Outlier Detection in GARCH Models.
We present a new procedure for detecting multiple additive outliers in GARCH(1,1) models at unknown dates. The outlier candidates are the observations with the largest standardized residual. First, a likelihood-ratio based test determines the presence and timing of an outlier. Next, a second test de...
| Main Authors: | , |
|---|---|
| Format: | Working paper |
| Language: | English |
| Published: |
Tinbergen Institute
2005
|
| _version_ | 1797083638490202112 |
|---|---|
| author | Doornik, J Ooms, M |
| author_facet | Doornik, J Ooms, M |
| author_sort | Doornik, J |
| collection | OXFORD |
| description | We present a new procedure for detecting multiple additive outliers in GARCH(1,1) models at unknown dates. The outlier candidates are the observations with the largest standardized residual. First, a likelihood-ratio based test determines the presence and timing of an outlier. Next, a second test determines the type of additive outlier (volatility or level). The tests are shown to be similar with respect to the GARCH parameters. Their null distribution can be easily approximated from an extreme value distribution, so that computation of "p"-values does not require simulation. The procedure outperforms alternative methods, especially when it comes to determining the date of the outlier. We apply the method to returns of the Dow Jones index, using monthly, weekly, and daily data. The procedure is extended and applied to GARCH models with Student-"t" distributed errors. |
| first_indexed | 2024-03-07T01:44:15Z |
| format | Working paper |
| id | oxford-uuid:97e168a4-4baa-4557-8ae8-bdf4916f9ee1 |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-03-07T01:44:15Z |
| publishDate | 2005 |
| publisher | Tinbergen Institute |
| record_format | dspace |
| spelling | oxford-uuid:97e168a4-4baa-4557-8ae8-bdf4916f9ee12022-03-27T00:03:01ZOutlier Detection in GARCH Models.Working paperhttp://purl.org/coar/resource_type/c_8042uuid:97e168a4-4baa-4557-8ae8-bdf4916f9ee1EnglishDepartment of Economics - ePrintsTinbergen Institute2005Doornik, JOoms, MWe present a new procedure for detecting multiple additive outliers in GARCH(1,1) models at unknown dates. The outlier candidates are the observations with the largest standardized residual. First, a likelihood-ratio based test determines the presence and timing of an outlier. Next, a second test determines the type of additive outlier (volatility or level). The tests are shown to be similar with respect to the GARCH parameters. Their null distribution can be easily approximated from an extreme value distribution, so that computation of "p"-values does not require simulation. The procedure outperforms alternative methods, especially when it comes to determining the date of the outlier. We apply the method to returns of the Dow Jones index, using monthly, weekly, and daily data. The procedure is extended and applied to GARCH models with Student-"t" distributed errors. |
| spellingShingle | Doornik, J Ooms, M Outlier Detection in GARCH Models. |
| title | Outlier Detection in GARCH Models. |
| title_full | Outlier Detection in GARCH Models. |
| title_fullStr | Outlier Detection in GARCH Models. |
| title_full_unstemmed | Outlier Detection in GARCH Models. |
| title_short | Outlier Detection in GARCH Models. |
| title_sort | outlier detection in garch models |
| work_keys_str_mv | AT doornikj outlierdetectioningarchmodels AT oomsm outlierdetectioningarchmodels |