Blackwell Reference Online

Extract

Figure 3.1 The probability density function of the two-piece normal distribution. Dashed line, two halves of normal distributions with μ = 2.5, σ 1 = 0.902 (left) and σ 2 = 1.592 (right); solid line, the two-piece normal distribution A density forecast of the realization of a random variable at some future time is an estimate of the probability distribution of the possible future values of that variable. It thus provides a complete description of the uncertainty associated with a forecast, and stands in contrast to a point forecast, which by itself contains no description of the associated uncertainty. Intermediate between these two extremes is an interval forecast, which specifies the probability that the actual outcome will fall within a stated interval. To report a forecast interval represents a first response by point forecasters to criticism of their silence on the subject of uncertainty, and this practice is becoming more common in macroeconomic forecasting. This field also contains several examples of density forecasts, and these feature as a more direct object of attention in the fields of finance and risk management. This chapter presents a selective survey of the use of density forecasts, and discusses some issues concerning their construction, presentation, and evaluation. A density forecast is, of course, implicit in the standard construction and interpretation of ... log in or subscribe to read full text