Detecting outliers in multivariate volatility models

It is well known that outliers can affect both the estimation of parameters and volatilities when fitting a univariate GARCH-type model. Similar biases and impacts are expected to be found on correlation dynamics in the context of multivariate time series. We study the impact of outliers on the esti...

Descripción completa

Detalles Bibliográficos
Autores: Grané, Aurea|||0000-0003-0980-6409, Martín-Barragán, Belén|||0000-0003-4807-2700, Veiga, Helena|||0000-0002-6810-7950
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universitat Autònoma de Barcelona
Repositorio:Dipòsit Digital de Documents de la UAB
Idioma:inglés
OAI Identifier:oai:ddd.uab.cat:218271
Acceso en línea:https://ddd.uab.cat/record/218271
https://dx.doi.org/urn:doi:10.2436/20.8080.02.89
Access Level:acceso abierto
Palabra clave:Correlations
Multivariate GARCH models
Outliers
Wavelets
Descripción
Sumario:It is well known that outliers can affect both the estimation of parameters and volatilities when fitting a univariate GARCH-type model. Similar biases and impacts are expected to be found on correlation dynamics in the context of multivariate time series. We study the impact of outliers on the estimation of correlations when fitting multivariate GARCH models and propose a general detection algorithm based on wavelets, that can be applied to a large class of multivariate volatility models. Its effectiveness is evaluated through a Monte Carlo study before it is applied to real data. The method is both effective and reliable, since it detects very few false outliers.