Smooth density estimation with moment constraints using mixture distributions

Ani Eloyan, Sujit K. Ghosh

Research output: Contribution to journalArticlepeer-review

Abstract

Statistical analysis often involves the estimation of a probability density based on a sample of observations. A commonly used nonparametric method for solving this problem is the kernel-based method. The motivation is that any continuous density can be approximated by a mixture of densities with appropriately chosen bandwidths. In many practical applications, we may have specific information about the moments of the density. A nonparametric method using a mixture of known densities is proposed that conserves a given set of moments. A modified expectation-maximisation algorithm for estimating the weights of the mixture density is then developed. The proposed method also obtains an estimate of the number of components in the mixture needed for optimal approximation. The proposed method is compared with two popular density estimation methods using simulated data and it is shown that the proposed estimate outperforms the others. The method is then illustrated by applying it to several real-data examples.

Original languageEnglish (US)
Pages (from-to)513-531
Number of pages19
JournalJournal of Nonparametric Statistics
Volume23
Issue number2
DOIs
StatePublished - Jun 1 2011

Keywords

  • Bandwidth selection
  • EM-algorithm
  • Estimation of mixture complexity
  • Kernel density estimation
  • Kullback-Leibler divergence

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Fingerprint

Dive into the research topics of 'Smooth density estimation with moment constraints using mixture distributions'. Together they form a unique fingerprint.

Cite this