BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Copula Shrinkage and Portfolio Allocation in Ultra-High Dimensions
DTSTART:20220629T084000Z
DTEND:20220629T090000Z
DTSTAMP:20240224T221900Z
UID:indico-contribution-351@conferences.enbis.org
DESCRIPTION:Speakers: Vladimir Pyrlik (CERGE-EI)\, Stanislav Anatolyev (CE
RGE-EI)\n\nThe problem of allocation of large portfolios requires modeling
joint distributions\, for which the copula machinery is most convenient.
While currently copula-based settings are used for a few hundred variables
\, we explore and promote the possibility of employing dimension-reduction
tools to handle the problem in ultra-high dimensions\, up to thousands of
variables that use up to 30 times shorter sample lengths.\n\nRecently\, s
tatistics research focused on developing covariance matrix estimators robu
st to and well-conditioned under the data dimensionality growing along wit
h the sample size. One approach is to adjust the traditional sample correl
ation matrix by directly restricting its eigenvalues to achieve better pro
perties under high data dimensionality. These advances rather conveniently
match the structure of Gaussian and t copulas\, which allows one to use s
hrinkage estimators to estimate the matrix parameters of Gaussian and t co
pulas in high dimensional datasets. \n\nWe apply the method to a large por
tfolio allocation problem and compare emerging portfolios to those from a
multivariate normal model and traditional copula estimators. Using daily d
ata on prices of U.S. stocks\, we construct portfolios of up to 3600 asset
s and simulate buy-and-hold portfolio strategies. The joint distributional
models of asset returns are estimated over a period of six months\, i.e.
120 observations. The comparisons show that the shrinkage-based estimators
applied to t copula based models deliver better portfolios in terms of bo
th cumulative return and maximum downfall over the portfolio lifetime than
the aforementioned alternatives.\n\nhttps://conferences.enbis.org/event/1
8/contributions/351/
LOCATION:EL5
RELATED-TO:indico-event-18@conferences.enbis.org
URL:https://conferences.enbis.org/event/18/contributions/351/
END:VEVENT
END:VCALENDAR