How to find the goodness of fit without using the curve fiting toolbox

Dear all , I would like to know if this is possible to calculate the goodness of fit measures R-square, adjusted R square, RMSE etc for an exponential fit without using curve fitting tool box.

When I do the exponential fit for my data , I get only the coefficient a and b exemple f =

     General model Exp1:
     f(x) = a*exp(b*x)
     Coefficients (with 95% confidence bounds):
       a =      0.4396  (0.3358, 0.5434)
       b =  -4.105e-05  (-0.001221, 0.001139)

Thanks in advance

[dpb]

Sure, assuming you have the underlying data and not just the model coefficients.

Rsq = 1-SSe/SSt

others are similar.

[afrya]

thank you for your answer, but is there a function with matlab that allow us to get directly the goodness of fit without any calculations?

[dpb]

AFAIK, no, it seems TMW has been careful to not do so to keep market for the Toolbox.

You might check on FileExchange for contributions; I don't know if they've prevented the facility to protect the market share there or not.

[afrya]

ok thanks