Quantile Sieve Estimates for Time Series

  • We consider the problem of estimating the conditional quantile of a time series at time \(t\) given observations of the same and perhaps other time series available at time \(t-1\). We discuss sieve estimates which are a nonparametric versions of the Koenker-Bassett regression quantiles and do not require the specification of the innovation law. We prove consistency of those estimates and illustrate their good performance for light- and heavy-tailed distributions of the innovations with a small simulation study. As an economic application, we use the estimates for calculating the value at risk of some stock price series.

Export metadata

  • Export Bibtex
  • Export RIS

Additional Services

Share in Twitter Search Google Scholar
Metadaten
Author:Jürgen Franke, Jean-Pierre Stockis, Joseph Tadjuidje
URN (permanent link):urn:nbn:de:hbz:386-kluedo-14779
Serie (Series number):Report in Wirtschaftsmathematik (WIMA Report) (105)
Document Type:Preprint
Language of publication:English
Year of Completion:2007
Year of Publication:2007
Publishing Institute:Technische Universität Kaiserslautern
Tag:conditional quantile ; neural network ; qualitative threshold model; sieve estimate ; time series
Faculties / Organisational entities:Fachbereich Mathematik
DDC-Cassification:510 Mathematik

$Rev: 12793 $