Go to the content. | Move to the navigation | Go to the site search | Go to the menu | Contacts | Accessibility

| Create Account

Cortese, Giuliana and Sartori, Nicola (2014) Integrated likelihoods in survival models with stratum nuisance parameters. [Working Paper] WORKING PAPER SERIES, 1/2014 . , PADOVA (Inedito)

Full text disponibile come:

PDF Document

Abstract (english)

When inference is about a parameter of interest in presence of many nuisance parameters, in general prole likelihoods perform very poorly and lead to serious bias. For stratied data, this problem is particularly evident in models with stratum nuisance parameters, when the number of strata is relatively high with respect to the within-stratum size. Stratied data are very frequent in many applied settings, such as in cohort studies based on multi-center clinical trials. We consider stratied survival data in a parametric framework under the general assumption of noninformative independent censoring (both type I censoring and random censoring schemes), and for such data an inferential approach based on integrated likelihood is proposed. Appropriately dened integrated likelihoods provide very accurate results in all circumstances. Test statistics based on them provides very accurate inference even in extreme settings. These conclusion were strongly supported by simulation studies. Therefore, the paper suggests to avoid prole likelihood methods and use instead integrated likelihood for inference on highly stratied data with relatively small within-stratum sample sizes.

Statistiche Download - Aggiungi a RefWorks
EPrint type:Working Paper
Anno di Pubblicazione:01 January 2014
Key Words:Noninformative censoring; Prole Likelihood; Right-censored Data; Stratum Nuisance Parameters; Weibull model
Settori scientifico-disciplinari MIUR:Area 13 - Scienze economiche e statistiche > SECS-S/01 Statistica
Struttura di riferimento:Dipartimenti > Dipartimento di Scienze Statistiche
Codice ID:6980
Depositato il:22 Jul 2014 09:38
Simple Metadata
Full Metadata
EndNote Format

Download statistics

Solo per lo Staff dell Archivio: Modifica questo record