The following data are replicate measurements of the sulfur dioxide concentration in each of three cities:
City I: 2, 1, 3
City II: 4, 6, 8
City III: 2, 5, 2
a. Complete the ANOVA table in the accompanying computer output for simultaneously comparing the mean sulfur dioxide concentrations in the three cities.
b. Test whether the three cities differ significantly in mean sulfur dioxide concentration levels.
c What is the estimated effect associated with each city?
d. State precisely the appropriate ANOVA fixed-effects model for these data.
e. Using dummy variables, state precisely the regression model that corresponds to the fixed-effects model in part (d). What is the relationship between the coefficients in the regression model and the effects in the ANOVA model?
f. Using the t distribution, find a 90% confidence interval for the true difference between the effects of cities I and II (making sure to use the best estimate of σ2 provided by the data).

Transcribed Image Text:

Dependent Variable: S02 Source Model Error Corrected Total DF Sum of Squares Mean Square F Value Pr> F 2 26.00000000 13.00000000 0.0553 R-Square Coeff Var Root MSE $02 Mean 3.686667 0.619048 44.53618 1.632993 Source DF city Source DF city Type I SS 26.00000000 Mean Square F Value Pr> F 2 13.00000000 4.88 0.0553 Type IlI SS Mean Square F Value Pr> F 2 26.00000000 13.00000000 4.88 0.0553