Hi: Thank you and sorry for getting back late. Your input helped me a
lot. I particularly liked using box.cox. Regards,
Ashraf
__
R-help@stat.math.ethz.ch mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide!
Ashraf Chaudhary wrote:
Hi All;
The following question is directed more to statisticians on the list.
Suppose I have a normal random variable. Is there a transformation that I
can apply so that the new variable is slightly positively skewed.
I greatly appreciate your help.
Ashraf
I think the box.cox function in package car can do this.
x - rnorm(1000)
hist(x)
library(car)
hist(box.cox(x, p=0.5))
Play around with different powers.
Best,
Matthias
-Ursprüngliche Nachricht-
Von: [EMAIL PROTECTED]
[mailto:[EMAIL PROTECTED] Im Auftrag von
Ashraf Chaudhary