Forecasting the intra-day effective bid ask spread: a comparison of models via density forecasts

Présentation de Malick Fall (CREM, Univ. Rennes 1)

2018-09-20_sem_fse

Malick Fall (CREM, Univ. Rennes 1)
En coll. avec Jean-Laurent Viviani (CREM, Univ. Rennes 1)

Abstract: We compare the forecasting power of a series of univariate econometrics models to predict the effective intra-day bid-ask spread series of CAC40 constituents.  Multiplicative Errors Models  and  ARMA-GARCH  types  of  models  are  compared  in  a  one-step-ahead  out-of-sample density forecast framework.  The Model Confidence Set procedure of Hansen et al. (2011) is employed to classify models and the potential benefit of combining density forecast is investigated.

Keywords: Liquidity, Multiplicative Errors Models, Forecasting