Time-Series Prediction Techniques

This section discusses statistics related to time-series prediction, or forecasting, techniques available in Predictor:

• Standard Forecasting

• Holdout Forecasting

• Simple Lead Forecasting

• Weighted Lead Forecasting

Related terms:

• Time series—The original data, expressed as Y_t

• Fit array—A retrofit of the time series, consisting of one-period-ahead forecasts performed from the data of previous periods; expressed as F_t

• Residual array—A set of positive or negative residuals, expressed as r_t, and defined as r_t = Y_t – F_t

• RMSE—Root mean square error for forecasting, calculated as described in RMSE, where n is the number of periods for which a fit is available. RMSE depends on the specific forecasting method and technique.

• Forecasts—Value projections calculated using the formula for the specific method; they are 1 to k periods ahead, where k is the number of forecasts required; also known as predictions.

• Standard error of forecasts—Used to calculate prediction intervals; see Prediction Intervals