A comparison of computational approaches for maximum likelihood estimation of the Dirichlet parameters on high-dimensional data
Likelihood estimates of the Dirichlet distribution parameters can be obtained only through numerical algorithms. Such algorithms can provide estimates outside the correct range for the parameters and/or can require a large amount of iterations to reach convergence. These problems can be aggravated i...
| Autores: | , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2015 |
| País: | España |
| Institución: | Universitat Politècnica de Catalunya (UPC) |
| Repositorio: | UPCommons. Portal del coneixement obert de la UPC |
| Idioma: | inglés |
| OAI Identifier: | oai:upcommons.upc.edu:2117/88522 |
| Acceso en línea: | https://hdl.handle.net/2117/88522 |
| Access Level: | acceso abierto |
| Palabra clave: | Levenberg-Marquardt algorithm re-parametrization starting values metabolomics data Classificació AMS::65 Numerical analysis::65C Probabilistic methods, simulation and stochastic differential equations Classificació AMS::62 Statistics::62F Parametric inference Àrees temàtiques de la UPC::Matemàtiques i estadística::Estadística matemàtica |
| Sumario: | Likelihood estimates of the Dirichlet distribution parameters can be obtained only through numerical algorithms. Such algorithms can provide estimates outside the correct range for the parameters and/or can require a large amount of iterations to reach convergence. These problems can be aggravated if good starting values are not provided. In this paper we discuss several approaches that can partially avoid these problems providing a good trade-off between efficiency and stability. The performances of these approaches are compared on high-dimensional real and simulated data. |
|---|