A Practitioner's Guide to Estimation of Random-Coefficients Logit Models of Demand

Estimation of demand is at the heart of many recent studies that examine questions of market power, mergers, innovation, and valuation of new brands in differentiated-products markets. This paper focuses on one of the main methods for estimating demand for differentiated products: random-coefficients logit models. The paper carefully discusses the latest innovations in these methods with the hope of increasing the understanding, and therefore the trust among researchers who have never used them, and reducing the difficulty of their use, thereby aiding in realizing their full potential.     

Sales and consumer inventory

Temporary price reductions (sales) are common for many goods and naturally result in a large increase in the quantity sold. We explore whether the data support the hypothesis that these increases are, at least partly, due to demand anticipation: at low prices, consumers store for future consumption. This effect, if present, has broad economic implications. We test the predictions of an inventory model using scanner data with two years of household purchases. The results are consistent with an inventory model and suggest that static demand estimates may overestimate price sensitivity.     

The Post-Promotion Dip Puzzle: What do the Data Have to Say?

One of the puzzles of store-level scanner data is the lack of a dip in quantity sold in the weeks following a promotion. Such a dip is predicted by a consumer inventory model. During a promotion consumers buy more, not only for current consumption, but stockpile for future consumption. The predictions of such a model have been confirmed by household-level data yet seem harder to find in aggregate brand- or category-level data. We re-examine this puzzle and reach two conclusions. First, the effects at the household-level are present, but are much smaller than previously found. Our estimates are different because we control for household heterogeneity in a more general way than most previous work. This suggests that since the effects are small they might be harder to spot in aggregate data. Second, we show that the dip is present in the aggregate data, once we control for additional promotional activity, like feature and display. The latter has an opposing dynamic effect that masks the existence of the post-promotion dip.     

The Year in Review: Economics at the Antitrust Division 2013–2014

During 2013–2014, the Antitrust Division of the U.S. Department of Justice brought a wide range of matters to successful conclusions. The three matters that are discussed below demonstrate the diverse set of issues that the division examines every year.     

THE ELASTICITY OF SUBSTITUTION BETWEEN TIME AND MARKET GOODS: EVIDENCE FROM THE GREAT RECESSION

We document a change in household shopping behavior during the Great Recession. Households purchased more on sale, larger sizes, and generic products and increased coupon usage and shopping at discount stores. We estimate a decline in returns to shopping during the recession. Therefore, the increase in shopping behavior implies a significant decrease in households' opportunity cost of time. Using the estimated cost of time and time use data, we estimate a high elasticity of substitution between market expenditure and time spent on nonmarket work. We find that households smooth a sizable fraction of consumption by varying their time allocation during recessions.     

The Year in Review: Economics at the Antitrust Division 2012–2013

During 2012–2013, the Antitrust Division brought a wide range of litigated matters to successful conclusions. Litigation puts the economic analysis of an antitrust investigation to the ultimate test, and the Division continues to rely on its first-rate economic staff to help explain a wide range of matters to the courts. The four cases discussed below demonstrate the diverse set of issues the Division examines every year.     

Recording discrepancies in Nielsen Homescan data: Are they present and do they matter?

We report results from a validation study of the Nielsen Homescan consumer panel data. We use data from a large grocery retailer to match transactions that were recorded by the retailer (at the store) and by the Homescan panelist (at home). The matched data allow us to identify and document discrepancies between the two data sets in reported shopping trips, products, prices, and quantities. We find that the discrepancies are largest for the price variable, and show that they are due to two effects: the first seems like standard recording errors (by Nielsen or the panelists), while the second is likely due to the way Nielsen imputes prices. We present two simple applications to illustrate the impact of recording differences, and we use one of the applications to illustrate how the validation study can be used to adjust estimates obtained from Nielsen Homescan data. The results suggest that while recording discrepancies are clearly present and potentially impact results, corrections, like the one we employ, can be adopted by users of Homescan to investigate the robustness of their results to such potential recording differences.     

Too smart for their own good? A study of perceived cognitive overqualification in the workforce

This study examined the concept of cognitive overqualification, the possession of a higher level of cognitive ability than is required for a given job. Among 156 US based customer service representatives, cognitive overqualification was found to be associated with job dissatisfaction, but was only weakly related to measures of job and training performance. The results of this study provide support for the common practice among personnel managers to reject overqualified job applicants, as these individuals may be more likely to develop negative job attitudes, although not necessarily in anticipation of their poorer job performance.