The aims of this paper are to explore the role of variations and commonalities in Medium-N comparative analysis and to suggest a technique that could maximize their explanatory power in the context of medium-N comparative designs, especially those designs that combine two or more comparative approaches to the study of regulatory change. The paper identifies four popular comparative approaches to the study of politics and policy in general and regulation in particular. These four might best be titled the National Patterns Approach (NPA), the Policy Sector Approach (PSA), the International Regime Approach (IRA), and the Temporal Patterns Approach (TPA). While these approaches are not necessarily contradictory they represent different assumptions as to the determinant of political and regulatory change. Each of these approaches omits some important sources of variations and commonalties in the regulation of the economy and society. To overcome these omissions it is suggested that combinations of these approaches - through complex research designs - might prove a more sound and effective method for the study of regulation.