Search code examples
rdataframeboxplotoutliers

R - Remove all outliers at once


I have a data set imported in R where I am trying to remove the outliers. I did it so far that I identified all outlier values with a boxplot and saved them in a variable.

outlier_values_2 <- boxplot.stats(myfileswoNA$smart_1_raw)$out  # outlier values.
boxplot(myfileswoNA$smart_1_raw, main="Outlier", boxwex=0.1)

hist(myfileswoNA$smart_1_raw)
summary(myfileswoNA$smart_1_raw)

Now I am trying to remove the lines with the identified outliers. I can do this with one certain value:

example <- myfileswoNA[myfileswoNA$smart_1_raw!=4294967295,]

But what I would like to do is to remove all outliers at once, which are stored in the variable outlier_values_2 For example this way is not working:

example <- myfileswoNA[myfileswoNA$smart_1_raw!=4294967295,]

Can anyone help me with this issue? Or does anyone have an idea?


Solution

  • The answer from @LAP helped me with my problem. Here is what he suggested:

    If all outlier values are stored in outlier_values_2, try myfileswoNA[!myfileswoNA$smart_1_raw %in% outlier_values_2,]