UNIGE document Scientific Article
previous document  unige:79880  next document
add to browser collection

Multivariate wavelet-based shape-preserving estimation for dependent observations

Cosma, Antonio
von Sachs, Rainer
Published in Bernoulli. 2007, vol. 13, no. 2, p. 301-329
Abstract We introduce a new approach on shape preserving estimation of cumulative distribution functions and probability density functions using the wavelet methodology for multivariate de- pendent data. Our estimators preserve shape constraints such as monotonicity, positivity and integration to one, and allow for low spatial regularity of the underlying functions. We discuss conditional quantile estimation for financial time series data as an application. Our methodology can be implemented with B-splines. We show with Monte Carlo simulations that it performs well in finite samples and for a data-driven choice of the resolution level.
Keywords Conditional quantileTime seriesShape preserving wavelet estimationB-splinesMultivariate process
Full text
Research group Geneva Finance Research Institute (GFRI)
(ISO format)
COSMA, Antonio, SCAILLET, Olivier, VON SACHS, Rainer. Multivariate wavelet-based shape-preserving estimation for dependent observations. In: Bernoulli, 2007, vol. 13, n° 2, p. 301-329. doi: 10.3150/07-BEJ5066 https://archive-ouverte.unige.ch/unige:79880

369 hits



Deposited on : 2016-01-22

Export document
Format :
Citation style :