MATLAB: How does matlab do maximum likelihood on custom functions

custom distributiondistribution fittingfittinggeneralized normal distributionmaximum likelihoodmlmlemlecustom

I am trying to fit a custom function ( generalized Normal distribution type II http://en.wikipedia.org/wiki/Generalized_normal_distribution)to my data and i am using mle function. I wonder what is the method that Matlab uses, is it a search method?

Best Answer

Ordinarily, the mle function minimizes the negative log-likelihood that you have defined (either as a PDF, or a log PDF, or as the LL) using fminsearch. If you have the Optimization Toolbox, you can tell mle to use fmincon. This is the 'OptimFun' parameter, explained in the help for the mle function.

Related Solutions

MATLAB: Are the logit-normal distribution is implemented in MATLAB

Try cumsum() and use Inverse Transform Sampling.

Also see RANDRAW to see how the author generates dozens of distributions.

MATLAB: How to interpret the output of mle()

When you use 'mle()' for estimating the parameters for a normal distribution, the output is a maximum likelihood of the parameters in the distribution. For a normal distribution, the function will be executed as,

likelihood = mle(data, 'distribution', 'norm')

Here, the likelihood contains the estimation of the parameters in the distribution. For your Gaussian distribution, the first output of the likelihood refers to mean and second output refers to the variance.

Best Answer

Related Solutions

MATLAB: Are the logit-normal distribution is implemented in MATLAB

MATLAB: How to interpret the output of mle()

Related Question