Detecting outliers in multivariate volatility models: A wavelet procedure

Aurea Grane, Belen Martin-Barragan, Helena Veiga

Research output: Contribution to journalArticlepeer-review


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.
Original languageEnglish
Pages (from-to)289-316
JournalSORT. Statistics and Operations Research Transactions
Issue number2
Publication statusPublished - 31 Dec 2019


  • correlations
  • multivariate GARCH models
  • outliers
  • wavelets

Fingerprint Dive into the research topics of 'Detecting outliers in multivariate volatility models: A wavelet procedure'. Together they form a unique fingerprint.

Cite this