Uses historical info regarding only the dependent variable.
  1. Naive forecast - demand for the next period equals demand for the current period; account for trend; best used when demand is horizontal, trend, seasonal pattern
  2. Simple moving average - average of a demand time series by averaging the demand for the n most recent periods; forecast error (demand-forecast);x-week moving average
  3. Weighted moving average - time series method where each historical demand in the average can have its own weight, the sum of weights equals 1; most recent is given the highest value (i.e. 0.5) last the smallest (i.e. 0.2); multiply the values and add all 3;
  4. Exponential smoothing - a weighted moving average method, that calculates the average of a time series by giving recent demands more weight than earlier demands;Example, p. 493;

Including a trend:

Trend adjusted exponential smoothing p.494;

Multiplicative seasonal method p.496

Additive seasonal method

Forecast errors:

bias - always too high or too low

random

Mean squared error, standard deviation, mean absolute deviation - measurement of the dispersion of forecast errors.

 

 

 

 

Report Place comment