Estimating Irregular Pricing Effects: A Stochastic Spline Regression Approach

Kalyanam, Kirthi; Shively, Thomas S.

doi:10.2307/3151927

Cited by 78 publications

(68 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another stream of work attempts to determine price thresholds from store-level data (or aggregations across stores). A promising approach was recently proposed by Kalyanam and Shively (1998), who use Bayesian methods (specifically Gibbs sampling) in combination with spline regression to estimate irregular price response functions on aggregate-level data. Nevertheless, the estimation problem is challenging in part because each consumer (and therefore each store) may have different zones of price insensitivity.…”

Section: Price Thresholds and Gapsmentioning

confidence: 99%

Commercial Use of UPC Scanner Data: Industry and Academic Perspectives

1999

View full text Add to dashboard Cite

The authors report the findings from an exploratory investigation of the use of UPC scanner data in the consumer packaged goods industry in the U.S. The study examines the practitioner community's view of the use of scanner data and compares these views with academic research. Forty-one executives from ten data suppliers, packaged goods manufacturers, and consulting firms participated in wide-ranging, inperson, interviews conducted by the authors. The interviews sought to uncover key questions practitioners would like to answer with scanner data, how scanner data is applied to these questions, and the industry's perspective regarding the success that the use of scanner data has had in each area.The authors then compare and contrast practitioners' views regarding the resolution of each issue with academic research. This produces a 2 ‫ן‬ 2 classification of each question as "resolved" or "unresolved" from the perspectives of industry and academia. Along the diagonal of the 2 ‫ן‬ 2, issues viewed as unresolved by both groups are important topics for future research. Issues deemed resolved by both groups are, correspondingly, of lower priority. In the offdiagonal cells, industry and academics disagree. These topics should be given priority for discussion, information exchange, and possible further research.Practitioners reported that scanner data analysis has had the most success and been most widely adopted for decision making in consumer promotions (i.e., coupons), trade promotions, and pricing. For example, logit and regression models applied to scanner data have revealed very low average consumer response to coupons which has directly led to reduced couponing activity. Managers also reported high levels of comfort with and impact from analyses of trade promotions and price elasticities. While industry views most of the issues in these areas to be resolved, academic research raises concerns about a number of practices in common commercial use. These include price threshold analysis and trade promotion evaluation using baseline and incremental sales.In product strategy, advertising, and distribution management, practitioners reported that the use of scanner data has had more limited development, success, and impact. In the case of new product decisions, scanner data use has been slow to develop due to the inherent limitations of historical data for these decisions and a heavy reliance on traditional primary research methods. In advertising, scanner data is widely analyzed with models, but confusion among practitioners is very high due to controversies about methods (e.g., what level of data aggregation is best) and conflicting results. In distribution and retail management, scanner data use has tremendous potential but a mixed track record to date. Thus, practitioners view the use of scanner data as unresolved for most issues in product strategy, advertising, and distribution. This view is largely, though not entirely, consistent with academic research, which has only begun to address many of the key quest...

show abstract

Section: Price Thresholds and Gapsmentioning

confidence: 99%

Commercial Use of UPC Scanner Data: Industry and Academic Perspectives

1999

View full text Add to dashboard Cite

show abstract

“…The 00-ending price is used for high-priced, high-quality, or upscale organisations; whereas 95-ending price is used for mid-priced or average quality organisations; and 99-ending price tends to be used extensively for low-priced, low-end organisations or organisations promoting a high-value image. Kalyanam and Shively (1998) and Schindler and Kibarian (1996) suggest that customers are sensitive to small differences in price; such that a penny reduction reflected in a nine-ending decreases the perception of a price, often, leading to a considerable augment in sales. Manning and Sprott (2009) found that, the extant study has paid significant attention to the impact of nine-ending prices on purchase decisions and a few studies have examined its usefulness in conjunction with other critical components of an advertisement.…”

Section: Literature Reviewmentioning

confidence: 99%

The impact of psychological pricing strategy on consumers' buying behaviour: a qualitative study

Kumar

Pandey

2017

IJBSR

View full text Add to dashboard Cite

Abstract:The recognition of consumers' behaviour is crucial for effective marketing plans. Evidences explain that the psychological pricing communicates meaning to consumers. This study theoretically examines the impact of psychological pricing on consumers' buying behaviour. The study has used secondary data from research papers, monographs, theses, popular articles, and newspapers. Findings show that socio demographic factors like age, income, education, gender, lifestyle, family size, reference groups, social roles and status and the psychological patterns like representativeness, availability of products and the anchoring heuristics are key factors which influence consumers' buying behaviour. Additionally, the consumers, who are more price cognisant are more probable to select nine-ending prices. Indeed, low involved customers, those with a small hedonic and symbolic attachment profile, low educated, low income and younger customers are prone to select the nine-ending priced products and services. The findings can have implications for retailers, pricing managers, researchers, academicians, society and government.

show abstract

“…Since cross-item price effects are usually much lower in magnitude than own-item price effects (e.g., Hanssens et al (2001)), and frequently not all competing brands in a product category are close substitutes to each other (e.g., Foekens (1995)), a stepwise selection to reduce the number of predictors in a sales response model seems very promising. Many previous approaches to analyze sales response to promotional activities have tackled this problem by imposing restrictions on the competitive market structure, e.g., by capturing competitive promotional effects in a highly parsimonious way through the use of a single competitive variable (e.g., Blattberg and George (1991), Kopalle et al (1999)) or by focusing only on a limited number of major brands in a product category (e.g., Kalyanam andShively (1998), van Heerde et al (2001)). The paper is organized as follows: in section 2, we propose the semiparametric model to estimate promotional effects and provide details about the P-splines approach we use to model the unknown smooth functions for ownand cross-promotional price effects; in section 3, we introduce the stepwise routine which includes a simultaneous smoothing parameter selection for the continuous price variables; in section 4, we illustrate the new methodology in an empirical application using weekly store-level scanner data for coffee brands; section 5 summarizes the contents of the paper.…”

Section: Introductionmentioning

confidence: 99%

“…A recent empirical comparison of parametric and seminonparametric sales response models (the latter specified as multilayer perceptrons) conducted by Hruschka (2004) also provides superior results for the more flexible neural net approach. We follow Kalyanam and Shively (1998) and van Heerde et al (2001) and propose a semiparametric model based on penalized B-splines to estimate sales promotion effects flexibly. We add to the body of knowledge by suggesting a stepwise regression procedure with simultaneous smoothing parameter choice for variable selection.…”

Section: Introductionmentioning

confidence: 99%

“…Kalyanam and Shively (1998) and van Heerde et al (2001) have proposed semiparametric models to estimate the influence of price promotions on brand sales, and both obtained superior performance for their models compared to strictly parametric modeling. Following these researchers, we suggest another semiparametric framework which is based on penalized B-splines to analyze sales promotion effects flexibly.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Semiparametric Stepwise Regression to Estimate Sales Promotion Effects

Steiner

Belitz²,

Lang

From Data and Information Analysis to Knowledge Engineering

View full text Add to dashboard Cite

Abstract. Kalyanam and Shively (1998) and van Heerde et al. (2001) have proposed semiparametric models to estimate the influence of price promotions on brand sales, and both obtained superior performance for their models compared to strictly parametric modeling. Following these researchers, we suggest another semiparametric framework which is based on penalized B-splines to analyze sales promotion effects flexibly. Unlike these researchers, we introduce a stepwise procedure with simultaneous smoothing parameter choice for variable selection. Applying this stepwise routine enables us to deal with product categories with many competitive items without imposing restrictions on the competitive market structure in advance. We illustrate the new methodology in an empirical application using weekly store-level scanner data.

show abstract

Estimating Irregular Pricing Effects: A Stochastic Spline Regression Approach

Cited by 78 publications

References 15 publications

Commercial Use of UPC Scanner Data: Industry and Academic Perspectives

Commercial Use of UPC Scanner Data: Industry and Academic Perspectives

The impact of psychological pricing strategy on consumers' buying behaviour: a qualitative study

Semiparametric Stepwise Regression to Estimate Sales Promotion Effects

Contact Info

Product

Resources

About