Simple Statistical Screens to Detect Bid Rigging

The paper applies simple statistical screens to a bid-rigging cartel in Switzerland, and shows how well the screens detect it by capturing the impact of collusion on the discrete distribution of the bids. In case of bid rigging, the support for the distribution of the bids decreases involving a lower variance, illustrated by the coefficient of variance and the kurtosis statistic. Furthermore, when firms rig bids without side-payment, the difference between the first and the second lowest bids increases whereas the difference between the losing bids decreases, involving a negatively skewed distribution of the bids, highlighted by the relative distance and the skewness statistic. Finally, the collusive interaction screen shows that the behaviour of firms changed radically between the cartel and post-cartel periods. Therefore, the simple statistical screens proposed in this paper purpose to screen large dataset and to detect bidrigging cartels by using only information on bids.