## octave-cvsupdate

 [Octave-cvsupdate] octave-forge/main/optim/inst wpolyfit.m, 1.1, 1.2 From: Paul Kienzle - 2006-12-28 06:15:16 ```Update of /cvsroot/octave/octave-forge/main/optim/inst In directory sc8-pr-cvs3.sourceforge.net:/tmp/cvs-serv6118 Modified Files: wpolyfit.m Log Message: Corrections to comments regarding F-test for polynomial degree Index: wpolyfit.m =================================================================== RCS file: /cvsroot/octave/octave-forge/main/optim/inst/wpolyfit.m,v retrieving revision 1.1 retrieving revision 1.2 diff -u -d -r1.1 -r1.2 --- wpolyfit.m 20 Aug 2006 13:37:57 -0000 1.1 +++ wpolyfit.m 28 Dec 2006 06:15:12 -0000 1.2 @@ -44,12 +44,12 @@ ## @example ## [poly1,S1] = wpolyfit(x,y,dy,n); ## [poly2,S2] = wpolyfit(x,y,dy,n+1); -## F = (S1.normr^2 - S2.normr^2)/(S2.normr^2/S2.df); -## p = 1-f_cdf(F,1,S2.df); +## F = (S1.normr^2 - S2.normr^2)/(S1.df-S2.df)/(S2.normr^2/S2.df); +## p = 1-f_cdf(F,S1.df-S2.df,S2.df); ## @end example ## p is the probability of observing the improvement in chi^2 obtained ## by adding the extra parameter to the fit. If p < 0.01, you can reject -## the higher order polynomial at the 1% level. +## the lower order polynomial at the 1% level. ## ## You can estimate the uncertainty in the polynomial coefficients ## themselves using ```