Autocorrelation curve Stretched Exponential Fit

Hi All,

I have a data with 2 columns i.e. x and y values. The data set is an autocorrelation function. I was wondering if there is a way to fit the curve to a stretched exponential of the following form ---

y = exp(-x/a)^b

Thanks

Atanu

Answer 1

[John D'Errico]

Yes. Use the curve fitting toolbox, or the optimization toolbox, or the stats toolbox. My gut says this model will tend to need decent starting values. But poor starting values are bad for any optimization.