Modern theories of sales make conflicting predictions about the temporal pattern of sales, which we test using retail chain level data. In this paper, we focus on the retail sale patterns of two retail milk prices in a New Member State (NMS), Hungary using weekly data across eight retail chain between 2005 January and 2008 June. We employ a battery of empirical tests, to try a number of sale theory hypotheses. First, we present summary statistics, histograms, and correlations of prices and sales from which we conclude that no theory of sales fully describes sale patterns and price distributions. Second, we apply vector autoregressive analysis and Granger tests of temporal ordering (”causality tests”) to determine whether the sale of one retail chain is followed in a predictable way by the sale of another retail chain or its own later sales. Our results suggest a dual retail market structure. Finally, we employ panel cointegration to test confirm that durable goods should have qualitatively different pricing pattern than less-durable goods. Similarly to Berck et al. (2007) we fail to see a clear difference between storable milk and boxed milk patterns.


Downloads Statistics

Download Full History