Attributes | Values |
---|
rdf:type
| |
Description
| - Statistical inference can be interpreted as a problem of minimum distance between an empirical (observed) and a theoretical distribution. The most used measures of dissimilarity/disparity between probability distributions are the well known divergence measures. These measures are not symmetric: basing on the duality in their formulation, we classify divergences within the context of estimation into two main classes and analyze them with reference to majorization theory. In this regard, the consistency of divergence measures with respect to the generalized (strong) majorization pre-order is can be easily derived from a well known characterization theorem. Nevertheless, in many practical contexts such as estimation problem, one of the main assumption for (strong) majorization could be unfulfilled. Thus we study under which conditions divergence measures are consistent with respect to the generalization of weak majorization (from above). This paper provides a guideline for the choice of an appropriate divergence measure for minimum distance estimation purpose. The results hold for discrete probability distributions but can be easily generalized to positive measures and applied to many dissimilarity indices.
- Statistical inference can be interpreted as a problem of minimum distance between an empirical (observed) and a theoretical distribution. The most used measures of dissimilarity/disparity between probability distributions are the well known divergence measures. These measures are not symmetric: basing on the duality in their formulation, we classify divergences within the context of estimation into two main classes and analyze them with reference to majorization theory. In this regard, the consistency of divergence measures with respect to the generalized (strong) majorization pre-order is can be easily derived from a well known characterization theorem. Nevertheless, in many practical contexts such as estimation problem, one of the main assumption for (strong) majorization could be unfulfilled. Thus we study under which conditions divergence measures are consistent with respect to the generalization of weak majorization (from above). This paper provides a guideline for the choice of an appropriate divergence measure for minimum distance estimation purpose. The results hold for discrete probability distributions but can be easily generalized to positive measures and applied to many dissimilarity indices. (en)
|
Title
| - Divergence measures and weak majorization in estimation problems
- Divergence measures and weak majorization in estimation problems (en)
|
skos:prefLabel
| - Divergence measures and weak majorization in estimation problems
- Divergence measures and weak majorization in estimation problems (en)
|
skos:notation
| - RIV/61989100:27510/14:86091093!RIV15-MSM-27510___
|
http://linked.open...avai/riv/aktivita
| |
http://linked.open...avai/riv/aktivity
| |
http://linked.open...vai/riv/dodaniDat
| |
http://linked.open...aciTvurceVysledku
| |
http://linked.open.../riv/druhVysledku
| |
http://linked.open...iv/duvernostUdaju
| |
http://linked.open...titaPredkladatele
| |
http://linked.open...dnocenehoVysledku
| |
http://linked.open...ai/riv/idVysledku
| - RIV/61989100:27510/14:86091093
|
http://linked.open...riv/jazykVysledku
| |
http://linked.open.../riv/klicovaSlova
| - dissimilarity; inequality; convex function; estimation; divergence measure; majorization (en)
|
http://linked.open.../riv/klicoveSlovo
| |
http://linked.open...ontrolniKodProRIV
| |
http://linked.open...v/mistoKonaniAkce
| |
http://linked.open...i/riv/mistoVydani
| |
http://linked.open...i/riv/nazevZdroje
| - Proceedings of the 2nd International Conference on Mathematical, Computational and Statistical Sciences (MCSS '14); Proceedings of the 7th International Conference on Finite Difference...: Gdansk, Poland May 15-17, 2014
|
http://linked.open...in/vavai/riv/obor
| |
http://linked.open...ichTvurcuVysledku
| |
http://linked.open...cetTvurcuVysledku
| |
http://linked.open...vavai/riv/projekt
| |
http://linked.open...UplatneniVysledku
| |
http://linked.open...iv/tvurceVysledku
| - Bertoli-Barsotti, Lucio
- Lando, Tommaso
|
http://linked.open...vavai/riv/typAkce
| |
http://linked.open.../riv/zahajeniAkce
| |
issn
| |
number of pages
| |
http://purl.org/ne...btex#hasPublisher
| |
https://schema.org/isbn
| |
http://localhost/t...ganizacniJednotka
| |