In Section 8.6.1 we estimated the linear probability model COKE b1 b2PRATIO b3DISP COKE b3DISP PEPSI e where COKE

In Section 8.6.1 we estimated the linear probability model COKE ¼ b1 þ b2PRATIO þ b3DISP COKE þ b3DISP PEPSI þ e where COKE ¼ 1 if a shopper purchased Coke and COKE ¼ 0 if a shopper purchased Pepsi. The variable PRATIO was the relative price ratio of Coke to Pepsi, and DISP_COKE and DISP_PEPSI were indicator variables equal to one if the relevant display was present. Suppose now that we have 1140 observations on randomly selected shoppers from 50 different grocery stores. Each grocery store has its own settings for PRATIO, DISP_COKE and DISP_PEPSI. Let an

(i, j) subscript denote the jth shopper at the ith store, so that we can write the model as COKEij ¼ b1 þ b2PRATIOi þ b3DISP COKEi þ b3DISP PEPSIi þ eij Average this equation over all shoppers in the ith store so that we have COKEi ¼ b1 þ b2PRATIOi þ b3DISP COKEi þ b3DISP PEPSIi þ ei (8.52)