Hi all,

Anyone have any method (e.g., a program) for finding the best "best
fit" regression?

Rather than graphing the series of data and then visually guessing
the best regression method to use, a program/function could do a one-
by-one check of each method on the series and return the one that has
the best fit (based I guess on the distance of actual and "regression-
guessed" values).

I could probably write this myself but thought I should check first
to save me from re-inventing the wheel.

TIA

tonyp@...