ACCURACY OF JUDGMENTAL EXTRAPOLATION OF TIME-SERIES DATA - CHARACTERISTICS, CAUSES, AND REMEDIATION STRATEGIES FOR FORECASTING

This paper links social judgment theory to judgmental forecasting of t ime series data. Individuals were asked to make forecasts for 18 diffe rent time series that were varied systematically on four cues: long-te rm levels, long-term trends, short-term levels, and the magnitude of t he last data point. A model of each individual's judgment policy was c onstructed to reflect the extent to which each cue influenced the fore casts that were made. Participants were assigned to experimental condi tions that varied both the amount of information and the forecasting h orizon; ''special events'' (i.e, discontinuities in the time series) a lso were introduced. Knowledge and consistency were used as measures o f the judgment process, and MPE and MAPE were used as measures of fore cast performance. Results suggest that consistency is necessary but no t sufficient for the successful application of judgment to forecasting time series data. Information provided for forecasters should make lo ng-term trends explicit, while the task should be limited to more imme diate forecasts of one or two steps ahead to reduce recency bias. This paper provides one method of quantifying the contributions and limita tions of judgment in forecasting. (C) 1998 Elsevier Science B.V.