Introductory Econometrics: A Modern Approach 6th Edition by Jeffrey M Wooldridge

Exercise 6

In Example 10.6, we estimated a variant on Fair's model for predicting presidential election outcomes in the United States.

(i) What argument can be made for the error term in this equation being serially uncorrelated? (Hint: How often do presidential elections take place?)

(ii) When the OLS residuals from (10.23) are regressed on the lagged residuals, we obtain = - 068 and se() = .240. What do you conclude about serial correlation in the ut?

(iii) Does the small sample size in this application worry you in testing for serial correlation?

Step 1 of 3

(i)

The U.S. presidential election occurs once in four years and it is expected that the election process may include the effect of any unobserved shocks of the economy. This unexpected shock can be denoted by the error term. The effect of the external unexpected shock should impact on the current year’s election, and the impact should not extent for the next term’s election. Hence, one can say that the {} is serially uncorrelated.