Carl F. Mela

Database Paper---The IRI Marketing Data Set

This paper describes a new data set available to academic researchers at the following website: http://mktsci.pubs.informs.org . These data are comprised of store sales and consumer panel data for 30 product categories. The store sales data contain 5 years of product sales, pricing, and promotion data for all items sold in 47 U.S. markets. In two U.S. markets, the store level data are supplemented with panel-level purchase data and cover the entire population of stores. Further information is available regarding store characteristics in these markets. We address several potential applications of these data, as well as the access protocol. The data set described in this paper is maintained by IRI. Any fees charged by IRI for the distribution of the data set will be used for the continual maintenance and updating of the data. Scholarships to cover IRIs fees for those who need it are available through the INFORMS Society for Marketing Science ISMS. Please see the website above for further details.

A Dynamic Model of Sponsored Search Advertising

Sponsored search advertising is ascendant---Forrester Research reports expenditures rose 28% in 2007 to

The Long-Term Effect of Marketing Strategy on Brand Sales

8.1 billion and will continue to rise at a 26% compound annual growth rate [VanBoskirk, S. 2007. U.S. interactive marketing forecast, 2007 to 2012. Forrester Research (October 10)], approaching half the level of television advertising and making sponsored search one of the major advertising trends to affect the marketing landscape. Yet little empirical research exists to explore how the interaction of various agents (searchers, advertisers, and the search engine) in keyword markets affects consumer welfare and firm profits. The dynamic structural model we propose serves as a foundation to explore these outcomes. We fit this model to a proprietary data set provided by an anonymous search engine. These data include consumer search and clicking behavior, advertiser bidding behavior, and search engine information such as keyword pricing and website design. With respect to advertisers, we find evidence of dynamic bidding behavior. Advertiser value for clicks on their links averages about 26 cents. Given the typical

Impact of Bundle Type, Price Framing and Familiarity on Purchase Intention for the Bundle

22 retail price of the software products advertised on the considered search engine, this implies a conversion rate (sales per click) of about 1.2%, well within common estimates of 1%--2% [Narcisse, E. 2007. Magid: Casual free to pay conversion rate too low. GameDaily.com (September 20)]. With respect to consumers, we find that frequent clickers place a greater emphasis on the position of the sponsored advertising link. We further find that about 10% of consumers do 90% of the clicks. We then conduct several policy simulations to illustrate the effects of changes in search engine policy. First, we find the search engine obtains revenue gains of 1% by sharing individual-level information with advertisers and enabling them to vary their bids by consumer segment. This also improves advertiser revenue by 6% and consumer welfare by 1.6%. Second, we find that a switch from a first-to second-price auction results in truth telling (advertiser bids rise to advertiser valuations). However, the second-price auction has little impact on search engine profits. Third, consumer search tools lead to a platform revenue increase of 2.9% and an increase of consumer welfare by 3.8%. However, these tools, by reducing advertising exposures, lower advertiser profits by 2.1%.

The impact of collinearity on regression analysis: the asymmetric effect of negative and positive correlations

Few studies have considered the relative role of the integrated marketing mix (advertising, price promotion, product, and place) on the long-term performance of mature brands, instead emphasizing advertising and price promotion. Thus, little guidance is available to firms regarding the relative efficacy of their various marketing expenditures over the long run. To investigate this issue, the authors apply a multivariate dynamic linear transfer function model to five years of advertising and scanner data for 25 product categories and 70 brands in France. The findings indicate that the total (short-term plus long-term) sales elasticity is 1.37 for product and .74 for distribution. Conversely, the total elasticities for advertising and discounting are only .13 and .04, respectively. This result stands in marked contrast to the previous emphasis in the literature on price promotions and advertising. The authors further find that the long-term effects of discounting are one-third the magnitude of the short-term effects. The ratio is reversed from other aspects of the mix (in which long-term effects exceed four times the short-term effects), underscoring the strategic role of these tools in brand sales.

The Role of Spatial Demand on Outlet Location and Pricing

Bundling of products is very prevalent in the marketplace. For example, travel packages include airfare, lodging, and a rental car. Considerable economic research has focused on the change in profits and consumer surplus that ensues if bundles are offered. There is relatively little research in marketing that deals with bundling, however. In this article we concentrate on some tactical issues of bundling, such as which types of products should be bundled, what price one can charge for the bundle, and how the price of the bundle should be presented to consumers to improve purchase intent. For example, we hypothesize that bundles composed of complements of equally priced goods will result in higher purchase intention. We also hypothesize that price increases will result in larger purchase intention changes than price decreases. Further, we expect that the presentation format for describing the price of the bundle will influence purchase intention in general, and depending on the price level of the bundle, different presentation formats will result in higher purchase intention. Finally, we hypothesize that purchase intention changes associated with different price levels will be higher for subjects who are familiar with the products than for subjects who are less familiar with the products. We used an interactive computer experiment conducted among 83 Master of Business Administration (MBA) students to test our hypotheses. Our findings suggest that: (1) bundles composed of complements have a higher purchase intent than bundles of similar or unrelated products, (2) consumers are more sensitive to a bundle price increase than to a bundle price decrease of equal amounts, (3) different presentation formats for describing the price of the bundle influence purchase intention, and (4) more familiar subjects respond to different presentations of equivalent bundles in different ways than less familiar subjects. We did not find any support for the hypothesis that bundles composed of similarly priced items have higher purchase intent than bundles composed of unequally priced products.

Online Auction Demand

The purpose of this paper is to ascertain how collinearity in general, and the sign of correlations in specific, affect parameter inference, variable omission bias, and their diagnostic indices in regression. It is found that collinearity can reduce parameter variance estimates and that positive and negative correlation structures have an asymmetric effect on variable omission bias. It is also shown that the effects of collinearity are moderated by the relationship between the dependent variable and the regressors, a consideration not incorporated into most commonly used collinearity diagnostics. The formulae derived enable researchers to assess the sensitivity of regression results to the underlying correlation structure in the data.

Determining Consumers' Discount Rates with Field Studies

In this paper we consider the problem of outlet pricing and location in the context of unobserved spatial demand. Our analysis constitutes a scenario wherein capacity-constrained firms set prices conditioned on their location, demand and costs. This enables firms to develop maps of latent demand patterns across the market in which they compete. The analysis further suggests locations for additional outlets and the resulting equilibrium effect on profits and prices. Using Bayesian spatial statistics, we apply our model to seven years of data regarding apartment location and prices in Roanoke, Virginia. We find spatial covariation in demand to be material in outlet choice; the 95% spatial decay in demand extends 7.5 miles in a region measuring slightly over 9.5 miles. We further find that capacity constraints can cost complexes upwards of

Sponsored search auctions : research opportunities in marketing

193 per apartment. As predicted, price elasticities and costs are biased downward when spatial covariance in demand is ignored. Using our analysis to suggest locations for entry, we find that a proper accounting of spatial effects and capacity constraints leads to an entry recommendation that improves profitability by 66% over a model that ignores these effects.

The Periodicity of Pricing

With