Determinants of Inter-trade Durations and Hazard Rates Using Proportional Hazard Arma Models

This paper puts a focus on the hazard function of inter-trade durations to characterize the intraday trading process. It sheds light on the time varying trade intensity and, thus, on the liquidity of an asset and the information channels which propagate price signals among asymmetrically informed market participants. We show, based on an exogenous information process, that the way traders aggregate information has implications for the shape of the hazard function. We use a semiparametric proportional hazard model which is augmented by an ARMA structure very similar to the wide spread ACD model to obtain consistent estimates of the baseline survivor function and to capture well known serial dependencies in the trade intensity process. From an inspection of conditional transaction probabilities based on Bund future transaction data of the DTB we nd a decreasing hazard shape providing evidence for the use of non-trading intervals as an indication for the absence of price information among market participants. However, this information content seems to be diluted by a high liquidity base level, particularly with respect to a large in ow of potential traders from the U.S. Furthermore, we provide evidence that past sequences of prices and volumes have a signi cant impact on the trading intensity in accordance with theoretical models.