Youre a new financial analyst at a major investment house, tracking and forecasting earnings of the health care industry. At the end of each quarter, you forecast industry earnings for the next quarter. Experience has revealed that your clients care about your forecast accuracy that is, they want small errors but that they are not particularly concerned with the sign of your error. (Your clients use your forecast to help allocate their portfolios, and if your forecast is way off, they lose money, regardless of whether youre too optimistic or too pessimistic.) Your immediate predecessor has bequeathed to you a forecasting model in which current earnings (yt) are explained by one variable lagged by one quarter (xt1) and all the historical values of y.

(a) What is your forecast-horizon of interest?

(b) What type of information set do you have? Univariate or multivariate?

(c) Which loss function would you choose, Quadratic or Linlin? Justify.

(d) Under the loss function you choose in 1.3, what is the optimal forecast? The optimal forecast is defined as the forecast with the smallest conditionally expected loss.