Munich Personal RePEc Archive

A Multivariate GARCH-Jump Mixture Model

Li, Chenxing and Maheu, John M (2020): A Multivariate GARCH-Jump Mixture Model.


Download (4MB) | Preview


This paper proposes a new parsimonious multivariate GARCH-jump (MGARCH-jump) mixture model with multivariate jumps that allows both jump sizes and jump arrivals to be correlated among assets. Dependent jumps impact the conditional moments of returns as well as beta dynamics of a stock. Applied to daily stock returns, the model identifies co-jumps well and shows that both jump arrivals and jump sizes are highly correlated. The jump model has better predictions compared to a benchmark multivariate GARCH model.

MPRA is a RePEc service hosted by
the Munich University Library in Germany.