Your browser does not support JavaScript!

Home    Μη παραμετρική εκτίμηση συναρτήσεων πυκνότητας πιθανότητας με μεθόδους ποινικοποιημένης πιθανοφάνειας σύμφωνα με το μοντέλο Koziol & Green.  

Results - Details

Add to Basket
[Add to Basket]
Identifier uch.math.msc//2006xifantarakis
Title Μη παραμετρική εκτίμηση συναρτήσεων πυκνότητας πιθανότητας με μεθόδους ποινικοποιημένης πιθανοφάνειας σύμφωνα με το μοντέλο Koziol & Green.
Alternative Title Non parametric estimation of probability density functions with methods of penalized likelihood, according to the Koziol &
Author Ξιφανταράκης, Ιωάννης
Abstract In this master thesis we refer to the non parametric estimation of probability density functions with methods of penalized likelihood, according to the Koziol & Green model, as it is shown in the title. This thesis consists of four chapters. At the first chapter we refer to some introductory elements, we give some useful definitions and we describe the time evolution of our subject. At the second chapter we formulate our estimators. At the third chapter we prove the strong consistency of our estimators according to various norms. Eventually, at the fourth chapter we study algorithmically the problem of the minimization of a functional and the graphic representation of our estimators. Anyhow, we must remark that our algorithm may have some programming errors because the results we receive are not satisfactory.
Language Greek
Subject Koziol & Green model
Non parametric estimation
penalized likelihood
random censorship
Μη παραμετρική εκτίμηση
μοντέλο Koziol & Green
ποινικοποιημένη πιθανοφάνεια
τυχαία κοπή δεδομένων
Issue date 2006-02-02
Collection   School/Department--School of Sciences and Engineering--Department of Mathematics--Post-graduate theses
  Type of Work--Post-graduate theses
Views 244

Digital Documents
No preview available

Download document
View document
Views : 5