| Titre : | On improve boundary effect in kernel distribution estimation |
| Auteurs : | Madiha Tour , Auteur ; Abdallah Sayah, Directeur de thèse |
| Type de document : | Thése doctorat |
| Editeur : | Biskra [Algérie] : Faculté des Sciences Exactes et des Sciences de la Nature et de la Vie, Université Mohamed Khider, 2018 |
| Format : | 1 vol. (75 p.) / 30 cm |
| Langues: | Anglais |
| Mots-clés: | Transformation ; effet de bourd ; Estimateur à noyau de la fonction de distribution ; Eerreur quadratique moyenne ; Erreur quadratique moyenne integre. |
| Résumé : |
In this thesis, we propose a new estimator for improve boundary effects in kernel estimator of the heavy-tailed distribution function specially the Pareto-type distributions and its bias,variance and mean squared error are determined. Kernel methods are widely used in many research areas in statistics. However, kernel estimators suffer from boundary effects when the support of the function to be estimated has finite end points. Boundary effects seriously affect the overall performance of the estimator. To remove the boundary effects, a variety of methods have been developed in the literature, the most widely used is the reflection, the transformation ... In this thesis, we introduce a new method of boundary correction when estimating the heavy-tailed distribution function. Our technique is kind of a generalized reflection method involving reflecting a transformation of the observed data by modified Champernowne distribution function. |
| Sommaire : |
Dédicace i Remerciements ii Abstract iii Résumé iv Table of Contents v Liste des gures vii Liste des tableaux viii Introduction 1 1 Nonparametric distribution estimation 6 1.1 Empirical distribution function . . . . . . . . . . . . . . . . . . . . . . . . 7 1.1.1 Properties of EDF . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 1.2 Kernel method . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.2.1 Kernel distribution function estimator . . . . . . . . . . . . . . . . 11 2 Heavy-tailed distribution 18 2.1 Heavy-tailed distribution . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 2.1.1 Examples of heavy-tailed distributions . . . . . . . . . . . . . . . . 21 2.2 Classes of heavy-tailed distributions . . . . . . . . . . . . . . . . . . . . . . 22 2.2.1 Regularity varying distribution functions . . . . . . . . . . . . . . . 23 2.2.2 Subexponential distribution functions . . . . . . . . . . . . . . . . . 25 3 Transformation in kernel density estimation for heavy-tailed distribu- tions 29 3.1 Kernel density estimator and boundary e¤ects . . . . . . . . . . . . . . . . 30 3.2 Methods for removing boundary e¤ects . . . . . . . . . . . . . . . . . . . . 32 3.3 Champernowne distribution . . . . . . . . . . . . . . . . . . . . . . . . . . 35 3.3.1 Modi ed Champernowne distribution . . . . . . . . . . . . . . . . . 36 3.4 Density estimation using Champernowne transformation . . . . . . . . . . 39 3.4.1 Asymptotic theory for the transformation kernel density estimator . 42 4 A modi ed Champernowne transformation to improve boundary e¤ect in kernel distribution estimation 46 4.1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 47 4.2 Boundary kernel distribution estimator . . . . . . . . . . . . . . . . . . . . 49 4.3 The proposed estimator . . . . . . . . . . . . . . . . . . . . . . . . . . . . 52 4.4 Simulation Studies . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 55 4.5 Proofs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57 Conclusion 66 Bibliographie 66 Abbreviation sand Notations 74 |
| En ligne : | http://thesis.univ-biskra.dz/3835/1/Th%C3%A8se%20Doctorate%2C%20Madiha-30.02.2018.pdf |
Disponibilité (1)
| Cote | Support | Localisation | Statut |
|---|---|---|---|
| TM/85 | Théses de doctorat | bibliothèque sciences exactes | Consultable |



