Estimating Order Imbalance Using Low Frequency Data
95 Pages Posted: 1 Feb 2016 Last revised: 15 Jan 2018
Date Written: January 12, 2018
We estimate net order flow of individual stocks as a fraction of contemporaneous return and illiquidity proxies at the daily frequency based on the Kyle (1985) model. The estimated low-frequency order imbalance (LFOI) has comparable performance to high-frequency order imbalance (HFOI) in the Nasdaq market. LFOI has positive and permanent predictive ability for future returns on daily and weekly horizons in the cross-section. An investment strategy based on LFOI is profitable in all G10 markets. LFOI becomes more informative around corporate events. As an order imbalance estimate, LFOI can be easily and promptly calculated when tick data are not available.
Keywords: Order flow; low frequency; return predictability; informed trading
JEL Classification: C18; C58; C81; D82; G12; G14
Suggested Citation: Suggested Citation