The data in the table below are sales, y, in thousands of dollars per week, for home improvement outlets in each of four cities. The objective is to model sales, y, as a function of traffic flow, adjusting for city-to-city variations that might be due to size or other market conditions. The model is

E(y) = β_o + β₁x₁ + β₂x₂ + β₃x₃ + β₄x₄

where

A SAS printout for the regression analysis is provided below.

a. Is the model statistically useful for predicting y? Explain.

b. Do you detect any outliers?

c. Refer to part b. Are the outliers detected in the residual plot influential?

d. Note that the value of sales (y) for the 13th observation was incorrectly entered into the computer as 82.0; the correct value is 8.2. Make the correction and rerun the regression analysis. Interpret the results.

Transcribed Image Text:

Si if city 1 l0 if other Si if city 2 X2 = lo if other Si if city 3 X3 = 10 if other X4 = traffic flow