Store Sales and Panel Purchase Data : Are They Compatible ?

The authors examine the compatibility of price elasticity estimates obtained from store sales and panel purchase data. If the store and panel models are not comparable, comparison of the estimates could be confounded since differences could arise due to data and/or model related effects. To overcome this confound, analytically equivalent models are specified for store and panel data. This ensures that the differences in the estimates can be attributed purely to the use of different types of data. A statistical procedure, which takes into account both estimation and sampling error, is developed to formally test for the differences in the store and panel estimates. The approach is implemented on scanner databases from three categories of packaged goods. A key finding is that on average, data differences result in panel data producing price elasticities estimates that are about 31% higher (more negative) than store data. Formal statistical tests confirm that the purchase behavior of panelists is not representative of the population at store level. Finally, the authors discuss how users of scanner data can use the methodology to benchmark datasets.

[1]  Gary J. Russell,et al.  A Probabilistic Choice Model for Market Segmentation and Elasticity Structure , 1989 .

[2]  Rajendra K. Srivastava,et al.  Inferring Market Structure with Aggregate Data: A Latent Segment Logit Approach , 1993 .

[3]  G. Schwarz.  Estimating the Dimension of a Model , 1978 .

[4]  Robert C. Blattberg,et al.  Sales Promotion: Concepts, Methods, and Strategies , 1990 .

[5]  Dipak C. Jain,et al.  A Random-Coefficients Logit Brand-Choice Model Applied to Panel Data , 1994 .

[6]  Lee G. Cooper,et al.  Market-Share Analysis , 1988 .

[7]  Naufel J. Vilcassim,et al.  Investigating Household Purchase Timing Decisions: A Conditional Hazard Function Approach , 1991 .

[8]  J. Louviere,et al.  The Role of the Scale Parameter in the Estimation and Comparison of Multinomial Logit Models , 1993 .

[9]  Sunil Gupta,et al.  Brand Choice, Purchase Incidence, and Segmentation: An Integrated Modeling Approach , 1992 .

[10]  Robert C. Blattberg,et al.  Shrinkage Estimation of Price and Promotional Elasticities: Seemingly Unrelated Equations , 1991 .

[11]  G. Tellis.  The Price Elasticity of Selective Demand: A Meta-Analysis of Econometric Models of Sales , 1988 .

[12]  Peter E. Rossi,et al.  Purchase frequency, sample selection, and price sensitivity: The heavy-user bias , 1994 .

[13]  V. Srinivasan,et al.  A Simultaneous Approach to Market Segmentation and Market Structuring , 1987 .

[14]  D. G. Morrison,et al.  A Note on Panel Bias , 1966 .

[15]  R. Ferber.  Observations on a Consumer Panel Operation * , 1953 .

[16]  Gary Chamberlain,et al.  Analysis of Covariance with Qualitative Data , 1979 .

[17]  Ruth N. Bolton.  The Relationship Between Market Characteristics and Promotional Price Elasticities , 1989 .

[18]  Russell S. Winer,et al.  Attrition Bias in Econometric Models Estimated with Panel Data , 1983 .