Forecasting the frequency of changes in quoted foreign exchange prices with the autoregressive conditional duration model

Abstract

This paper applies the Autorecressive Conditional Duration model to Foreign Exchange quotes arriving on Reuters screens. The Autoregressive Conditional Duration model, developed in Engle and Russell (1995) [Engle, R., Russell, J., 1995. Autoregressive conditional duration; a new model for irregularly spaced time series data, University of California, San Diego, unpublished manuscript.], is a new statistical model for the analysis of data that does not arrive in equal time intervals. When Dollar/Deutschmark data are examined, it is clear that many of the price quotes are simply noisy repeats of the previous quote. By systematically thinning the sample, a measure of the time between price changes is developed. These price durations are modeled with the ACD to obtain estimates of the instantaneous intensity of price changes. This measure is related to standard measures of volatility but is formulated in a way that incorporates the information in the irregular sampling intervals. A simple market microstructure model implies that the bid-ask spread should have predictive power for the volatility which is supported by the data. A model of price leadership however, is not supported.