Re: Norm of the error

I guess you are looking for an objective function to be used in
fminsearch.

there are more than a few choices
mean square error
sum of squared errors
mean absolute error
normalized error
chi-square error

The choice is dictated by the kind of data set you have. Sum of squared
residuals/least squares is the most popular but it is also very
susceptible to noise.
This might help
http://www.itl.nist.gov/div898/handbook/pmd/section1/pmd14.htm

.

Relevant Pages

  • Re: Approximating Differential Equation on the Basis of Measured Values
    ... I think you should try squaring each error and summing it and minimizing the sum of square error. ... Dividing the sum of square error by the number of points gives me a better idea of how close the fit is. ... Even your 3 poles solution is too complicated to be used on a PLC because they only have PIDs, ...
    (sci.engr.control)
  • Re: Goodness of fitting of a distribution
    ... so there isn't a goodness of fit test that i ... I thinked about sum of square error but my colleague says that ...
    (sci.stat.math)