* Einladung zum Forschungsseminar *
3840 Janko/Otruba/Mitloehner: Artificial Financial Life
SE 2, Tuesday 17.00-19.00, S. 2.19 (A), Begin October 8, 1996.
Interdisciplinary research seminar in connection with the SFB Adaptive
Information Systems and Modelling in Economics and Management Science.
There are two areas of work planned for this term:
Analysis package: participants develop analysis instruments for financial
time series, based on selected literature. This group should consist of
participants with economics and computer science background. The tools -
based on well-documented economic and statistical concepts - will be
employed in future work in SFB projects.
Financial robot competition: financial agents created by the participants
compete against each other on an artificial electronic market. These
robots should employ some form of adaptive behaviour. We aim to explore
how even a population of very simple agents can show complex dynamic
behaviour.
The programming language C++ will be used for implementations. In
preparation for the work within the SFB the seminar language will be
English. The participants will work on projects in small groups and
present their work in the seminar. Well-documented projects and good
presentation will earn the students a seminar certificate for the SBWL
Informationswirtschaft or VWL.
Organized by Leopold.Soegner(a)wu-wien.ac.at (Dep. of Economics/Prof.
Otruba) and Johann.Mitloehner(a)wu-wien.ac.at (Dep. of Applied Computer
Science/Prof. Janko) On the web as
http://www.wu-wien.ac.at/usr/ai/mitloehn/se/w96
Auf Ihre Teilnahme freuen sich
Leopold Soegner & Johann Mitloehner
Johann.Mitloehner(a)wu-wien.ac.at, Abt. Angewandte Informatik
A-1090 Wien, Augasse 2-6, Tel: (+431) 31336-5202, Fax: -739
http://www.wu-wien.ac.at/usr/ai/mitloehn
Einladung
zum
Betriebswirtschaftlichen Forschungsseminar
am BWZ
Prof. Thaleia Zariphopoulou
University of Wisconsin, Madison, USA
Market frictions and Derivative Pricing
Abstract: In this talk, I will address the problem of pricing
derivative securities in markets with frictions, namely transaction
costs and stochastic volatility. The approach is based on utility
maximization and not on replication arguments. The mathematical
tools stem from the theory of stochastic control and nonlinear
differential equations.
Dienstag, 1. Oktober 1996, 14.15 Uhr, HS 8
BWZ
Bruennerstrasse 72,
1210 Wien
o. Prof. W. Schachermayer
=========================================================================
>From Blake Sun Mar 19 17:27:57 2000
>From: Blake LeBaron
To: OWNER-SNDE_L
Subject: Old working paper now published
Date: Wednesday, September 04, 1996 4:26PM
Status: RO
X-Status:
X-Keywords:
X-UID: 272
This paper has been in circulation as a working paper for nearly 10 years,
but it has finally come out:
A Test for Independence Based on the Correlation Dimension,
W. A. Brock,
W. D. Dechert,
J. A. Scheinkman,
B. LeBaron
Econometric Reviews 15(3), 197-235, 1996.
ABSTRACT:
This paper presents a test of independence that can be applied to the
estimated residuals of any time series model that can be transformed into a
model driven by independent and identically distributed errors. The first
order asymptotic distribution of the test statistic is independent of
estimation error provided that the parameters of the model under test can be
estimated sqrt(N)-consistently. Because of this, our method can be used as
a
model selection tool and as a specification test. Widely used software
written by Dechert and LeBaron can be used to implement the test. Also,
this
software is fast enough that the null distribution of our test statistic can
be estimated with bootstrap methods. Our method can be viewed as a
nonlinear
analog of the Box-Pierce Q statistic used in ARIMA methods.
(For software info check http://www.econ.wisc.edu/~blake.)
Note: Also, of related interest is the paper in the same issue,
Nuisance Parameter Free Properties of Correlation Integral Based Statistics,
P. J. F. de Lima,
Econometric Reviews 15(3), 237-259, 1996.
=========================================================================