help needed to fit dataset with two peaks

[bb1711]

I have a distribution with two peaks where the right hand one resemble Gaussian distribution. I want to fit a curve to the entire dataset, determine the minimum point between two peaks, cut data set using that figure, and try to fit some parametric distribution to both sets of data.

I managed to get very good non-parametric fit for the entire dataset (using dfittool) but cannot get its function (to be able to determine MIN). I tried to fit various polynomials but they do not produce good fit. Can anyone advise me how to get a function from the non-parametric fit?

 

[IRstuff]

I'm not sure I follow. Your "cutting" of the distribution is bound to screw up any future parametric fits because the tails from the two distributions must be overlapping.

Seems to me, the way to do this is to directly fit to two parametric distributions.

TTFN