theoretically expected sign estimated over the ll sample}, (b) Assume that investors rule out a negative equity premium, and set the forecast to zero whenever it is negative. Repeat the 003 forecasting exercise in the following scenarios: (i) Impose restriction (a). (ii) Impose restriction (b). (iii) Impose rst restriction (a) and then restriction (1)). Do you see improvements in predictive performance vis-a-vis not imposing these restrictions