Stark, Florian ORCID: 0000-0001-7419-6702 (2019). Detecting Structural Breaks in Factor Copula Models and in Vectors of Dependence Measures. PhD thesis, Universität zu Köln.

[img]
Preview
PDF
Dissertation.pdf

Download (1MB) | Preview

Abstract

We propose new fluctuation tests for detecting structural breaks in factor copula models and analyse the behavior under the null hypothesis of no parameter change. In the model, the joint copula is given by the copula of random variables which arise from a factor model. This is particularly useful for analysing data with high dimensions. Parameters are estimated with the simulated method of moments (SMM). The discontinuity of the SMM objective function complicates the derivation of a functional limit theorem for the parameters. We analyse the behavior of the tests in Monte Carlo simulations and a real data application. It turns out that our test is more powerful than nonparametric tests for copula constancy in high dimensions. Further, we propose a new monitoring procedure based on moving sums (MOSUM) for detecting single or multiple structural breaks in factor copula models. The test compares parameter estimates from a rolling window to those from a historical data set and analyzes the behavior under the null hypothesis of no parameter change. The case of multiple breaks is also treated. Parameters are again estimated with the simulated method of moments (SMM). We analyze the behavior of the monitoring procedure in Monte Carlo simulations and a real data application. We consider an online procedure for predicting the day-ahead Value-at-risk based on the suggested monitoring procedure. Lastly, we investigate a cumulative sum (CUSUM) type test for constant dependence measures, considering pairwise averaged Spearman's rho and quantile dependencies in an equidependence setting. The asymptotic null distribution is not known in closed form and therefore estimated by an i.i.d. bootstrap procedure. To decide whether two estimated break point locations using different subsets of the studied dependence measures, belong to the same break event we propose a heuristic procedure. We apply the test for different dependence settings to historical data of ten large financial firms during the last financial crisis. The results suggest that the tests are suitable for financial data applications and useful for portfolio optimization.

Item Type: Thesis (PhD thesis)
Creators:
CreatorsEmailORCIDORCID Put Code
Stark, Florianfstark3@uni-koeln.deorcid.org/0000-0001-7419-6702UNSPECIFIED
Editors:
EditorsEmailORCIDORCID Put Code
Stark, Florianfstark3@uni-koeln.deorcid.org/000-0001-7419-6702UNSPECIFIED
URN: urn:nbn:de:hbz:38-95004
Number of Pages: 156
Date: 3 April 2019
Language: English
Faculty: Faculty of Management, Economy and Social Sciences
Divisions: Faculty of Management, Economics and Social Sciences > Economics > Econometrics and Statistics > Professorship for Statistics and Econometrics
Subjects: General statistics
Economics
Mathematics
Uncontrolled Keywords:
KeywordsLanguage
Factor Copula ModelEnglish
Fluctuation TestEnglish
Simulated method of momentsEnglish
MonitoringUNSPECIFIED
Value at RiskEnglish
VaREnglish
DependenceEnglish
Common breakEnglish
Date of oral exam: 26 March 2019
Referee:
NameAcademic Title
Wied, DominikProf. Dr.
Steinebach, JosefProf. i.R. Dr.
Funders: Deutsche Forschungsgemeinschaft
Refereed: Yes
URI: http://kups.ub.uni-koeln.de/id/eprint/9500

Downloads

Downloads per month over past year

Export

Actions (login required)

View Item View Item