Skip to content

non-linear correlation

2 messages · Irene Mantzouni, David Hewitt

#
I think the starting point is to develop a model, even conceptual, of how
you expect them to be related. If you've already determined that they are
related, and in a way that's nonlinear, then you can probably come up with a
model. "Effect size" will be dependent on the model, but in a nonlinear
model it won't be as simple as "y goes as x goes".

I can't see what you mean concerning the autocorrelation, but if this is a
time series problem your first question is then a mystery to me. You might
do well to read the posting guide for the mailing list and provide an
example.

-----
David Hewitt
Virginia Institute of Marine Science
http://www.vims.edu/fish/students/dhewitt/