Identifying and Pricing Adverse Selection Risk with VPIN

Abstract

We perform the first large-sample estimation of the Volume Synchronized Probability ofInformed Trading (VPIN) measure, validating it and performing pricing tests of informedtrading. The pricing of VPIN is not explained by firm characteristics. A portfolio long(short) high-VPIN (low-VPIN) stocks delivers a monthly five-factor alpha of .18%, whichrises to .29% when using a signed version of the measure (SVPIN). A long-short trade onSVPIN delivers an annualized five-factor BHAR of 11.45%. Incorporating a reversal in stockperformance in portfolio sorts on SVPIN improves BHARs to 17.34%