From nader@maths.lth.se Wed Oct 4 15:14:45 2000 Received: from celsius.maths.lth.se (celsius [130.235.3.14]) by maths.lth.se (8.9.1b+Sun/8.9.1) with ESMTP id PAA01742 for ; Wed, 4 Oct 2000 15:14:45 +0200 (MET DST) Received: (from nader@localhost) by celsius.maths.lth.se (8.9.3+Sun/8.9.1) id PAA02759; Wed, 4 Oct 2000 15:14:41 +0200 (MEST) MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit Message-ID: <14811.11585.333472.150540@celsius.maths.lth.se> Date: Wed, 4 Oct 2000 15:14:41 +0200 To: Søren Asmussen Subject: Abstract X-Mailer: VM 6.76 under Emacs 19.34.1 Reply-To: nader@maths.lth.se From: Nader.Tajvidi@maths.lth.se X-No-Archive: yes Content-Length: 1557 Status: RO Hej! Här skickar jag titeln och abstraktet till mitt seminarium. Mvh, Nader Title: On Distribution Estimation and Prediction for Bivariate Extreme-Value Distributions ABSTRACT: Two new methods are suggested for estimating the dependence function of a bivariate extreme-value distribution. One is based on a multiplicative modification of an earlier technique suggested by Pickands, and the other employs spline smoothing under constraints. Both produce estimators that satisfy all the conditions that define a dependence function, including convexity and the restriction that its curve lie within a certain triangular region. The first approach does not require selection of smoothing parameters; the second does, and for that purpose we suggest explicit tuning methods, one of them based on cross-validation. Applications of our dependence function estimators to estimating the full bivariate distribution, and its density, are described, as too are applications to prediction. Indeed, the cross-validation algorithm is designed to provide near-optimal performance when estimating the bivariate density, and is particularly useful for constructing compact prediction regions by the method of profiling. -- --------------------------------------------------------------- Nader Tajvidi Email: nader@maths.lth.se Telephone: +46 46 2229612 Telefax: +46 46 2224623 http://www.maths.lth.se/matstat/staff/nader/ Department of Mathematical Statistics Lund Institute of Technology Box 118 SE-22100 Lund, Sweden