Reply
Mon 20 Feb, 2012 09:15 am
I understand quadratic and linear regression, but am not understanding what a log transformation regression is. Can someone offer any insight? Also, from what I have read online people are transforming the Y variable in SPSS. Why wouldn't you transform the X variable?
@eremlo,
Study this graph. Do you see why it's easier to work with the data on the left after the logarithmic transformation (right)? Download interactive demo here:
http://demonstrations.wolfram.com/InteractiveCurveFitting/
As far as your second Q, y is usually the dependent variable so you can transform its equation (see above) while X is an input - can't change it.
Stumble It!
Tweet This
Bookmark on Delicious
Share on Facebook
Share on MySpace