Or bananas. Is your questions whether a linear or non-linear regression model fits your data better? You can use AICc to rank and compare multiple models if you have the log-likelihoods or deviance from both fitted models.
Anderson (2008) is the easiest to understand and least technical book on the subject if you're not familiar with it. Any statistician could show you how to use AICc. Anderson, D. R. 2008. Model based inference in the life sciences: a primer on evidence. Springer. -----Original Message----- From: Ecological Society of America: grants, jobs, news [mailto:[email protected]] On Behalf Of Hal Caswell Sent: Wednesday, March 14, 2012 9:35 AM To: [email protected] Subject: [ECOLOG-L] Fwd: [ECOLOG-L] linear and nonlinear regression comparison Apples. And oranges. Begin forwarded message: > From: Dendy Lofton <[email protected]> > Date: March 13, 2012 6:57:26 PM EDT > To: [email protected] > Subject: [ECOLOG-L] linear and nonlinear regression comparison > > Does anyone know how to statistically compare the slope of a linear > regression equation to the slope of a nonlinear (i.e., exponential) regression equation? > Thanks in advance for your thoughts. > --------------------------------- Hal Caswell Senior Scientist Biology Department Woods Hole Oceanographic Institution Woods Hole MA 02543 508-289-2751 [email protected]
