Past studies based upon scanning data have often reported nonsignificant coefficients of the dummy variables which were included in a store-level regression model. This study suggests to "pool" the regression models across stores and it shows the relationship between the store-level estimators and the "pooled" estimator. Link to the article
BEMMAOR, A.C., FRANSES, P.H. and KIPPERS, J. (1999). Estimating the Impact of Displays and Other Merchandising Support on Retail Brand Sales: Partial Pooling with Examples. Marketing Letters, 10(1), pp. 87-100.