Hi,
I have a few lines of code that will remove outliers for a regression test
based on the studentized residuals being above or below 3, -3. I have to do
this multiple times and have attempted to create a function to lessen the
amount of copying, pasting and replacing.
I run into trouble with the function and receiving the error "Error in
`$<-.data.frame`(`*tmp*`, "varpredicted", value = c(0.114285714285714, :
replacement has 20 rows, data has 19
"
any help would be appreciated. a list of code is listed below.
Thank you for your time!
x = c(1:20)
y = c(1,3,4,2,5,6,18,8,10,8,11,13,14,14,15,85,17,19,19,20)
data1 = data.frame(x,y)
# remove outliers for regression by studentized residuals being greater than
3
data1$predicted = predict(lm(data1$y~data1$x))
data1$stdres = rstudent(lm(data1$y~data1$x));
i=length(which(data1$stdres>3|data1$stdres< -3))
while(i >= 1){
remove<-which(data1$stdres>3|data1$stdres< -3)
print(data1[remove,])
data1 = data1[-remove,]
data1$predicted = predict(lm(data1$y~data1$x))
data1$stdres = rstudent(lm(data1$y~data1$x))
i = with(data1,length(which(stdres>3|stdres< -3)))
}
# attemp to create a function to perfom same idea as above
rm.outliers = function(dataset,var1, var2) {
dataset$varpredicted = predict(lm(var1~var2))
dataset$varstdres = rstudent(lm(var1~var2))
i = length(which(dataset$varstdres > 3 | dataset$varstdres < -3))
while(i >= 1){
removed = which(dataset$varstdres > 3 | dataset$varstdres < -3)
print(dataset[removed,])
dataset = dataset[-removed,]
dataset$varpredicted = predict(lm(var1~var2))
dataset$varstdres = rstudent(lm(var1~var2))
i = with(dataset,length(varstdres > 3 | varstdres < -3))
}
}
--
View this message in context:
http://r.789695.n4.nabble.com/removing-outlier-function-dataset-update-tp3238394p3238394.html
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.
