Using Matched Samples to Test for Differences in Trade Execution Costs


For full text, please contact the Babson Faculty Research Fund.


We consider how to use matched samples to test for differences in bid-ask spreads. Based on extensive simulations, we conclude that it is best to match firms one-to-one based on market capitalization and share price. We demonstrate that pre-sorting by industry groups or eliminating apparent poor matches may reduce test power. We show that tests based on one-to-one matches have comparable power and less size distortion than alternatives that place more weight on distant firms. We provide guidance on optimal estimation when there are few available matched pairs and/or large data measurement errors. We compare matched sample estimation with the corresponding event study.


Corporate Finance | Finance and Financial Management

This document is currently not available here.