Robustez estadística
DOI:
https://doi.org/10.17533/udea.le.n24a7769Abstract
• Resumen: El uso de modelos paramétricos estocásticos exactos tales como el normal, log-normal, exponencial, poisson, gama, etc. está hoy profundamente arraigado en la práctica estadística. La razón es que ellos permiten la representación aproximada de un conjunto de datos que puede ser fácilmente descrita e interpretada. Sin embargo, es bien conocido que el mundo real no se comporta tan bien como lo describen estos modelos. Recientemente surge una técnica estadística la cual emplea también los modelos paramétricos pero la inferencia es realizada para un entorno del modelo asumido. Es decir, aunque emplea modelos paramétricos, los procedimientos que construye no dependen fundamentalmente de las hipótesis inherentes a ellos.
• Abstract: The use of precise stochastic parameter models, such as the normal, log-normal, exponential, poisson and gamma models, is nowadays deeply entrenched in statistical practice. The cause of this trend is their ability to approximately represent a series of data that can be easily described and interpreted. Nevertheless, it is well known that the real world doesn't behave as these models describe it. Recently, a statistical technique, employing parametrical models, appeared. This method tests part of the assumed model that is, although it employs parametrical models the procedure, it builds, doesn't fundamentally depend on the included hypothesis.
Downloads
Downloads
Published
How to Cite
Issue
Section
License
This page, by Universidad de Antioquia, is licensed under a Creative Commons Attribution License.
Authors who publish with this journal agree to retain copyright and grant the journal right of first publication, with the article licensed under a Creative Commons Attribution-NonCommercial-ShareAlike License allowing others to share it as long as they acknowledge its authorship and original publication in this journal.
Authors can enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), provided that these arrangements be not for profit and the journal be acknowledged as the original source of publication.
Authors are permitted and encouraged to post their papers online (e.g., in institutional repositories or on their websites), as it can lead to valuable exchanges as well as greater citation of the published work.
