Exercise 42 analyzes whether weekly earnings are related to employment opportunities in Canada. Other factors that might impact people’s weekly earnings are their number of years of education (ED) and their number of years of work experience (EX). To investigate how important these factors are, Statistics Canada added them to its multivariate regression given in Exercise 42. Preliminary data analysis had shown a nonlinear relationship between weekly earnings and years of experience, which analysts took into account with a term in EX². The resulting multivariate regression analysis is

The P-values associated with the intercept and the five coefficients in the above equation are ,0.001, ,0.001, 0.140, ,0.001, ,0.001, and ,0.001. The F-ratio has a P-value ,0.001.

a) Is the regression model significant overall?

b) Which variable(s) is (are) significantly linearly related to weekly earnings at the 95% level?

c) Does this regression show that employment in the same location is related to weekly earnings at the 95% level? What form does this relation take, linear or other (specify)?

d) Statistics Canada states, “The advantage of cities lies as much in their capacity to educate, attract and retain highly educated workers, as in their innate ability to facilitate the interaction of workers and firms.” Which parts of the regression results lead to this conclusion?

e) What other factors might contribute to weekly earnings other than those in this regression equation?

Transcribed Image Text:

In(w) = 4.322 + 0.023 × In(EL) + 0.007 x In(ELI) + 0.055 x EX – 0.001 x EX? 0.055 +0.078 × ED.