On 12 Jun 2003 07:44:32 -0700, [EMAIL PROTECTED] (akhan) wrote: > Is there any statistical metod which can be applied to test whether a > non-linear model fit a dataset well or significantly? > > Thanks for your help or any reference.
Is it possibly and is it okay to transform it into a *linear* model? That is the best chance. If that is so, then transform it, and test it in the usual ways. On my desk, I have "Model discrimination for nonlinear regression models" by Borowaik. That's one reference. Tests can be devised or described, for sets of circumstances. But there's not one magical formula or reference. -- Rich Ulrich, [EMAIL PROTECTED] http://www.pitt.edu/~wpilib/index.html "Taxes are the price we pay for civilization." Justice Holmes. . . ================================================================= Instructions for joining and leaving this list, remarks about the problem of INAPPROPRIATE MESSAGES, and archives are available at: . http://jse.stat.ncsu.edu/ . =================================================================
