Comparison of Transitive Bennet and Montgomery Indicators on the Basis of Scanner Data Sets
Purpose: The main purpose of the study is to assess the practical applicability of Bennet and Montgomery indicators for analysing electronic transaction data in the form of scanner data. The specific goal is to compare transitive versions of these indicators on the basis of dynamic scanner data, where there is a high turnover of products. Design/Methodology/Approach: The model for considerations is developed based on a comprehensive review of existing literature. Authors adopt the transitive Bennet and Montgomery indicators from the field of inter-firm comparisons and use the Fox’s transformation for obtaining multilateral versions of these indicators being applicable in the scanner data case. Findings: The transitive Bennet formula leads to greater differences in values between the price and quantity indicators than the transitive Montgomery formula. This conclusion is identical for each type of data filter and for each data aggregation level. However, it can be seen that for a higher level of data aggregation (COICOP level 6), the differences between the corresponding multilateral Bennet and Montgomery indicators are much smaller than for the barcode level (GTIN level). In principle, it can be said that at a higher level of aggregation, the Bennet and Montgomery multilateral indicators lead to fairly similar values and any differences between their values are substantial at the disaggregated level. Practical Implications: The Benet and Montgomery transitive indicators can be useful in analysing scanner data if retail chain managers want to decompose sales value into a price and quantity factor. The framework provides a roadmap for practical using these multilateral indicators for dynamic scanner data sets. The adoption of the transitive indicators for the scanner data analysis can lead to substantial improvements in the management of product sales by the retail chain. Areas of potential application for the approach based on price and quantity differences could be also, for example: profit and cost change decompositions or the analysis of changes in consumer surplus. Originality/Value: The added value of the work is the identification of potential differences between the multilateral Bennet and Montgomery indicators calculated on scanner data sets obtained from retail chains. In particular, it is pioneering to determine the magnitude of these differences depending on the level of data aggregation and the type of data filters used.