Finding Bestfit Distribution [image]

[hoodrych]

I need to find the bestfit distribution for this. I'm using excel, so I need to be able to use xcel to graph it.


[PLAIN]http://img831.imageshack.us/img831/8770/unledcwx.png

 

[adoado]

I use CurveExpert to find best fit models; give that a try. Then simply evaluate a few points from the model and plot them as separate data.

 

[hoodrych]

I use CurveExpert to find best fit models; give that a try. Then simply evaluate a few points from the model and plot them as separate data.

Maybe I'm using the program wrong (I don't think I am), but it's not coming up with any results.


I have no Y values, only X's, so that may be the problem? There are lots of errors for almost every test. And when I click the "scan for bestfit" button, the 20 or so different best fit models it tests all come up with a Score of 0.0.

 

[Stephen Tashi]

As I said in the other thread, you should use a cumulative histogram of the data. The x-axis should be the errors and the y-axis should be the frequency.