R语言在散点图中添加lm线性回归公式的问题
1. 简单的线性回归
函数自带的例子（r 中键入?lm），lm(y ~ x)回归y=kx + b， lm( y ~ x -1 )省略b，不对截距进行估计：
require(graphics)
## annette dobson (1990) "an introduction to generalized linear models".
## page 9: plant weight data.
ctl <- c(4.17,5.58,5.18,6.11,4.50,4.61,5.17,4.53,5.33,5.14)
trt <- c(4.81,4.17,4.41,3.59,5.87,3.83,6.03,4.89,4.32,4.69)
group <- gl(2, 10, 20, labels = c("ctl","trt"))
weight <- c(ctl, trt)
lm.d9 <- lm(weight ~ group)
lm.d90 <- lm(weight ~ group - 1) # omitting intercept
anova(lm.d9)
summary(lm.d90)
opar <- par(mfrow = c(2,2), oma = c(0, 0, 1.1, 0))
plot(lm.d9, las = 1) # residuals, fitted, ...
par(opar)
使用r中自带的mtcars数据，可以得到截距和斜率，也可以得到解释率r-square：
require(ggplot2)
library(dplyr) #加载dplyr包
library(ggpmisc) #加载ggpmisc包
library(ggpubr)
require(gridextra)
model=lm(mtcars$wt ~ mtcars$mpg)
model
## 输出：
call:
lm(formula = mtcars$wt ~ mtcars$mpg)
coefficients:
(intercept) mtcars$mpg
6.047 -0.141
```
```handlebars
summary(model)
## 输出：
call:
lm(formula = mtcars$wt ~ mtcars$mpg)
residuals:
min 1q median 3q max
-0.652 -0.349 -0.138 0.319 1.368
coefficients:
estimate std. error t value pr(>|t|)
(intercept) 6.0473 0.3087 19.59 < 2e-16 ***
mtcars$mpg -0.1409 0.0147 -9.56 1.3e-10 ***
---
signif. codes: 0 ‘***' 0.001 ‘**' 0.01 ‘*' 0.05 ‘.' 0.1 ‘ ' 1
residual standard error: 0.494 on 30 degrees of freedom
multiple r-squared: 0.753, adjusted r-squared: 0.745
f-statistic: 91.4 on 1 and 30 df, p-value: 1.29e-10
提取回归r-square值：
通过summary提取： ## 上面的例子 ## mtcars例子 model=lm(mtcars$wt ~ mtcars$mpg) res=summary(model) str(res) ## 提取各个值： res$r.squared res$coefficients res$adj.r.squared ## df 矫正后的结果 res$coefficients[1,1] res$coefficients[2,1]
使用默认的plot绘制回归散点：
plot(mtcars$mpg, mtcars$wt, pch=20,cex=2) abline(model,col="red",lwd=2)
计算confidence interval（95%）：
test=mtcars[c("mpg","wt")]
head(test)
colnames(test)=c("x","y")
model = lm(y ~ x, test)
test$predicted = predict(
object = model,
newdata = test)
test$ci = predict(
object = model,
newdata = test,
se.fit = true
)$se.fit * qt(1 - (1-0.95)/2, nrow(test))
test$predicted = predict(
object = model,
newdata = test)
test$ci_u=test$predicted+test$ci
test$ci_l=test$predicted-test$ci
plot(mtcars$mpg, mtcars$wt, pch=20,cex=1) ## have replicated x values
abline(model,col="red",lwd=2)
lines(x=test$x,y=test$ci_u,col="blue")
lines(x=test$x,y=test$ci_l,col="blue")
上面的图蓝线有点奇怪，简单绘制最初的plot：
plot(mtcars$mpg, mtcars$wt, pch=20,cex=1,type="b") ## have replicated x values
实际上面的计算方法没问题，但是数据不合适，因为数据x含有重复值，所以要考虑这个。
2. 使用ggplot2展示
ggplot2例子：
p <- ggplot(df, aes(x=yreal, y=ypred)) +
geom_point(color = "grey20",size = 1, alpha = 0.8)
#回归线
#添加回归曲线
p2 <- p + geom_smooth(formula = y ~ x, color = "red",
fill = "blue", method = "lm",se = t, level=0.95) +
theme_bw() +
stat_poly_eq(
aes(label = paste(..eq.label.., ..adj.rr.label.., sep = '~~~')),
formula = y ~ x, parse = true,color="blue",
size = 5, #公式字体大小
label.x = 0.05, #位置 ，0-1之间的比例
label.y = 0.95) +
labs(title="test",x="real value (huang huaihai 1777)" , y="predicted value (correlation: 0.5029)")
p2
ggplot版本的手动计算：
require(ggplot2)
library(dplyr) #加载dplyr包
library(ggpmisc) #加载ggpmisc包
library(ggpubr)
require(gridextra)
ggplot(data=df, aes(x=yreal, y=ypred)) +
geom_smooth(formula = y ~ x, color = "blue",
fill = "grey10", method = "lm") +
geom_point() +
stat_regline_equation(label.x=0.1, label.y=-1.5) +
stat_cor(aes(label=..rr.label..), label.x=0.1, label.y=-2)
test=df
head(test)
colnames(test)=c("x","y")
model = lm(y ~ x, test)
test$predicted = predict(
object = model,
newdata = test)
test$ci = predict(
object = model,
newdata = test,
se.fit = true
)$se.fit * qt(1 - (1-0.95)/2, nrow(test))
ggplot(test) +
aes(x = x, y = y) +
geom_point(size = 1,colour="grey40") +
geom_smooth(formula =y ~ x,method = "lm", fullrange = true, color = "black") +
geom_line(aes(y = predicted + ci), color = "blue") + # upper
geom_line(aes(y = predicted - ci), color = "red") + # lower
theme_classic()
参考：
https://stackoverflow.com/questions/23519224/extract-r-square-value-with-r-in-linear-models （提取r2）
https://blog.csdn.net/leaningr/article/details/118971000 （提取r2等）
https://stackoverflow.com/questions/45742987/how-is-level-used-to-generate-the-confidence-interval-in-geom-smooth （添加lm线）
https://zhuanlan.zhihu.com/p/131604431 （知乎）
到此这篇关于r语言在散点图中添加lm线性回归公式的问题的文章就介绍到这了,更多相关r语言线性回归内容请搜索萬仟网以前的文章或继续浏览下面的相关文章希望大家以后多多支持萬仟网！
看完文章，还可以扫描下面的二维码下载快手极速版领4元红包
除了扫码领红包之外，大家还可以在快手极速版做签到，看视频，做任务，参与抽奖，邀请好友赚钱）。
邀请两个好友奖最高196元，如下图所示：
