Jump to content

  • Log in with Facebook Log in with Twitter Log in with Windows Live Log In with Google      Sign In   
  • Create Account

Submit your paper to J Biol Methods today!
Photo
- - - - -

log transformed data


  • Please log in to reply
2 replies to this topic

#1 ari_doodle

ari_doodle

    member

  • Active Members
  • Pip
  • 10 posts
1
Neutral

Posted 19 February 2009 - 12:59 PM

I am working with some data on hormones. The distribution is very non-normal so I log transformed the data but data is still very skewed. What can I do??

#2 hobglobin

hobglobin

    Growing old is mandatory, growing up is optional...

  • Global Moderators
  • PipPipPipPipPipPipPipPipPipPip
  • 5,548 posts
104
Excellent

Posted 19 February 2009 - 01:02 PM

I am working with some data on hormones. The distribution is very non-normal so I log transformed the data but data is still very skewed. What can I do??


Try out other transformations. But some data sets are skewed, nothing helps. The you should use nonparametric methods...

One must presume that long and short arguments contribute to the same end. - Epicurus
...except casandra's that belong to the funniest, most interesting and imaginative (or over-imaginative?) ones, I suppose.

That is....if she posts at all.


#3 pcrboy

pcrboy

    member

  • Active Members
  • Pip
  • 18 posts
0
Neutral

Posted 20 February 2009 - 11:31 PM

try a normal score transformation, which basically will rank everything and smash everything into something with a normal distribution. the advantage of course is you get rid of outliers. the disadvantage is that you'll no longer have relative distance between each gene. if you prefer, there are nonparametric methods to analyze your data as previously suggested.




Home - About - Terms of Service - Privacy - Contact Us

©1999-2013 Protocol Online, All rights reserved.