Using Spatial Econometrics to Test for Collusive Behavior in Procurement Auction Data

Abstract

In this paper we evaluate whether spatial econometric techniques can be used to test for collusive bidder behavior in public procurement auctions, using the submitted bids and procurement characteristics. The proposed method is applied to the so-called Swedish asphalt cartel, which was discovered in 2001. As our dataset covers the period 1995-2009, we are able to test for conditional independence between complementary cartel bids before and after the detection. Our estimates show a significant positive correlation between complementary cartel bids during the cartel period, whereas a non-significant (and negative) correlation is shown during the later period. The parameter estimate of interest also differs in magnitude between periods. Hence, we argue that the method suggested can be used to verify or possibly screen for collusive bidding behavior. The main advantage of this method is its relatively small data requirements.