一文搞定R语言拟合p值、R方...

R:ggplot2拟合，我推荐geom_smooth绘制拟合和ggpmisc添加统计信息。

几行代码就可以搞定了，对新手非常友好。

线性拟合

library(tidyverse)
library(readxl)
library(ggplot2)
library(ggpmisc)

repeat1_rawgrassland <- 
  read_excel("D:/OneDrive/Untitled Folder/R/repeat1-rawgrassland.xlsx")
colnames(repeat1_rawgrassland)[5] <- 'EE'

# 线性拟合
repeat1_rawgrassland %>% 
  ggplot(aes(x=latitude, y=EE)) +
  geom_point(color='#4a86e8', size=5) +
  geom_smooth(method = 'lm') +
  stat_fit_deviations(formula = y ~ x, color = "skyblue") +
  stat_poly_eq(use_label(c("eq", "adj.R2", "p.value.label")),
    formula = y ~ x,  parse = TRUE,
      size = 5, #公式字体大小
      label.x = 0.05,  #位置 ，0-1之间的比例
      label.y = 0.95)

# 自行查看拟合
model <- lm(EE~latitude,data=repeat1_rawgrassland)
values <- summary(model)

这是最简单的拟合方法，当然这张图还有很多优化的空间，如颜色、刻度等等。现在对代码进行说明：

• sta_fit_deviations用于添加点与拟合线的连接直线，如不需要，可删去

• stat_poly_eq第一个参数是所需的统计量，可以选择需要的值

• label.xy都是相对于轴的大小，是百分比，不再是刻度值了

多项式拟合

# 多项式拟合
repeat1_rawgrassland %>% 
  ggplot(aes(x=latitude, y=EE)) +
  geom_point(color='#4a86e8', size=5) +
  geom_smooth(method = 'lm', formula = y ~ poly(x,3)) +
  stat_fit_deviations(formula = y ~ poly(x,3), color = "skyblue") +
  stat_poly_eq(use_label(c("eq", "adj.R2", "p.value.label")),
    formula = y ~ poly(x,3),  parse = TRUE,
      size = 5, #公式字体大小
      label.x = 0.05,  #位置 ，0-1之间的比例
      label.y = 0.95)

# 自行查看拟合
model <- lm(EE~poly(latitude, 3),data=repeat1_rawgrassland)
values <- summary(model)

好了，我们已经明白了拟合的基本原理了，下面来看一张完备的图吧

library(ggplot2)
library(tidyverse)
theme_set(theme_bw())  # pre-set the bw theme.
data("midwest", package = "ggplot2")
# midwest <- read.csv("http://goo.gl/G1K41K")  # bkup data source

# Scatterplot
ggplot(midwest, aes(x=area, y=poptotal)) + 
  geom_point(aes(col=state, size=popdensity)) + 
  geom_smooth(method="loess", se=F) + 
  xlim(c(0, 0.1)) + 
  ylim(c(0, 500000)) + 
  labs(subtitle="Area Vs Population", 
       y="Population", 
       x="Area", 
       title="Scatterplot", 
       caption = "Source: midwest")

references:

https://github.com/cran/ggpmisc