English

A new inequality for maximum likelihood estimation in statistical models with latent variables

Statistics Theory 2019-12-10 v1 Methodology Statistics Theory

Abstract

Maximum-likelihood estimation (MLE) is arguably the most important tool for statisticians, and many methods have been developed to find the MLE. We present a new inequality involving posterior distributions of a latent variable that holds under very general conditions. It is related to the EM algorithm and has a clear potential for being used in a similar fashion.

Keywords

Cite

@article{arxiv.1912.04011,
  title  = {A new inequality for maximum likelihood estimation in statistical models with latent variables},
  author = {Niels Lundtorp Olsen},
  journal= {arXiv preprint arXiv:1912.04011},
  year   = {2019}
}

Comments

4 pages

R2 v1 2026-06-23T12:39:56.234Z