Estimating Information Asymmetry in Securities Markets

We propose and estimate a model of informed trading that is a hybrid of the PIN and Kyle models. The relationships between price impacts and the estimated parameters are consistent with the model’s theoretical predictions. We compare the hybrid model estimates to PIN estimates. The probability of information events in the PIN model is negatively correlated with the hybrid model’s estimated probability and with price impacts. A composite information asymmetry measure explains more cross-sectional variation in price impacts than does PIN, whose explanatory power stems primarily from its liquidity trading parameter. The empirical results are consistent with the model’s implication that both prices and order flows are necessary to identify private information. Versions of this paper were presented under various titles at the University of Colorado, the SEC, the NYU Stern Microstructure Conference, and the University of Chicago Market Microstructure and High Frequency Data Conference. We thank Pete Kyle, Rob Engle, and seminar participants for helpful comments. Email addresses: [email protected] (Kerry Back), [email protected] (Kevin Crotty), [email protected] (Tao Li)