Results (1)
Search Parameters:
Author/Affiliation: Leonard SikorskiOpen AccessArticle
13 Pages, 1,286 KB 
Empirical Probability Distributions with Unknown Number of Components
Abstract:
We consider the estimation of empirical probability distributions, both discrete and continuous. We focus on deriving formulas to estimate number of categories for the discrete distribution, when the number of categories is hidden, and the means and methods to estimate the number of components in the Gaussian mixture model representing a probability density function given…
Read More(This article belongs to the SP9 (Special Issue on Multidisciplinary Innovation in Engineering Science & Technology 2020) & Section Mathematics (MAT))