从lm汇总系数 [英] Tabulate coefficients from lm

问题描述

我有10个线性模型，其中我只需要一些信息，即:r平方，p值，斜率和截距系数.我设法提取了这些值(通过荒谬地重复代码).现在，我需要将这些值制成表格(列中的信息；行列出了线性模型1-10的结果).谁能帮帮我吗?我还有数百个线性模型要做.我确定一定有办法.

I have 10 linear models where I only need some information, namely: r-squared, p-value, coefficients of slope and intercept. I managed to extract these values (via ridiculously repeating the code). Now, I need to tabulate these values (Info in the columns; the rows listing results from linear models 1-10). Can anyone please help me? I have hundreds more linear models to do. I'm sure there must be a way.

托管在此处的数据文件

代码:

d<-read.csv("example.csv",header=T)

# Subset data
A3G1 <- subset(d, CatChro=="A3G1"); A4G1 <- subset(d, CatChro=="A4G1")
A3G2 <- subset(d, CatChro=="A3G2"); A4G2 <- subset(d, CatChro=="A4G2")
A3G3 <- subset(d, CatChro=="A3G3"); A4G3 <- subset(d, CatChro=="A4G3")
A3G4 <- subset(d, CatChro=="A3G4"); A4G4 <- subset(d, CatChro=="A4G4")
A3G5 <- subset(d, CatChro=="A3G5"); A4G5 <- subset(d, CatChro=="A4G5")
A3D1 <- subset(d, CatChro=="A3D1"); A4D1 <- subset(d, CatChro=="A4D1")
A3D2 <- subset(d, CatChro=="A3D2"); A4D2 <- subset(d, CatChro=="A4D2")
A3D3 <- subset(d, CatChro=="A3D3"); A4D3 <- subset(d, CatChro=="A4D3")
A3D4 <- subset(d, CatChro=="A3D4"); A4D4 <- subset(d, CatChro=="A4D4")
A3D5 <- subset(d, CatChro=="A3D5"); A4D5 <- subset(d, CatChro=="A4D5")

# Fit individual lines
rA3G1 <- lm(Qend~Rainfall, data=A3G1); summary(rA3G1)
rA3D1 <- lm(Qend~Rainfall, data=A3D1); summary(rA3D1)
rA3G2 <- lm(Qend~Rainfall, data=A3G2); summary(rA3G2)
rA3D2 <- lm(Qend~Rainfall, data=A3D2); summary(rA3D2)
rA3G3 <- lm(Qend~Rainfall, data=A3G3); summary(rA3G3)
rA3D3 <- lm(Qend~Rainfall, data=A3D3); summary(rA3D3)
rA3G4 <- lm(Qend~Rainfall, data=A3G4); summary(rA3G4)
rA3D4 <- lm(Qend~Rainfall, data=A3D4); summary(rA3D4)
rA3G5 <- lm(Qend~Rainfall, data=A3G5); summary(rA3G5)
rA3D5 <- lm(Qend~Rainfall, data=A3D5); summary(rA3D5)

rA4G1   <- lm(Qend~Rainfall, data=A4G1); summary(rA4G1)
rA4D1   <- lm(Qend~Rainfall, data=A4D1); summary(rA4D1)
rA4G2   <- lm(Qend~Rainfall, data=A4G2); summary(rA4G2)
rA4D2   <- lm(Qend~Rainfall, data=A4D2); summary(rA4D2)
rA4G3   <- lm(Qend~Rainfall, data=A4G3); summary(rA4G3)
rA4D3   <- lm(Qend~Rainfall, data=A4D3); summary(rA4D3)
rA4G4   <- lm(Qend~Rainfall, data=A4G4); summary(rA4G4)
rA4D4   <- lm(Qend~Rainfall, data=A4D4); summary(rA4D4)
rA4G5   <- lm(Qend~Rainfall, data=A4G5); summary(rA4G5)
rA4D5   <- lm(Qend~Rainfall, data=A4D5); summary(rA4D5)

# Gradient
summary(rA3G1)$coefficients[2,1]
summary(rA3D1)$coefficients[2,1]
summary(rA3G2)$coefficients[2,1]
summary(rA3D2)$coefficients[2,1] 
summary(rA3G3)$coefficients[2,1] 
summary(rA3D3)$coefficients[2,1] 
summary(rA3G4)$coefficients[2,1] 
summary(rA3D4)$coefficients[2,1] 
summary(rA3G5)$coefficients[2,1] 
summary(rA3D5)$coefficients[2,1]

# Intercept
summary(rA3G1)$coefficients[2,2] 
summary(rA3D1)$coefficients[2,2] 
summary(rA3G2)$coefficients[2,2] 
summary(rA3D2)$coefficients[2,2] 
summary(rA3G3)$coefficients[2,2] 
summary(rA3D3)$coefficients[2,2] 
summary(rA3G4)$coefficients[2,2] 
summary(rA3D4)$coefficients[2,2] 
summary(rA3G5)$coefficients[2,2] 
summary(rA3D5)$coefficients[2,2] 

# r-sq
summary(rA3G1)$r.squared
summary(rA3D1)$r.squared
summary(rA3G2)$r.squared
summary(rA3D2)$r.squared
summary(rA3G3)$r.squared
summary(rA3D3)$r.squared
summary(rA3G4)$r.squared
summary(rA3D4)$r.squared
summary(rA3G5)$r.squared
summary(rA3D5)$r.squared

# adj r-sq
summary(rA3G1)$adj.r.squared
summary(rA3D1)$adj.r.squared
summary(rA3G2)$adj.r.squared
summary(rA3D2)$adj.r.squared
summary(rA3G3)$adj.r.squared
summary(rA3D3)$adj.r.squared
summary(rA3G4)$adj.r.squared
summary(rA3D4)$adj.r.squared
summary(rA3G5)$adj.r.squared
summary(rA3D5)$adj.r.squared

# p-level
p <- summary(rA3G1)$fstatistic
pf(p[1], p[2], p[3], lower.tail=FALSE) 
p2 <- summary(rA3D1)$fstatistic
pf(p2[1], p2[2], p2[3], lower.tail=FALSE) 
p3 <- summary(rA3G2)$fstatistic
pf(p3[1], p3[2], p3[3], lower.tail=FALSE) 
p4 <- summary(rA3D2)$fstatistic
pf(p4[1], p4[2], p4[3], lower.tail=FALSE) 
p5 <- summary(rA3G3)$fstatistic
pf(p5[1], p5[2], p5[3], lower.tail=FALSE) 
p6 <- summary(rA3D3)$fstatistic
pf(p6[1], p6[2], p6[3], lower.tail=FALSE) 
p7 <- summary(rA3G4)$fstatistic
pf(p7[1], p7[2], p7[3], lower.tail=FALSE) 
p8 <- summary(rA3D4)$fstatistic
pf(p8[1], p8[2], p8[3], lower.tail=FALSE) 
p9 <- summary(rA3G5)$fstatistic
pf(p9[1], p9[2], p9[3], lower.tail=FALSE) 
p10 <- summary(rA3D5)$fstatistic
pf(p10[1], p10[2], p10[3], lower.tail=FALSE) 

这是我预期结果的结构:

This is the structure of my expected outcome:

有什么办法可以做到这一点?

Is there any way to achieve this?

推荐答案

这是基本的R解决方案:

Here is a base R solution:

data <- read.csv("./data/so53933238.csv",header=TRUE)

# split by value of CatChro into a list of datasets
dataList <- split(data,data$CatChro)

# process the list with lm(), extract results to a data frame, write to a list
lmResults <- lapply(dataList,function(x){
     y <- summary(lm(Qend ~ Rainfall,data = x))
     Intercept <- y$coefficients[1,1]
     Slope <- y$coefficients[2,1]
     rSquared <- y$r.squared
     adjRSquared <- y$adj.r.squared
     f <- y$fstatistic[1]
     pValue <- pf(y$fstatistic[1],y$fstatistic[2],y$fstatistic[3],lower.tail = FALSE)
     data.frame(Slope,Intercept,rSquared,adjRSquared,pValue)
})
lmResultTable <- do.call(rbind,lmResults)
# add CatChro indicators
lmResultTable$catChro <- names(dataList)

lmResultTable 

...以及输出:

    > lmResultTable
            Slope   Intercept   rSquared  adjRSquared       pValue catChro
A3D1 0.0004085644 0.011876543 0.28069553  0.254054622 0.0031181110    A3D1
A3D2 0.0005431693 0.023601325 0.03384173  0.005425311 0.2828170556    A3D2
A3D3 0.0001451185 0.022106960 0.04285322  0.002972105 0.3102578215    A3D3
A3D4 0.0006614213 0.009301843 0.37219027  0.349768492 0.0003442445    A3D4
A3D5 0.0001084626 0.014341399 0.04411669 -0.008987936 0.3741011769    A3D5
A3G1 0.0001147645 0.024432020 0.03627553  0.011564648 0.2329519751    A3G1
A3G2 0.0004583538 0.026079409 0.06449971  0.041112205 0.1045970987    A3G2
A3G3 0.0006964512 0.043537869 0.07587433  0.054383038 0.0670399684    A3G3
A3G4 0.0006442175 0.023706652 0.17337420  0.155404076 0.0032431299    A3G4
A3G5 0.0006658466 0.025994831 0.17227383  0.150491566 0.0077413595    A3G5
>

要以HTML表格格式呈现输出，可以使用knitr::kable().

To render the output in a tabular format in HTML, one can use knitr::kable().

library(knitr)
kable(lmResultTable[1:5],row.names=TRUE,digits=5) 

...在渲染Markdown之后产生以下输出:

...which produces the following output after rendering the Markdown:

这篇关于从lm汇总系数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！