Easley, Kiefer, O'Hara & Paperman (1996) - Probability of Informed Trading (PIN)
Key Insights
- Easley, Kiefer, O'Hara and Paperman develop a structural model to estimate the probability of informed trading (PIN) from order flow data, providing an empirical measure of information asymmetry in securities markets.
Edit on GitHub — registry.json
Overview
Easley, Kiefer, O'Hara and Paperman (1996) develop the first structural model for estimating the probability of informed trading (PIN) from observable transaction data. PIN has become one of the most widely used measures of information asymmetry in empirical market microstructure research.
Model Framework
The model extends the sequential trade framework of Glosten-Milgrom. Each day has an information event with probability alpha. Informed traders know whether the news is good (delta) or bad (1-delta). Informed traders arrive at rate mu, uninformed buyers and sellers at rate epsilon. The likelihood function for observed buy/sell orders combines these parameters.
PIN = alpha * mu / (alpha * mu + 2*epsilon) — the ratio of informed order flow to total order flow.
Key Results
- PIN is estimable: MLE from daily buy/sell order counts yields an information asymmetry measure.
- Cross-sectional patterns: Higher PIN for small caps, less liquid stocks, and those with wider analyst disagreement.
- Extensions: VPIN uses volume buckets instead of time for intraday estimation.
Significance
PIN is one of few directly computable information asymmetry measures from public data. It has been used in hundreds of studies on information in asset pricing, market quality, and regulation.
Further Reading
- Easley, David, et al. "Liquidity, Information, and Infrequently Traded Stocks." Journal of Finance 51, no. 4 (1996): 1405-36.
- Easley, David, and Maureen O'Hara. "Time and the Process of Security Price Adjustment." Journal of Finance (1992).