JEFS_Vol 13 N 01

Permanent URI for this collectionhttps://archives.univ-eloued.dz/handle/123456789/18242

Browse

Browsing JEFS_Vol 13 N 01 by Author "Benamirouche, Rachid"

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Bayesian Constant Hazard Risk Model With A Change Point Case Of Study: The Durations Of Unemployment Of A Local Employment Agency
    (جامعة الوادي - University of Eloued, 2020-12-31) Hamimes, Ahmed; Benamirouche, Rachid
    The purpose of the change methods is to make statistical inferences about the position of breakpoints and about other model parameters. In this article we look at the unemployed registered with the local employment agency of Ain El Benian (January 2011-July 2013). The objective is to find the breaking point in the overall survival function represents the integration probabilities of individuals registered with this agency and in the determined period. We use the constant model of instantaneous risk which corresponds to an exponential function of survival. This breaking point represents the duration of change for an unemployed individual, which is an important element for economic analysis and comparison.
  • Thumbnail Image
    Item
    Kaplan Meier's Bayesian Model Under An Informative Prior Distribution Case: Integration Study Of Unemployed Registered With The Local Employment Agency Of Ain El Benian (january 2011-july 2013)
    (جامعة الوادي - University of Eloued, 2020-12-31) Hamimes, Ahmed; Benamirouche, Rachid
    A Bayesian approach to nonparametric survival offers practical, simple and relatively easysolutions to exploit numerically. In this contribution, we will demonstrate the efficiency of the Bayesian approach in themodeling of durations and in an econometric context, we propose a new conception of theKaplan Meier Bayesian estimator under an a priori informative law based on the stochasticapproximation. Which here represents by Gibbs sampling.Our contribution is to improve thedeductive stage in estimating nonparametric survival times and under censorship, and this iswhat we reached in our research L'approche bayésienne de la survie non paramétrique offre des solutions pratiques, simples et relativement faciles à exploiter numériquement. Dans cette contribution, nous démontrerons l'efficacité de l'approche de Bayes dans la modélisation de la durée et dans le contexte économétrique, en proposant un nouveau concept pour l'estimateur bayésien de Kaplan Meyer sous une loi informationnelle a priori basée sur l'approximation stochastique. Ce qui est représenté ici par l'échantillonnage de Gibbs. Notre contribution est d'améliorer la phase déductive dans l'estimation des temps de survie non paramétriques et sous censure, et c'est ce que nous avons trouvé dans nos recherches