GLMM：标准化与实尺度变量表示模型

Question

我在 glmm 调整之前标准化了输入变量，但在最终图中，我的变量和预测值的实际规模存在问题。在我的示例中：

我做：

#Packages
library(lme4)
library(ggplot2)
library(ggeffects)
library(tidyverse)
library(bbmle) 
library(broom)

#Open my dataset
myds<-read.csv("https://raw.githubusercontent.com/Leprechault/trash/main/ds.desenvol.csv")
str(myds)
# 'data.frame': 400 obs. of  4 variables:
#  $ temp       : num  0 0 0 0 0 0 0 0 0 0 ...
#  $ storage    : int  5 5 5 5 5 5 5 5 5 5 ...
#  $ rep        : chr  "r1" "r2" "r3" "r4" ...
#  $ development: int  0 23 22 27 24 25 24 22 0 22 ...

# Storage (days) is temporally correlated with temperature then mixed model
ds.scale<- myds %>%
  mutate(across(c(temp, storage), ~ drop(scale(.))))

# Models creation Poisson/Negative binomial
m_1 <- glmer(development ~ temp + storage +
               (1 | storage ), data = ds.scale, 
                 family = "poisson")
m_2 <- glmer(development ~ poly(temp,2) + storage +
               (1 | storage ), data = ds.scale, 
                 family = "poisson")  
m_3 <- glmer(development ~ poly(temp,2) + poly(storage,2) +
               (1 | storage ), data = ds.scale, 
                 family = "poisson")  
m_4 <- glmer.nb(development ~ temp + storage +
               (1 | storage ), data = ds.scale)
m_5 <- glmer.nb(development ~ poly(temp,2) + storage +
               (1 | storage ), data = ds.scale)  
m_6 <- glmer.nb(development ~ poly(temp,2) + poly(storage,2) +
               (1 | storage ), data = ds.scale)   
modList <- tibble::lst(m_1,m_2,m_3,m_4,m_5,m_6)
bbmle::AICtab(modList)

#     dAIC df
# m_6  0.0 7 
# m_3  1.0 6 
# m_5  3.3 6 
# m_2  5.0 5 
# m_4 17.9 5 
# m_1 21.0 4

# Plot the results for my better model (m_6)
mydf <- ggpredict(m_6, terms = c("temp [all]", "storage[all]"))

# For temp
ggplot(mydf, aes(x, predicted)) +
  geom_point(data=myds, aes(temp, development), alpha = 0.5) + 
  geom_line() +
  labs(x = "temp", y = "development")

# For storage
ggplot(mydf, aes(x, predicted)) +
  geom_point(data=myds, aes(storage, development), alpha = 0.5) + 
  geom_line() +
  labs(x = "storage", y = "development")
# -------------------------------------------------------------------------------------------  

但我希望在我更好的模型中表示我的 temp 和 storage 变量的原始规模（m_6）。 正确的做法是什么？ 尽管有警告，但不要标准化我的输入变量（模型几乎无法识别：非常大的特征值 - 重新缩放变量？）？ 最后进行一些数据转换？

请问有什么帮助吗？

Answer 1

基本思想是将非标准化变量的范围值与标准化变量的范围值进行映射，然后使用 ggplot 中的scale_x_...() 来更改标签。

library(datawizard)
library(lme4)
library(ggeffects)
library(ggplot2)

myds <- read.csv("https://raw.githubusercontent.com/Leprechault/trash/main/ds.desenvol.csv")
d.scale <- standardize(myds, select = c("temp", "storage"))
m_6 <- glmer.nb(development ~ poly(temp,2) + poly(storage,2) + (1 | storage ), data = d.scale)


# for temp
mydf <- ggpredict(m_6, terms = "temp [all]")

# retrieve center and scale from standardization
center_temp <- attributes(d.scale)$center["temp"]
scale_temp <- attributes(d.scale)$scale["temp"]

# scaled range, calculate back to range of unstandardized
scaled_range <- c(-1, 0, 1, 2)
new_range <- round(scaled_range * scale_temp + center_temp)

# scaled range
plot(mydf, add.data = TRUE)

# original range
plot(mydf, add.data = TRUE) +
  scale_x_continuous(
    breaks = scaled_range,
    labels = new_range
  )

# 用于存储
mydf <- ggpredict(m_6, terms = "存储[全部]")

# retrieve center and scale from standardization
center_storage <- attributes(d.scale)$center["storage"]
scale_storage <- attributes(d.scale)$scale["storage"]

# scaled range, calculate back to range of unstandardized
scaled_range <- c(-1, 0, 1)
new_range <- round(scaled_range * scale_storage + center_storage)

# scaled range
plot(mydf, add.data = TRUE)

# original range
plot(mydf, add.data = TRUE) +
  scale_x_continuous(
    breaks = scaled_range,
    labels = new_range
  )