Determinants of Inter-Trade Durations Using Proportional Hazard ARMA Models

This paper disseminates the survivor function of inter-trade durations as a key feature of the intraday trading process. It sheds light on the time varying trading intensity and, thus, liquidity of a traded asset and the information channels which propagate price signals among asymmetrically informed market participants. To obtain a consistent estimate of the baseline survivor function and capture well-known serial dependency in the trade intensity process as well we use a semiparametric proportional hazard model wich is augmented by an ARMA structure very similar to the obiquous ACD model. Based on transaction data from the DTB, Frankfurt, we find evidence that past sequences of prices and volumes have a significant impact on the trading intensity in accordance with theoretical models on the basis of rational expectations equilibria. However, we cannot find any evidence in favour of strategic behaviour with respect to the chosen transaction volume by informed traders. From an inspection of conditional failure probabilities we find weak 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 large inflow of traders of the U.S.~market.