 34, 48, 64, 46, 30, 37, 37, 48, 54, 45, 
48, 48, 62, 36, 49, 52, 49, 60, 54, 35, 53, 50, 55, 42, 66, 49, 
25, 52, 26, 48, 47, 59, 34, 71, 45, 41, 29, 37, 42, 51), BMI = c(24.7, 
28.8, 35.8, 26.9, 33.6, 29.7, 31, 39, 23, 23.5, 31.9, 25.6, 24.6, 
27.4, 30.6, 25.6, 28.3, 34.3, 32.6, 21.3, 25.1, 26.4, 43, 25.7, 
30.4, 25.2, 26.1, 26, 34.8, 34.4, 40.6, 40.1, 36.8, 26, 18.6, 
26.6, 22.8, 22.7, 31.7, 32.5, 28.6, 22.9, 24.7, 25.9, 22.8, 32.4, 
30.9, 21.4), Sex = structure(c(1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 
2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 
1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 
2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L), levels = c("Female", "Male"), class = "factor")), row.names = c(NA, 
-48L), class = c("tbl_df", "tbl", "data.frame"))

library(gtsummary) packageVersion("gtsummary") #> [1] '1.7.2' sampled_df <- structure(list(ALT = c(46, 49, 47, NA, 68, 66, 40, 42, 52, 30, 47, 35, 32, 37, 42, 28, 33, 46, 17.4, 33, NA, 45, 64, 64, 32, NA, 33.7, 17, 32, 67, 31, 13, 35, 30, 28, 44.2, 48, 37, 33, 33, 48, 44, 58, 18.4, 48, 28, 74, 50), AST = c(27, 24, NA, NA, 34, 34, 17, 22, 33, 16, 19, 26, 15, 19, 19, 17, 19, 21, 19.7, 13, NA, 24, 31, 46, 23, NA, 19.3, 19, 19, 29, 43, 14, 22, 14, 23, 26.5, 31, 24, 16, 17, 30, 25, 28, 17.7, 31, 18, 35, 34), CRP = c(3, 5, 3, NA, 3, 2, 2, NA, 0.9, 2.9, 1, 1, 2, 1, 4, 1, NA, 5, 3, 1, NA, 1, 4, 1, 8, NA, 3, 3, 2.7, 3, 3, NA, 7, 1, 2, 2, 1, 2, 4, 3, 1, 1, 3, 3, 1, 1, 3, 3), DiabetesStatus = structure(c(1L, 3L, 1L, 1L, 1L, 2L, 2L, 3L, 2L, 2L, 3L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 2L, 2L, 2L, 1L, 3L, 2L, 2L, 1L, 3L, 2L, 2L, 3L, 1L, 3L, 1L, 2L, 3L, 3L, 2L, 3L, 1L, 1L, 1L, 1L, 3L, 1L), levels = c("Non-diabetic", "Pre-diabetic", "Diabetic"), class = "factor"), Age = c(51, 55, 32, 52, 40, 48, 40, 57, 34, 48, 64, 46, 30, 37, 37, 48, 54, 45, 48, 48, 62, 36, 49, 52, 49, 60, 54, 35, 53, 50, 55, 42, 66, 49, 25, 52, 26, 48, 47, 59, 34, 71, 45, 41, 29, 37, 42, 51), BMI = c(24.7, 28.8, 35.8, 26.9, 33.6, 29.7, 31, 39, 23, 23.5, 31.9, 25.6, 24.6, 27.4, 30.6, 25.6, 28.3, 34.3, 32.6, 21.3, 25.1, 26.4, 43, 25.7, 30.4, 25.2, 26.1, 26, 34.8, 34.4, 40.6, 40.1, 36.8, 26, 18.6, 26.6, 22.8, 22.7, 31.7, 32.5, 28.6, 22.9, 24.7, 25.9, 22.8, 32.4, 30.9, 21.4), Sex = structure(c(1L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 2L, 1L, 1L, 1L, 2L, 1L, 1L, 1L, 1L, 1L, 1L, 2L, 1L, 2L, 1L, 2L, 2L, 2L, 2L, 2L, 1L, 2L, 2L, 1L, 2L, 2L), levels = c("Female", "Male"), class = "factor")), row.names = c(NA, -48L), class = c("tbl_df", "tbl", "data.frame")) oxid <- c('ALT','AST', 'CRP') adjusted_p <- function(data, variable, by, ...) { reformulate(c(by, c("Age", "BMI", "Sex")), response = variable) |> lm(data = data) |> broom::tidy() |> head(1) |> dplyr::mutate(method = "ANCOVA: Adjusted for Age, BMI, and Sex") } tbl <- sampled_df |> tbl_summary( by = DiabetesStatus, include = all_of(oxid), type = all_continuous() ~ "continuous2", statistic = all_continuous() ~ c("{mean} ({sd})"), missing_text = "missing" ) |> add_p(test = ~adjusted_p)

是否可以将线性模型的p值添加到tbl_summary中

推荐答案

R相关问答推荐

更改网格的crs以匹配简单要素点对象的crs

通过绘图 Select 线串几何体并为其着色

使用预定值列表将模拟数量(n)替换为rnorm()

对lme 4对象运行summary()时出错(diag中的错误(from，names = RST)：对象unpackedMatrix_diag_get找不到)

r—绘制相交曲线

R Sapply函数产生的值似乎与for循环方法略有不同

gganimate在使用shadow_mark选项时不保留所有过go 的标记

为什么舍入POSIXct会更改能力以匹配等效的POSIXct？

合并DFS列表并将索引提取为新列

使用data.table：：fcase()而不是dplyr：：case_When()时保持值

用约翰逊分布进行均值比较

从服务器在Shiny中一起渲染图标和文本

按时间顺序对不同事件进行分组

将多个变量组合成宽格式

循环遍历多个变量，并将每个变量插入函数R

有没有办法将基于每个值中出现的两个关键字或短语的字符串向量重新编码为具有这两个值的新向量？

在生成打印的自定义函数中，可以通过变量将线型或 colored颜色设置为NULL吗？

无法保存gglot的所有pdf元素

根据用户输入更改标记大小和 colored颜色 (R)

如何在类应用函数中访问函数本身