Skip to main content

ANALISIS Y APLICACIONES DE PROCESOS GAUSSIANOS Y PROCESOS DE LEVY

MTM2012-33937

•
Funding agency name Ministerio de Economía y Competitividad
Funding agency acronym MINECO
Program Programa Nacional de Proyectos de Investigación Fundamental
Subprogram Subprograma de Proyectos de Investigación Fundamental no Orientada
Call Proyectos I+D
Call year 2012
State Plan 2008-2011 Plan Nacional de Investigación Científica, Desarrollo e Innovación Tecnológica
Management unit Secretaría de Estado de Investigación, Desarrollo e Innovación
Beneficiary centre UNIVERSIDAD AUTONOMA DE BARCELONA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 4
Encontrada(s) 1 página(s)

Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

On the norming constants for normal maxima

  • Gasull, Armengol|||0000-0002-1719-8231
  • Jolis Giménez, Maria|||0000-0001-7270-0813
  • Utzet, Frederic
In a remarkable paper, Peter Hall [On the rate of convergence of normal extremes, J. App. Prob, 16 (1979) 433-439] proved that the supremum norm distance between the distribution function of the normalized maximum of n independent standard normal random variables and the distribution function of the Gumbel law is bounded by 3/ log n. In the present paper we prove that choosing a different set of norming constants that bound can be reduced to 1/ log n. As a consequence, using the asymptotic expansion of a Lambert W type function, we propose new explicit constants for the maxima of normal random variables.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Maxima of Gamma random variables and other Weibull like distributions and the Lambert W function

  • Gasull, Armengol|||0000-0002-1719-8231
  • López-Salcedo, José A.|||0000-0002-5392-6005
  • Utzet i Civit, Frederic
In some applied problems of signal processing, the maximum of a sample of _2(m) random variables is computed and compared with a threshold to assess certain properties. It is well known that this maximum, conveniently normalized, converges in law to a Gumbel random variable; however, numerical and simulation studies show that the norming constants that are usually suggested are inaccurate for moderate or even large sample sizes. In this paper, we propose, for Gamma laws (in particular, for a _2(m) law) and other Weibull-like distributions, other norming constants computed with the asymptotics of the Lambert W function that significantly improve the accuracy of the approximation to the Gumbel law.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Approximating Mills ratio

  • Gasull, Armengol|||0000-0002-1719-8231
  • Utzet i Civit, Frederic
Consider the Mills ratio f(x) =1 - Φ(x)/φ(x), x ≥ 0, where φ is the density function of the standard Gaussian law and Φ its cumulative distribution. We introduce a general procedure to approximate f on the whole [0, ∞) which allows to prove interesting properties where f is involved. As applications we present a new proof that 1/f is strictly convex, and we give new sharp bounds of f involving rational functions, functions with square roots or exponential terms. Also Chernoff type bounds for the Gaussian Q-function are studied.
Dipòsit Digital de Documents de la UAB
Publication Artículo científico (JournalArticle)

Las Redes Bayesianas como herramienta para la evaluación del riesgo de reincidencia: Un estudio sobre agresores sexuales, Bayesian Networks as a tool for assessing the risk of recidivism: A study on sexual offenders

  • Delgado, Rosario|||0000-0003-1208-9236
  • Tibau, Xavier-Andoni
La reincidencia, especialmente en delitos sexuales, constituye una problemática que afecta a los ámbitos político, jurídico-penal y social, con gran repercusión en los medios. Por este motivo es necesario desarrollar metodologías de análisis para su predicción, para mejorar la eficiencia de la gestión del riesgo asociado. Las Redes Bayesianas han demostrado ser una herramienta muy útil en la predicción de sucesos que dependen de muchas variables en un entorno de incertidumbre. Este trabajo introduce su uso como metodología novedosa en la evaluación del riesgo de reincidencia, a partir de un estudio sobre delincuentes sexuales basado en la información recogida en un informe previo. Se observa la coherencia de los resultados obtenidos con los del informe en cuanto a la influencia individual de las variables explicativas en el riesgo de reincidencia. El interés principal de esta metodología radica en que permite explorar la influencia simultánea de diversas variables, por lo que se podrán hacer estimaciones precisas de riesgo individualizado y estudiar las interacciones entre los factores de riesgo., Recidivism in sexual offences is a problem that affects the political, criminal justice and social context, with great media coverage. In order to improve the efficiency in managing the risk of these offences some methodologies for prediction need to be developed. Bayesian Networks have proved to be a useful tool in predicting events that depend on many variables in an uncertain environment. This paper introduces their use as a novel methodology in assessing the risk of recidivism, from a study of sex offenders based on the information in a report. Consistency of the results obtained with the report regarding the individual influence of the explanatory variables on the risk of recurrence was observed. The main interest of this methodology is to explore the simultaneous influence of several variables, so it may make accurate estimates of individual risk and study the interactions between the risk factors.