Over the last few years, economic analysis in general, and empirical screens in particular, have become increasingly important in cases of conspiracies and manipulations, a trend detailed for example in Abrantes-Metz & Bajari (2009, 2010), Hüschelrath (2010), and Laitenberger & Hüschelrath (2011). Competition authorities and other agencies worldwide have begun using screens to detect possible market conspiracies and manipulations, and defendants and plaintiffs have begun adopting them as well.
Screens use commonly available data such as prices, costs, market shares, bids, transaction quotes, spreads, volumes, and other data to identify patterns that are anomalous or highly improbable. A survey of screening methodologies and their multiple applications can be found in Abrantes-Metz & Bajari (2009, 2010) and Harrington (2008). The use of these methods in conspiracy cases is detailed in the 2010 volume Proof of Conspiracy under Antitrust Federal Laws, by the American Bar Association.
Screens' increased popularity and use on both sides of litigation have enhanced the debate on detection tools, their relative advantages and disadvantages, and the realized experience of those who have adopted them. Motivated by this debate, I propose in this article to achieve a two-fold objective. First, I will address some of the main criticisms commonly made against empirical screens and elaborate on the key features of design and implementation needed for a successful screen. Second, I will demonstrate the development and implementation of a screen on behalf of defendants in a case of an alleged conspiracy and manipulation in commodities markets. As the use of these approaches by defendants is as important as their use by competition authorities and plaintiffs, I take this opportunity to show how screens can be successfully developed and applied on that side of a case.