Parameterised Function - looks a bit like a log-normal

I need to come up with a parameterised function with as few parameters as possible which I can fit to the distributions shown in the diagrams (it needs to be the same parameterised function for all but I can fit the parameters in each case). The x axis is plotted on a log scale. I tried a log normal but it didn't work out. It looks like a power law with a cut off at the lower end of the x-axis.

Any suggestions would be appreciated!!

model.png149.1KB

Reply 1

Gregorius

Original post by qrty12

Can you tell us a little bit more about what we're seeing plotted in those pictures? They don't look like histograms to me, so what are they? How much data do you have for each plot/function fit?

You can fit almost anything like that to a (transformed) beta function, but it would also be helpful to know how this data has been generated in order to suggest a function family based on that generation process.