The treatment of missing values varies by method. For METHOD=STEPAR, missing values are tolerated in the series; the autocorrelations are estimated from the available data and tapered, if necessary. For the EXPO, WINTERS, and ADDWINTERS methods, missing values after the start of the series are replaced with one-step-ahead predicted values, and the predicted values are applied to the smoothing equations. For the WINTERS method, negative or zero values are treated as missing.