A Note on a Nonparametric Maximum Penalized Likelihood Estimator of the Probability Density Function of a Positive Random Variable. A Maple with Positive Support

摘要

The 'first nonparametric maximum penalized likelihood density estimator of Good and Gaskins', corresponding to a penalty proportional to the Fisher information, is derived in the case that the density function has its support on the half-line. The computational feasibility as well as the consistency properties of the estimator are indicated. (Author)