Używałem tej funkcji lmp dość dużo razy.
W pewnym momencie zdecydowałem się dodać nowe funkcje, aby ulepszyć analizę danych. Nie jestem ekspertem w R ani statystykach, ale ludzie zwykle patrzą na różne informacje dotyczące regresji liniowej:
- wartość p
- a i b
- r²
- i oczywiście aspekt dystrybucji punktów
Weźmy przykład. Masz tutaj
Tutaj odtwarzalny przykład z różnymi zmiennymi:
Ex<-structure(list(X1 = c(-36.8598, -37.1726, -36.4343, -36.8644,
-37.0599, -34.8818, -31.9907, -37.8304, -34.3367, -31.2984, -33.5731
), X2 = c(64.26, 63.085, 66.36, 61.08, 61.57, 65.04, 72.69, 63.83,
67.555, 76.06, 68.61), Y1 = c(493.81544, 493.81544, 494.54173,
494.61364, 494.61381, 494.38717, 494.64122, 493.73265, 494.04246,
494.92989, 494.98384), Y2 = c(489.704166, 489.704166, 490.710962,
490.653212, 490.710612, 489.822928, 488.160904, 489.747776, 490.600579,
488.946738, 490.398958), Y3 = c(-19L, -19L, -19L, -23L, -30L,
-43L, -43L, -2L, -58L, -47L, -61L)), .Names = c("X1", "X2", "Y1",
"Y2", "Y3"), row.names = c(NA, 11L), class = "data.frame")
library(reshape2)
library(ggplot2)
Ex2<-melt(Ex,id=c("X1","X2"))
colnames(Ex2)[3:4]<-c("Y","Yvalue")
Ex3<-melt(Ex2,id=c("Y","Yvalue"))
colnames(Ex3)[3:4]<-c("X","Xvalue")
ggplot(Ex3,aes(Xvalue,Yvalue))+
geom_smooth(method="lm",alpha=0.2,size=1,color="grey")+
geom_point(size=2)+
facet_grid(Y~X,scales='free')
#Use the lmp function
lmp <- function (modelobject) {
if (class(modelobject) != "lm") stop("Not an object of class 'lm' ")
f <- summary(modelobject)$fstatistic
p <- pf(f[1],f[2],f[3],lower.tail=F)
attributes(p) <- NULL
return(p)
}
# create function to extract different informations from lm
lmtable<-function (var1,var2,data,signi=NULL){
#var1= y data : colnames of data as.character, so "Y1" or c("Y1","Y2") for example
#var2= x data : colnames of data as.character, so "X1" or c("X1","X2") for example
#data= data in dataframe, variables in columns
# if signi TRUE, round p-value with 2 digits and add *** if <0.001, ** if < 0.01, * if < 0.05.
if (class(data) != "data.frame") stop("Not an object of class 'data.frame' ")
Tabtemp<-data.frame(matrix(NA,ncol=6,nrow=length(var1)*length(var2)))
for (i in 1:length(var2))
{
Tabtemp[((length(var1)*i)-(length(var1)-1)):(length(var1)*i),1]<-var1
Tabtemp[((length(var1)*i)-(length(var1)-1)):(length(var1)*i),2]<-var2[i]
colnames(Tabtemp)<-c("Var.y","Var.x","p-value","a","b","r^2")
for (n in 1:length(var1))
{
Tabtemp[(((length(var1)*i)-(length(var1)-1))+n-1),3]<-lmp(lm(data[,var1[n]]~data[,var2[i]],data))
Tabtemp[(((length(var1)*i)-(length(var1)-1))+n-1),4]<-coef(lm(data[,var1[n]]~data[,var2[i]],data))[1]
Tabtemp[(((length(var1)*i)-(length(var1)-1))+n-1),5]<-coef(lm(data[,var1[n]]~data[,var2[i]],data))[2]
Tabtemp[(((length(var1)*i)-(length(var1)-1))+n-1),6]<-summary(lm(data[,var1[n]]~data[,var2[i]],data))$r.squared
}
}
signi2<-data.frame(matrix(NA,ncol=3,nrow=nrow(Tabtemp)))
signi2[,1]<-ifelse(Tabtemp[,3]<0.001,paste0("***"),ifelse(Tabtemp[,3]<0.01,paste0("**"),ifelse(Tabtemp[,3]<0.05,paste0("*"),paste0(""))))
signi2[,2]<-round(Tabtemp[,3],2)
signi2[,3]<-paste0(format(signi2[,2],digits=2),signi2[,1])
for (l in 1:nrow(Tabtemp))
{
Tabtemp$"p-value"[l]<-ifelse(is.null(signi),
Tabtemp$"p-value"[l],
ifelse(isTRUE(signi),
paste0(signi2[,3][l]),
Tabtemp$"p-value"[l]))
}
Tabtemp
}
# ------- EXAMPLES ------
lmtable("Y1","X1",Ex)
lmtable(c("Y1","Y2","Y3"),c("X1","X2"),Ex)
lmtable(c("Y1","Y2","Y3"),c("X1","X2"),Ex,signi=TRUE)
Na pewno jest szybsze rozwiązanie niż ta funkcja, ale działa.
r <- summary(lm(rnorm(10)~runif(10)))
Nic nie wyświetla).