Management Differences and Productivity: A Simulated Investigation into Dummy Variables in Two-Stage Data Envelopment Analysis
18 Pages Posted: 2 Feb 2016 Last revised: 22 Nov 2016
Date Written: October 6, 2016
This paper tests the ability of two-stage DEA to pick up on efficiency differences between two groups. Using the context of franchising, I simulate establishment-level data and give franchisee-owned establishments an artificial output bump of various sizes. In the second stage, I test the two of the more common second-stage specifications, OLS and Tobit, against a bootstrap method advocated by Simar and Wilson (2007). Using a dummy variable for ownership, I find that two-stage DEA is able to detect that franchisee-owned establishments are more efficient than their franchisor-owned counterparts using all three second-stage specifications. The results suggest that the estimated difference in efficiency found in the second stage should be thought of as a lower bound on the true effect.
Suggested Citation: Suggested Citation