Authors: | Wied, Dominik Weiß, Gregor N. F. Ziggel, Daniel |
Title: | Evaluating value-at-risk forecasts |
Other Titles: | A new set of multivariate backtests |
Language (ISO): | en |
Abstract: | We propose two new tests for detecting clustering in multivariate Value-at-Risk (VaR) forecasts. First, we consider CUSUM-tests to detect first-order instationarities in the matrix of VaR-violations. Second, we propose χ 2-tests for detecting cross-sectional and serial dependence in the VaR-forecasts. Moreover, we combine our new backtests with a test of unconditional coverage to yield two new backtests of multivariate conditional coverage. In all cases, a bootstrap approximation is possible, but not mandatory in terms of empirical size and power. |
Subject Headings: | Model Risk Value-at-Risk Multivariate Backtesting |
URI: | http://hdl.handle.net/2003/33998 http://dx.doi.org/10.17877/DE290R-7210 |
Issue Date: | 2015 |
Appears in Collections: | Sonderforschungsbereich (SFB) 823 |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
DP_0915_SFB823_Wied_Weiss_Ziggel.pdf | DNB | 149.96 kB | Adobe PDF | View/Open |
This item is protected by original copyright |
This item is protected by original copyright
rightsstatements.org