1.

Record Nr.

UNINA9910437860803321

Autore

Ferrario Paola <1963->

Titolo

Local variance estimation for uncensored and censored observations / / Paola Gloria Ferrario

Pubbl/distr/stampa

Dordrecht, : Springer, 2013

ISBN

3-658-02314-7

Edizione

[1st ed. 2013.]

Descrizione fisica

1 online resource (xvii, 130 pages) : illustrations

Collana

Gale eBooks

Disciplina

519.546

Soggetti

Data mining

Variational inequalities

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Note generali

Description based upon print version of record.

Nota di bibliografia

Includes bibliographical references.

Nota di contenuto

Least Squares Estimation of the Local Variance via Plug-In.- Local Averaging Estimation of the Local Variance via Plug-In -- Partitioning Estimation of the Local Variance via Nearest Neighbors -- Estimation of the Local Variance under Censored Observations.

Sommario/riassunto

Paola Gloria Ferrario develops and investigates several methods of nonparametric local variance estimation. The first two methods use regression estimations (plug-in), achieving least squares estimates as well as local averaging estimates (partitioning or kernel type). Furthermore, the author uses a partitioning method for the estimation of the local variance based on first and second nearest neighbors (instead of regression estimation). Approaching specific problems of application fields, all the results are extended and generalised to the case where only censored observations are available. Further, simulations have been executed comparing the performance of two different estimators (R-Code available!). As a possible application of the given theory the author proposes a survival analysis of patients who are treated for a specific illness.   Contents ·         Least Squares Estimation of the Local Variance via Plug-In ·         Local Averaging Estimation of the Local Variance via Plug-In ·         Partitioning Estimation of the Local Variance via Nearest Neighbors ·         Estimation of the Local Variance under Censored Observations     Target Groups ·         Researchers and graduate students in the fields of mathematics and statistics ·         Practitioners in the fields of medicine,



reliability, finance, and insurance     Author Paola Gloria Ferrario received her doctorate degree (doctor rerum naturalium) from the University of Stuttgart, Germany, in 2012, after having studied Mathematical Engineering at the Polytechnic of Milano, Italy. She taught mathematics to students of economics at University of Hohenheim and now works as a researcher at the University of Lübeck, Germany.