The random walk model is written as: . In this model, represents the: NOT the forecasted value
Random walk model is used for the time series forecasting. In this model the major assumption is that in each and every period, the variable will have a random step away from the previous value. These steps are identical and independent in the distribution in its size.
This random model is represented as the distribution to have “drift” or “no drift” depending on the step sizes with a non-zero mean or a zero mean. This model is represented as the averages of X's and Y's. The forecast value is not represented by this model.
