Using a Fractional Factorial Design to Increase Direct Mail Response at Mother Jones Magazine Johannes Ledolter University of Iowa, Iowa City, Iowa, USA Arthur J. Swersey Yale School of Management, New Haven, Connecticut, USA Experimental design methods have been widely applied to problems in manufacturing, but little attention has been given to applying these tools to service problems. In the world of direct marketing, the traditional approach is called A=B testing and involves changing one factor at a time. In this article we address the problem of improving direct mail response at Mother Jones magazine, employing a 16-run two-level fractional factorial design that tests seven factors simultaneously. We compare this design to other possible design choices, discuss sample size determination, and show how we labeled factors to isolate likely two-factor interac- tions. We discuss the results and conclusions of our study and the benefits to Mother Jones magazine. Keywords Confounding; Direct mail marketing; Fractional factorial experiments; Mother Jones magazine; Sample size. INTRODUCTION Experimental design methods have been widely applied to manufacturing problems, with numerous case studies and examples published in Quality Engi- neering and other journals. Bisgaard (1992) provides a notable, historical review of experimental design case studies that includes what he calls ‘‘a partial and unsys- tematic list of articles...showing engineering and man- ufacturing applications of experimental design.’’ This list comprises more than 130 case studies. More recent case studies applying experimental design methods to manufacturing problem are papers by Lin and Chanada (2003), Cherfi et al. (2002), Schaub and Montgomery (1997), and Young (1996). In contrast to work on manufacturing problems, applications of experimental design to marketing and other service problems have been limited with pub- lished case studies rarely appearing in the academic lit- erature. In searching for service applications of experimental design, we found a few early papers all in the marketing literature. Curhan (1974) used a two-level fractional factorial design to test the effects of price, advertising, display space, and display loca- tion on sales of fresh fruits and vegetables in supermar- kets, while Barclay (1969) used a factorial design to evaluate the effect on profitability of raising the prices of two retail products manufactured by the Quaker Oats Company. Holland and Cravens (1973) presented the essential features of fractional factorial design and illustrated them with a hypothetical example concern- ing the effect of advertising and other factors on the sales of candy bars. Wilkinson et al. (1982) described a factorial experiment for assessing the impact of price, promotion, and display on the sales of selected items at Piggly Wiggly grocery stores. This article describes how a fractional factorial design was used by Mother Jones magazine to increase its subscription response rates. Our purpose in present- ing this case study is both to report on a successful application and to highlight the opportunity that exists for quality engineers and other quality professionals to apply experimental design methods to service pro- blems. These applications include the optimal design of websites, direct mail marketing of magazines, credit cards and other products, and various in-store market- ing experiments to evaluate changes in factors such as package design, price, and advertising displays. Mother Jones, published six times a year, and known for its political muckraking, is named for Mary Harris Address correspondence to Johannes Ledolter, Manage- ment Sciences, University of Iowa, S352 PBB, 21 E. Market Street, Iowa City, IA 52242. E-mail: johannes-ledolter@ uiowa.edu Quality Engineering, 18:469–475, 2006 Copyright # Taylor & Francis Group, LLC ISSN: 0898-2112 print=1532-4222 online DOI: 10.1080/08982110600846622 469