This paper evaluates the performance of 17 different parametric and non-parametric specifications and high frequency data for Colombian exchange market index (IGBC). We model the variance of the 10-minute returns using GARCH-M and TGARCH models that take in account the leverage effect, the day-of-the-week effect, and the hour-of-the-day effect. We estimate those models under two assumptions of the behavior of the returns: Normal distribution and t distribution. This exercise is performed for two different ten-minute intraday samples: 2006-2007 and 2008-2009. For the first sample, we found that the best model is a GARCH-M (1,1) with the hour-of-the-day effect. For the 2008-2009 sample, we found that the model with the correct conditional VAR coverage would be the GARCH-M with the day-of-the-week effect, and the hour-of-the-day effect.
