Also
referred to as weighted moving
average. Unlike the simple moving
average where each observation receives the same weight, this method computes a
different weight for each observation before computing the weighted mean as a
forecast. In most cases, more recent
observations receive a greater weight than older observations. For example, in a 3-week moving average the
most recent observation receives a weight that is 3 times as great as that
given to the oldest observation (e.g. 3/6 versus 1/6). The middle observation’s weight would be
twice that of the oldest observation (2/6).