[R] Entropy Optimization to fit distribution parameters through Alabama package

Vijaya mulakalapalli vijaya.mulakalapalli at gmail.com
Sat May 23 22:16:26 CEST 2015


Hi,

I am trying to fit the parameters of a distribution to my data using
entropy optimization. For this I am using the first 4 moments of my data
and trying to calibrate them to the most suitable distribution by
maximizing entropy. Since the moment constraints are nonlinear, I am trying
to use package alabama to achieve this. Since negative Entropy is a convex
function, I was hopeful of achieving a global minima through this exercise.
However, my entropy function converges to different values with different
starting points. Am I doing something wrong here? I could provide the code
based on your inputs

Thanks!

	[[alternative HTML version deleted]]



More information about the R-help mailing list