T. C. Chiang considered several time series forecasting models of future foreign exchange rates for U.S. currency (The Journal of Financial Research, Summer 1986). One popular theory among financial analysts is that the forward (90-day) exchange rate is a useful predictor of the future spot exchange rate. Using monthly data on exchange rates for the British pound for n = 81 months, Chiang fit the model E(Yt) = β0 + β1xt - 1, where Yt = ln (spot rate) in month t, and xi = 1 = ln (forward rate) in month t - 1. The analysis yielded the following results:
t-value = 47.9, s = .025, R2 = .957,
Durbin-Watson d = .962
a. Is the model statistically useful for forecasting future spot exchange rates for the British pound? Test using α = .05.
b. Interpret the values of s and R2.
c. Is there evidence of positive autocorrelation among the residuals? Test using α = .05.
d. Based on the results of parts a - c, would you recommend using the model to forecast spot exchange rates?