D**e
发帖数: 10169 | 1 the standard error refers to the standard deviation of a sample distribution.
for the fitting parameters, a and b, there is no such thing called 'standard
error'. if you want to know how well a and b are determined, you may talk
about the error on the parameter estimation, which is calculated as
1/2 * d^2S/(dpi*dpj) where S is Chi2 and d is partial derivative. and (pi, pj)
is a vector of the parameters. in your case, you will have 3 of them, namely
(pa,pa), (pb, pb), (pa, pb). this gives you a |
|
