Distributional Properties and Deviations of Transaction Sizes in U.S. Equities

Abstract

In order to get a comprehensive understanding of the market dynamics, we need to investigate the relationship between price and volume. However, it is a well known fact that it takes volume to move prices. We analyze the transaction data of S&P 500 stocks and found that the transaction size displays a power-law decay and can be characterized by an exponent within the stable Levy domain. Further more, most interestingly there are significant positive deviations at transaction sizes of 100, 500, 1000, 1500, 2000, 2500, 3000, 4000, 5000, 6000, …, 10000, for the S&P 500 companies. In other words, there are more trades at above trade sizes than anticipated by the Pareto distribution.

TOPICS: Statistical methods, volatility measures, exchanges/markets/clearinghouses