This paper tests how well the method proposed by Bajari and Ye (2003) performs to detect bidrigging cartels. In the case investigated in this paper, the bid-rigging cartel rigged all contracts during the collusive period, and all firms participated to the bid-rigging cartel. The two econometric tests constructed by Bajari and Ye (2003) produce a high number of false negative results: the tests do not reject the null hypothesis of competition, although they should have rejected it. A robustness analysis replicates the econometric tests on two different sub-samples, composed solely by cover bids. On the first sub-sample, both tests produce again a high number of false negative results. However, on the second sub-sample, one test performs better to detect the bidrigging cartel. The paper interprets these results, discusses alternative methods, and concludes with recommendations for competition agencies.
Read online and download on Rero-Doc