Exponential smoothing procedures, in particular those recommended by Brown [1962] are used extensively in many areas of economics, business and engineering. It is shown in this paper that: Brown's forecasting procedures are optimal in terms of achieving minimum mean square error forecasts only if the underlying stochastic process is included in a limited subclass of ARIMA (p, d, q) processes. Hence, it is shown what assumptions are made when using these procedures. The implication of point (i) is that the users of Brown's procedures tacitly assume that the stochastic processes which occur in the real world are from the particular restricted subclass of ARIMA (p, d, q) processes. No reason can be found why these particular models should occur more frequently than others. It is further shown that even if a stochastic process which would lead to Brown's model occurred, the actual methods used for making the forecasts are clumsy and much simpler procedures can be employed.