Effects of advertising on sales

Effects of Advertising on Sales: A Methodological Critique

There is a reliable relationship between advertising and sales, but one in which sales lead advertising rather than vice versa Hsu, Darrat and Zhong (2002). This review focuses on a limited number of articles following Hsu, Darrat and Zhong from major journals in advertising and marketings thant focus on advertising and sales relationship Danaher, Bomefrer and Dhar, 2008; Esteve and Requena, 2006; Frank, Bruce and Majumdar, 2007; Kim, 2005; Leache and Reekie, 1996; Newstead, Taylor and Kennedy, 2009; Taylor, Kennedy and Sharp, 2009; Yoo and Mandhachitra, 2003; Zhou, Zhou and Ouyang, 2003. The first fragment of the paper discuss about the methodological oreintation and in the second portion it focuses on the argument whether there is any effect of advertising on sales.

Methodological Orientaions

Hsu, Darrat and Zhong (2002) tried to empirically examine the Gallbaraithian Hypothesis that advertising aggregate demand to the changing industrial development and consequently stimulates sales. (2002, p.175). To do so, they have chosen three aggregate variables wrapping from period of 1948 to 1995. The variables they selected are aggregate advertising expenditures (A) obtained from the Direct Marketing Association’s Statistical Fact Book; aggregate sales (S) measured by personal consumption expenditures and obtained from the S&P/DRI Database; and personal disposable income (I) culled from various issues of the Statistical Abstracts of the United States (2002, p.178). They have tested two competing hypothesis simultaneously using three variable vector autoregressive modeling procedure, which indicates that they have gone through a deductive approach of study.  Their methodology indicates that it is an empirical, quantitative and positivist study.

Newstead, Taylor,  Kennedy and Sharp (2009) together brings out the knowledge through two different approaches that if advertising is to be slaes effective in the liong trm, it must firs work in short term and advertising typically as a half-life of three to four weeks. The two approaches they used are aggregate-level analysis from experimental split cable test marketing environments and individual-level (2009, p.207). Single-Source pannel date for 40 years have been collected and analysed. For individual-level analysis. Their approachess indicates that they were more into qualitative and interpretivist approach.

Esteve and Requena (2006) tires to examine the relationship between advertising and sales across the market segments of the UK car industry over the period of 1971-2001 (total of 31 observations). The tired to figure out whether there is long-run stable equilibrium relaionship or not. The relationship between advertising and sales were both expressed in logarithms, using cointegration techniques (2006, p.114) Despite the relative small sample size, they used the Dynamic Ordinary Least Squares (DOLS) methods from stock and watson (1993) and following the methodology proposed by Shin (1994) (2006, p.118). They have also used the Model with Multiple structural Breaks to check whether the long-run advertising sales link is stable over time, proposed by Bai and Perron (1998, 2003a, 2003b). Few hypothesis were also st regarding the advertisment sales relationship which indicates that it is ia deductive approach and the methodlogy of the article suggested that it is a quantitative n positivist mode of study.

Kim (2005)  investigate the advertising-sales relationship in the annual Lydia Pinkham data . Here the botstrap method is used as an alternative to the asympthotic method exclusively adopted by past studies. The orthogonalized impulse response analysis based on bivariate auto-regressive (AR) model is conducted (2005, p.348). Sample size of only 54 was  set  and the bootstrap method of Efron and Tibshirani (1993) was choosen. The articles doesn’t discuss a proper methodolocial system which they have used, rather it is moreinto data details and estimation results. It is a quantitative and positivist aproach of study. Overall, this paper finds evidence of one-way causalty from advertising to sales.

Zhou, Zhou and Ouyang (2005) further study the effect of short-term advertising on long-term sales of consumer durable and nondurables in China by cross-sectional times-series television advertising and sales data. This model is not only directional but also measures the quantitative magnitude of the persistence effect of specific variable (2005, p.47). Sales Data of 45 months from the retail stores were coverd.  Advertising data included television advertising expenditures covering all of the television channels in Shanghai (2005, p.48). This articles clearly outline the methodolgy and it is a quantitative positivist approach.

(Bryman & Bell, 2007)Yoo and Mandhachitra (2003) analysed the effects in a competitive setting. The longitudinal data on Scotch Whisky brands in thiland were choosen. The sample size was 90 and it was collected over a period of 7 hours 6 months. Sales data were obtained from the Excise Department of Thailand based on liquor taxes, and the monthly advertising spending data in print and broadcast media came from the AC Nielsen Media Monitoring Service and the Media Data Resources Inc. (2003, p.313) The SAS package was then used for analysis, and no serious multicollinearity was detected in the regression models. From the methodological system it is a quantitative positivist approach of study.              

Leach and Reekie (1996) experimented on the relationship between sales and advertisement with petrol on the market share of brand . Market share of SASOL brand ws collected from their advertising agency  for eight years. The expenditure on advertising was collected from different conventional source of market research (1996, p.1082). with the hypothesis set before; advertising effect on sales; this indicates that it is a detuctive study and positivist quantitative study. Due to insufficient sales information there is a weakness in the study, though the article claims that it is not a such a deficiency.

 Danaher, Bonfrer and Dhar (2008) further analysis the relationship of advertisiment and sales and took it into the next level by  including competitive advertising in their study. They have collected sales information from more than 80 grocery stores in a large marketi, in which information is collected by in-store scanner (2008, p.213). Danaher, bonfrer and Dhar specifically examine two categories; liquid laundry detergent and raisin bran cereals. This is because these items are considerd as the top most household product. Sales data from grocerry shops, advertising data from Arbitron’s spot television commercial monitoring service and Broadcast Advertising Reports are taken(2008, p.217). For this study the research only considerd the Television adverisement data, which might lead to missconception because there are also other forms of media available for advertisement.  It is more into equation and statistical analysis which leads to quantitative research.

Advertising Effect on Sales

Hsu, Darrat and Zhong (2002) re-examine the Galbraithian hypothesis that advertising increases with disposible income and promotes sales, but the result for USA reject the Galbraithian hypothesis.  But unlike Chowdhury’s bivrate results, their broader model suggest that there is a reliable relationship between advertising and sales. They also states that consumers view advertising as the company’s way to conver confidence in their product. (2002, p.188). Whereas Newstead, Taylor,  Kennedy and Sharp found that advertisements work immediately and the strength of the effect verymuch influence the toal sales effect.  They also found an interesting point thet advertising exposure typically has a half life of three to four weeks (2009, p.210). Zhou, Zhou and Ouyang, concluded that longterm advertising have impacts on sales of consumer durable and nondurables. Yoo and Mandhachitra (2003) and Danaher, Bonfrer and Dhar (2008) both took it frther to competitive advertisment. Although advertisers have probably suspected that high levels of competitive interference reduce the effect of advertising on sales, until now, the magnitude of the reduction has not been quantified (2008, p. 222) their findings make contribution to three new areas of methodological, substantive and advertising practice. Esteve and Requena, (2006) observed substantial shift in the estimated coefficients of the long-run elasticity. In the last period, there was a notable rise in the long-run elasticity of advertising on sales. Leach and Reekie (1996) stated that sales are determined by past as well as current advertising expenditures, but that the cumulative effects of advertising lasts for months rather than years.

Conclusion

From most of the article it has been seen that they are positivistic, and quantitative research. It may be because to find out the relationship between Advertisement and sales, it requires statistical analysis. More or less every of the article concludes that advertising has effect on sales. Very few researches have been conducted regarding this area, which leaves opportunity for the potential researcher in this field. One of the other limitations of the study is the availability of data. It is hard to get the data based on the product category, and it is also that there are many types of advertisements available. Thus which advertisements actually affect the sales of the product is a question to be asked. As Hsu, Darrat and Zhong (2002, p.188) stated that from a broader model consistently suggest that there is a reliable relationship between advertising and sales, but one in which sales lead advertising rather than vice versa.

• Reference

  Bryman, A., & Bell, E. (2007). Business Research Methods (Vol. 2). Oxford University Press.

  DANAHER, P. J., BONFRER, A., & DHAR, S. (2008). The Effect of Competitive Advertising Interference on Sales for Packaged Goods. Journal of Marketing Research , XLV, 211-225.

  Esteve, V., & Requena, F. (2006). A Cointegration Analysis of Car Advertising and Sales Data in the Presence of Structural Change. Int. J. of the Economics of Business , 13 (1), 111-128.

  Hsu, M. K., Darrat, A. F., Zhong, M., & Abosedra, S. S. (2002). Does advertising stimulate sales or mainly deliver signals? A multivariate analysis. International Journal of Advertising , 175-195.

  Kim, H. J. (2005). Investigating the advertising-sales relationship in the Lydia Pinkham data: a bootstrap approach. Applied Economics (37), 347-354.

  LEACH, D. F., & REEKIE, W. D. (1996). A natural experiment of the e¤ ect of advertising on sales: the SASOL case. Applied Economics (28), 1081-1091.

  Newstead, K., Taylor, J., Kennedy, R., & Sharp, B. (2009, June ). The Total Long-Term Sales Effects of Advertising: Lessons from Single Source. Journal of Advertising Research , 207-210.

  Yoo, B., & Mandhachitra, R. (2003, September). Estimating Advertising Effects on Sales in a Competitive Setting. Journal of Advertising Research , 310-320.

  Zhou, N., Zhou, D., & Ouyang, M. (2003). LONG-TERM EFFECTS OF TELEVISION ADVERTISING ON SALES OF CONSUMER DURABLES AND NONDURABLES. Journal of Advertising , 52 (2), 45-54.

7