19 Probability distribution of forecasts Assume that the following regression model was applied to historical quarterly data: et = a0 + a1 INTt + a2 INFt-1 + t where et = percentage change in the exchange rate of the Japanese yen in period t INTt = average real interest rate differential (US interest rate minus Japanese interest rate) over period t INFt-1 = inflation differential (US. inflation rate minus Japanese inflation rate) in the previous period a0, a1, a2 = regression coefficients t = error term Assume that the regression coefficients were estimated as follows: a0 = 0.0 a1 = 0.9 a2 = 0.8 Also assume that the inflation differential in the most recent period was 3 per cent. The real interest rate differential in the upcoming period is forecasted as follows: Interest Rate Differential Probability 0% 30% 1 60 2 10 If Stillwater, Pty Ltd uses this information to forecast the Japanese yen's exchange rate, what will be the probability distribution of the yen's percentage change over the upcoming period