Purpose – Little research on the influence of external factors, such as weather and holiday periods, on retail sales is available with regards to the alcoholic beverages industry. This study investigates how weekly retail sales of alcoholic beverages vary in association with daily maximum temperatures and annual federal holidays across US counties in the years 2013 to 2015.
Design/Methodology/Approach – Secondary data of weekly retail sales (volume) of alcoholic beverages from stores in 651 counties in the US are analysed. The data covers on average 21% of all existing US counties and 12% of the total US off-trade retail sales of alcoholic beverages in the period studied (Euromonitor 2017). Data of federal holidays and meteorological data are collated for each county in the sample. Seasonal autoregressive integrated moving average models with exogenous regressors (SARIMAX) are applied for the time series to investigate possible relationships and effects.
Findings – The results indicate that off-trade retail sales of beer, liquor, red and white wine are temperature sensitive overall throughout the year, while rosé, sparkling and other wine are not. Sales sensitivities to temperature also differ by geographies. In the warmest regions liquor and white wine sales do not respond to temperature changes. Public holidays represent a constant influencing factor on sales increases for all categories investigated.
Keywords – retail, alcoholic beverages, temperature, holidays, time-series, SARIMAX
Hirche, M., Haensch, J. and Lockshin, L.(2017). "Hot weather – cool drinks: Is day temperature associated with retail sales of alcoholic beverages?" Academy of Wine Business Research.
The entertainment industry relies heavily on advertising to attract audiences. This article demonstrates a method to measure the effect of on-air television promotions, or promos, on viewing behaviour, based on a well-established single-source method for determining the causal impact of advertising on sales. We illustrate this method on 18 new prime-time programmes, showing that promos have a positive impact on viewing behaviour. Exposed viewers are substantially more likely to view the premiere episode of a new series, across a wide range of different television-viewing weights, frequency of promo exposures and programme types. The research also shows evidence of reach- based scheduling strategies being generally more efficacious than frequency-based strategies. These findings provide guidance to help networks implement their promo strategy more effectively, as well as a method for future research into the effectiveness of television promos as this approach can be utilised in any country with a television ratings panel.
Keywords: television, programme promos, advertising effectiveness, single-source data, scheduling
Beal, V., Romaniuk, J., and Sharp, B. (2017). Television advertising television: measuring the ability of television promos to deliver ratings for new programmes using single-source data. Adelaide, South Australia, Ehrenberg Bass Institute for Marketing Science: 1-32.
Celebrity endorsers can be devices to improve the cut-through and branding of advertising. This research examines the contribution of two factors, celebrity awareness (ability to name the celebrity) and general celebrity interest, in the linkage of a celebrity with an endorsed brand. Testing of endorsements across 16 celebrities from the fields of movies, television, music and sports finds that name awareness of a celebrity is consistently significantly related to brand linkage, while having a general interest in celebrities is not. This suggests caution when choosing lesser-known celebrities as part of an endorsement strategy.
Romaniuk, J., Nguyen, C., and Simmonds, L. (2017). "The effectiveness of celebrities as a branding device." European Marketing Academy Conference.
Entertainment is one pathway to effective advertising, but what is more or less entertaining to mass audiences is an under researched area. This study took a novel approach to the issue by exploring the experiences of performing artists. Our intent was to identify possible implications for advertising creative development. In-depth interviews were conducted with professional performers (comedians, actors and singers) to uncover performance elements that they found consistently elicited desirable reactions from audiences. We found that performers rarely followed a clearly structured process when planning for a performance, but most believed that using emotions is the most important way to increase the likelihood of success. Few specific performance elements were consistently considered more or less effective (e.g. shared experiences, pace, narrative structures). The lack of converging ideas or detailed examples mean that the findings offer limited tactical guidance for marketers.
Hartnett, N., Gelzinis, A., Nenycz-Thiel, M., Kennedy, K. (2017). "Making Advertising Entertaining: Insights from Performing Artists." European Marketing Academy Conference.
This study demonstrates the potential of certain neurological measures—in particular, biometrics— to identify television advertisements that successfully lead to sales. The researchers, who represent academia and industry, used direct measures of what they believe matters most to marketers: in-market sales response (from single-source data). To the authors’ knowledge, the dataset is the largest ever studied: more than 100 consumer packaged-goods advertisements for 20 Mars, Inc., brands, combined with laboratory testing from more than 1,000 respondents. The goal of the research, funded by Mars, was to identify evidence-based measures to inspire improved advertising practice and to explore the factors behind advertising effectiveness.
Bellman, S., Nenycz-Thiel, M., Kennedy, R., Larguinat, L., McColl, B. and Varan, D., 2016. What Makes a Television Commercial Sell? Using Biometrics to Identify Successful Ads. Journal of Advertising Research, pp.JAR-2016.
CFO: “But what if we invest in training these sales and marketing people and then they leave?”
CMO: “What if we don’t invest in them and they stay?”
Sharp, Byron (2014), “The CMO's Legacy,” in Admap. online: Warc.
Can science help brands grow? Mars, Inc. has embarked on a program to apply the marketing laws originally developed and promoted by Andrew Ehrenberg. Mars has discovered that both creativity and science can—and should—work together. Just as an architect marries creativity with the laws of physics; marketers should construct brand plans that embrace the laws of growth. Mars executives are learning that creativity is more productive when unleashed within known boundaries of buyer behavior. The authors share some lessons from a continuing journey that may help others also make the transformation to a marketing science culture.
Kennedy, R. and B. McColl (2012). "Brand growth at Mars, Inc.: How the global marketer embraced Ehrenberg’s science with creativity." Journal of Advertising Research 52(2): 270-276.
Bogomolova, Svetlana and Christopher Villani (2010), “Brand Trust Demystified,” Direct Magazine.
DIRICHLET is an Excel-based program for fitting the Dirichlet model to data recording individual purchases of a number of entities, usually brands, in a particular product category. It was written by Zane Kearns (Kearns 2002). The purpose of this Guide is to supplement the instructions given in the program itself, which explain how to enter data and fit the model. Some theoretical points are discussed in the Notes at the end. A comprehensive theoretical background is given in the book ‘Repeat Buying’ by Professor A.S.C. Ehrenberg.
Bound, John (2009), “User's Guide to Dirichlet,” Marketing Bulletin, 20.
Brand trust is considered a key aspect of brand relationships, brand personality and brand equity. This paper is an empirical examination of trust scores’ variation across 110 brands in 13 markets, ranging from fast moving consumer goods
to durables and services. The authors find that generally there is little variation in the trust scores for competing brands that cannot be explained by usage biases in perceptual responses.1,2 This lack of variation means that deviations could be detected easily, with ten brands (9 per cent) having substantial higher or lower levels of trust. The cases of lower than average trust levels appear to be linked to widespread negative publicity. In contrast it was difficult to see a pattern in the brands with higher than average trust levels. The analysis conducted does demonstrate, however, that by controlling for usage biases, it is possible to evaluate all brands on an equal basis to create benchmarks and to more clearly see deviations. On a cautionary note this research supports suggestions from other authors such as Ehrenberg, Barnard and Scriven3 that differences in the perceptions between brands that are simply a reflection of the current size of the brand’s user base should not be overplayed.
Romaniuk, Jenni and Svetlana Bogomolova (2005), “Variation in Brand Trust Scores,” Journal of Targeting, Measurement and Analysis for Marketing, 13 (4), 363-73.
Can’t find what you are looking for? or have some feedback about the site? Contact Us
Now available as an eBook exclusively to Apple iBooks
The Ehrenberg-Bass Institute for Marketing Science is the world’s largest centre for research into marketing. Our team of market research experts can help you grow your brand and develop a culture of evidence-based marketing.
Ehrenberg-Bass Institute acknowledges the Traditional Owners of the lands across Australia as the continuing custodians of Country and Culture. We pay our respect to First Nations people and their Elders, past and present.
