2010- Working Papers: Marketing

Marketing managers and scholars have focused substantial attention on the role of advertising message appeal in the persuasion process. We conducted a comprehensive quantitative and qualitative literature review of more than a thousand reports, not previously systematically reviewed, to study whether and by what size advertisements with appeals are more persuasive and better liked than ads with no structured appeals. We compared the most common appeals (fear, humor, sex, comparative, gain/loss frame, two or one sided, and metaphor) to determine their relative effectiveness. We also performed separate analyses for each response variable to assess the contribution of several moderating effects on the results. A test of heterogeneity indicated the presence of moderators on observed relationships. Moreover, we employed a cumulative meta-analysis (CMA), at every point during the history of a research domain to test for stability of results. To supplement the quantitative analyses and to analyze qualitative papers and case studies, we employed a qualitative comparative analysis (QCA) on an additional 306 qualitative reports. The meta-analysis included 703 articles containing 1631 independent samples and 2547 effect sizes representing 142,443 participants. Results show that the overall appeal effect between conditions is of small to moderate size and that profound differences exist between appeals while some moderating variables have significant effects on effect sizes in appeal studies. All methods provided the opportunity to obtain results of theoretical and practical interest. We discuss explanations for these results, suggest managerial applications, and identify directions for future research.

On election days many of us see a colorful map of the U.S. where each tiny county has a color on the continuum between red and blue. So far we have not used such data to improve the effectiveness of marketing models. In this study, we show that we should.  We demonstrate the usefulness of political data via an interesting application—the demand for movies.  Using box office data from 25 counties in the U.S. Midwest (21 quarters between 2000 and 2005) we show that by including political data one can improve out-of-sample predictions significantly. Specifically, we estimate the improvement in forecasts due to the addition of political data to be around $43 million per year for the entire U.S. theatrical market.  Furthermore, when it comes to movies we depart from previous work in another way. While previous studies have relied on pre-determined movie genres, we estimate perceived movie attributes in a latent space and formulate viewers’ tastes as ideal points. Using perceived attributes improves the out-of-sample predictions even further (by around $93 million per year). Furthermore, the latent dimensions that we identify are not only effective in improving predictions, they are also quite insightful about the nature of movies.