A Network-Based Analysis for Evaluating Conditional Covariance Estimates
The modeling and forecasting of dynamically varying covariances has received a great deal of attention in the literature. The two most widely used conditional covariances and correlations models are BEKK and the DCC. In this paper, we advance a new method based on network analysis and a new targetin...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/2/382 |
| _version_ | 1797438988374507520 |
|---|---|
| author | Carlo Drago Andrea Scozzari |
| author_facet | Carlo Drago Andrea Scozzari |
| author_sort | Carlo Drago |
| collection | DOAJ |
| description | The modeling and forecasting of dynamically varying covariances has received a great deal of attention in the literature. The two most widely used conditional covariances and correlations models are BEKK and the DCC. In this paper, we advance a new method based on network analysis and a new targeting approach for both the above models with the aim of better estimating covariance matrices associated with financial time series. Our approach is based on specific groups of highly correlated assets in a financial market and assuming that those relationships remain unaltered at least in the long run. Based on the estimated parameters, we evaluate our targeting method on simulated series by referring to two well-known loss functions introduced in the literature. Furthermore, we find and analyze all the maximal cliques in correlation graphs to evaluate the effectiveness of our method. Results from an empirical case study are encouraging, mainly when the number of assets is not large. |
| first_indexed | 2024-03-09T11:46:21Z |
| format | Article |
| id | doaj.art-3b5c0a8b52434860a638ea5e9a43ce90 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-09T11:46:21Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-3b5c0a8b52434860a638ea5e9a43ce902023-11-30T23:21:25ZengMDPI AGMathematics2227-73902023-01-0111238210.3390/math11020382A Network-Based Analysis for Evaluating Conditional Covariance EstimatesCarlo Drago0Andrea Scozzari1Facoltà di Economia, Università degli Studi Niccolò Cusano Roma, 00166 Roma, ItalyFacoltà di Economia, Università degli Studi Niccolò Cusano Roma, 00166 Roma, ItalyThe modeling and forecasting of dynamically varying covariances has received a great deal of attention in the literature. The two most widely used conditional covariances and correlations models are BEKK and the DCC. In this paper, we advance a new method based on network analysis and a new targeting approach for both the above models with the aim of better estimating covariance matrices associated with financial time series. Our approach is based on specific groups of highly correlated assets in a financial market and assuming that those relationships remain unaltered at least in the long run. Based on the estimated parameters, we evaluate our targeting method on simulated series by referring to two well-known loss functions introduced in the literature. Furthermore, we find and analyze all the maximal cliques in correlation graphs to evaluate the effectiveness of our method. Results from an empirical case study are encouraging, mainly when the number of assets is not large.https://www.mdpi.com/2227-7390/11/2/382network analysismining financial datamaximal cliquesmultivariate GARCH modelsBEKKDCC |
| spellingShingle | Carlo Drago Andrea Scozzari A Network-Based Analysis for Evaluating Conditional Covariance Estimates Mathematics network analysis mining financial data maximal cliques multivariate GARCH models BEKK DCC |
| title | A Network-Based Analysis for Evaluating Conditional Covariance Estimates |
| title_full | A Network-Based Analysis for Evaluating Conditional Covariance Estimates |
| title_fullStr | A Network-Based Analysis for Evaluating Conditional Covariance Estimates |
| title_full_unstemmed | A Network-Based Analysis for Evaluating Conditional Covariance Estimates |
| title_short | A Network-Based Analysis for Evaluating Conditional Covariance Estimates |
| title_sort | network based analysis for evaluating conditional covariance estimates |
| topic | network analysis mining financial data maximal cliques multivariate GARCH models BEKK DCC |
| url | https://www.mdpi.com/2227-7390/11/2/382 |
| work_keys_str_mv | AT carlodrago anetworkbasedanalysisforevaluatingconditionalcovarianceestimates AT andreascozzari anetworkbasedanalysisforevaluatingconditionalcovarianceestimates AT carlodrago networkbasedanalysisforevaluatingconditionalcovarianceestimates AT andreascozzari networkbasedanalysisforevaluatingconditionalcovarianceestimates |