使用 broom::tidy 对 GAM 系数和置信区间取幂

如何解决使用 broom::tidy 对 GAM 系数和置信区间取幂

我正在使用 mgcv::gam 运行广义加性模型，并尝试使用 broom:tidy 来组织我的结果，但是 tidy 显然不会对 GAM 的系数或置信区间取幂，尽管它确实适用于常规 glm 模型。是否有 broom::tidy 方法可以对来自 GAM 的系数和 CI 取幂？我专门询问 tidy，因为我想使用 gtsummary 创建的回归表中的结果。

library(tidyverse)
library(magrittr)
library(mgcv)
library(parameters)
library(gtsummary)
library(broom)

# sample data

id <- 1:2000
gender <- sample(0:1,2000,replace = T)
age <- sample(17:64,replace = T)
race <- sample(0:1,replace = T)
health_score <- sample(0:25,replace = T)
dead <- sample(0:1,replace = T)
days_enrolled <- sample(30:3000,replace = T)

df <- data.frame(id,gender,age,race,health_score,dead,days_enrolled)

# model

model <- gam(dead ~ gender + s(age) + race + s(health_score) + offset(log(days_enrolled)),data = df,method = "REML",family = nb())

# both give the same output:

tidy(model,parametric = T,conf.int = T)
tidy(model,conf.int = T,exponentiate = T)

解决方法

您可以直接使用 tbl_regression() 对结果求幂。如果这不是您想要的，请告诉我。

library(tidyverse)
library(mgcv)
library(parameters)
library(gtsummary)
library(broom)

# sample data

id <- 1:2000
gender <- sample(0:1,2000,replace = T)
age <- sample(17:64,replace = T)
race <- sample(0:1,replace = T)
health_score <- sample(0:25,replace = T)
dead <- sample(0:1,replace = T)
days_enrolled <- sample(30:3000,replace = T)

df <- data.frame(id,gender,age,race,health_score,dead,days_enrolled)

# model

model <- gam(dead ~ gender + s(age) + race + s(health_score) + offset(log(days_enrolled)),data = df,method = "REML",family = nb())


tbl_regression(model,exponentiate = TRUE)