From - Fri May 11 09:49:50 2001
Received: from maths.lth.se (matcent28 [130.235.3.108])
	by maths.lth.se (8.9.1b+Sun/8.9.1) with ESMTP id IAA19289
	for <asmus@maths.lth.se>; Fri, 11 May 2001 08:05:30 +0200 (MET DST)
Message-ID: <3AFB8127.2F06791E@maths.lth.se>
Date: Fri, 11 May 2001 08:05:27 +0200
From: Aurelia Vogel <aurelia@maths.lth.se>
X-Mailer: Mozilla 4.76 [en] (Win98; U)
X-Accept-Language: en
MIME-Version: 1.0
To: asmus@maths.lth.se
Subject: Seminarium =?iso-8859-1?Q?p=E5?= fredagen
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 8bit
X-Mozilla-Status: 8001
X-Mozilla-Status2: 00000000
X-UIDL: 6fe1aeb178233c9fdf87c29430593d94


Seminarium i matematisk statistik fredagen 11 maj 13.15  i MH227


Thomas Mikosch, Köpenhamn


Modeling dependence and fat tails in financial data

Abstract

Return time series of share prices, stock indices, FX rates, etc. have
in common that they are extremely heavy-tailed (when considered as
realizations of stationary sequences). Moreover, the extremes of such
sequences tend to occur in clusters (clustering of volatility,
dependence in the tails).

We consider the theoretical properties of some standard models (GARCH,
stochastic volatility models) and check whether the empirically observed
facts can be explained by these models.