If you're interested in downloading a copy of my recent paper with Xiao Ling, "Bias Reduction for the Maximum Likelihood Estimator of the Parameters of the Generalized Rayleigh Family of Distributions", but don't have a subscription to Communications in Statistics, fear not!
The publisher (Taylor and Francis) will provide free downloads for up to 50 people from here.
Knock yourselves out!
Ugh. In a lot of cases, getting the second derivatives of the likelihood function can be a real chore. This requires the third derivative, and I suspect getting that numerically with finite differences might be too imprecise.
ReplyDeleteObviously you're not familiar with this literature. The derivatives are obtained analytically, not numerically.
Delete