Picture of rolled up £5 note

Open Access research that shapes economic thinking...

Strathprints makes available scholarly Open Access content by the Fraser of Allander Institute (FAI), a leading independent economic research unit focused on the Scottish economy and based within the Department of Economics. The FAI focuses on research exploring economics and its role within sustainable growth policy, fiscal analysis, energy and climate change, labour market trends, inclusive growth and wellbeing.

The open content by FAI made available by Strathprints also includes an archive of over 40 years of papers and commentaries published in the Fraser of Allander Economic Commentary, formerly known as the Quarterly Economic Commentary. Founded in 1975, "the Commentary" is the leading publication on the Scottish economy and offers authoritative and independent analysis of the key issues of the day.

Explore Open Access research by FAI or the Department of Economics - or read papers from the Commentary archive [1975-2006] and [2007-2018]. Or explore all of Strathclyde's Open Access research...

Approximate uncertainty modeling in risk analysis with vine copulas

Bedford, Tim and Daneshkhah, Alireza and Wilson, Kevin J. (2016) Approximate uncertainty modeling in risk analysis with vine copulas. Risk Analysis, 36 (4). pp. 792-815. ISSN 0272-4332

[img]
Preview
Text (Bedford-etal-RA-2015-Approximate-uncertainty-modelling-in-risk-analysis)
Bedford_etal_RA_2015_Approximate_uncertainty_modelling_in_risk_analysis.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo

Download (1MB) | Preview

Abstract

Many applications of risk analysis require us to jointly model multiple uncertain quantities. Bayesian networks and copulas are two common approaches to modelling joint uncertainties with probability distributions. This paper focuses on new methodologies for copulas by developing work of Cooke, Bedford, Kurowica and others on vines as a way of constructing higher dimensional distributions which do not suffer from some of the restrictions of alternatives such as the multivariate Gaussian copula. The paper provides a fundamental approximation result, demonstrating that we can approximate any density as closely as we like using vines. It further operationalizes this result by showing how minimum information copulas can be used to provide parametric classes of copulas which have such good levels of approximation. We extend previous approaches using vines by considering non-constant conditional dependencies which are particularly relevant in financial risk modelling. We discuss how such models may be quantified, in terms of expert judgement or by fitting data, and illustrate the approach by modelling two financial datasets.