0
$\begingroup$

I am clustering (K-MEANS) a data 1.7million observations, which displays a heavy-tailed distribution when examined by plot. What is the best transformation to correct it. does log can handle this?

enter image description here enter image description here

$\endgroup$
0
$\begingroup$

Yes! The log transformation is perfect for this sort of right-tailed data. Alternatively, a different member of the Box-Cox family might help, depending on what you're using the data for.

$\endgroup$
  • $\begingroup$ Ok thanks, coul help me to for the syntax if I want to transform many variables at the same time? I'm sas starter. $\endgroup$ – dataflowus Jun 19 '18 at 8:57
  • $\begingroup$ No clue sorry. I use R. $\endgroup$ – Ingolifs Jun 19 '18 at 9:19

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.