Please use this identifier to cite or link to this item:
Title: Nonparametric estimation of copulas of financial time series
Keywords: Copulas,Archimedean Copulas,plug-in method, generator function
Issue Date: 18-Mar-2004
Citation: CAO JIANFEI (2004-03-18). Nonparametric estimation of copulas of financial time series. ScholarBank@NUS Repository.
Abstract: Copulas, especially Archimedean copulas, are fit for modelling nonellipticallydistributed multivariate data with different dependent structure,such as multivariate financial return series. They are very useful tools forIntegrated Risk Management. This thesis considers using the kernel smoothingmethod to estimate bivariate copulas and apply them for financial timeseries.In the thesis, we present the theoretical inference on how to use the kernelsmoothing method to estimate the joint distribution functions, the generatorfunctions and the copulas functions. Bandwidth selection is important for thekernel estimators, we use plug-in method to select optimal global bandwidths.Numerical simulations are presented to verify the theoretical results.Applications concern modelling the daily return of S&P 500 compositeindex and NASDAQ composite index and the daily return of Dow Jones Industrialsindex and Hang Seng index with the Gumbel family of Archimedeancopulas. Extending bivariate Archimedean copulas to multivariate cases isdiscussed at the end.
Appears in Collections:Master's Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
copula.pdf2.62 MBAdobe PDF



Page view(s)

checked on Oct 14, 2018


checked on Oct 14, 2018

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.