Decomposition for Judgmental Forecasting and Estimation

Forecasters often need to estimate uncertain quantities, but with limited time and resources. Decomposition is a method for dealing with such problems by breaking down (decomposing) the estimation task down into a set of components that can be more readily estimated, and then combining the component estimates to produce a target estimate. Estimators can effectively apply decomposition to either multiplicative or segmented forecasts, though multiplicative decomposition is especially sensitive to correlated errors in component values. Decomposition is most used for highly uncertain estimates, such as ones having a large numerical value (e.g., millions or more) or quantities in an unfamiliar metric. When possible, multiple estimations should be used and the results aggregated. In addition, multiple decompositions can be applied to the same estimation problem and the results resolved into a single estimate. Decomposition should be used only when the estimation can make component estimates more accurately or more confidently than the target estimate.

[1]  M. W. Nelson,et al.  Using Decision Aids to Improve Auditors' Conditional Probability Judgments , 1998 .

[2]  John S. Morris,et al.  Top-Down or Bottom-Up: Which Is the Best Approach to Forecasting? , 1997 .

[3]  G. Menon,et al.  Are the Parts Better than the Whole? The Effects of Decompositional Questions on Judgments of Frequent Behaviors , 1997 .

[4]  S. Andradóttir,et al.  Choosing the Number of Conditioning Events in Judgemental Forecasting , 1997 .

[5]  Terry Connolly,et al.  Decomposed versus holistic estimates of effort required for software writing tasks , 1997 .

[6]  Don N. Kleinmuntz,et al.  Conditioned assessment of subjective probabilities : Identifying the benefits of decomposition , 1996 .

[7]  J. Scott Armstrong,et al.  Judgmental Decomposition: When Does it Work? , 1994 .

[8]  S. Plous.  The psychology of judgment and decision making , 1994 .

[9]  Max Henrion,et al.  Divide and Conquer? Effects of Decomposition on the Accuracy and Calibration of Subjective Probability Distributions , 1993 .

[10]  Nancy G. Dodd,et al.  The use of decomposition in probability assessments of continuous variables , 1993 .

[11]  Byron J. Dangerfield,et al.  Top-down or bottom-up: Aggregate versus disaggregate extrapolations , 1992 .

[12]  R. H. Edmundson.  Decomposition; a strategy for judgemental forecasting , 1990 .

[13]  Donald G. MacGregor,et al.  Problem Structuring Aids for Quantitative Estimation , 1990 .

[14]  Paul Slovic,et al.  Structuring Knowledge Retrieval: An Analysis of Decomposed Quantitative Judgments , 1988 .

[15]  W. Edwards,et al.  Decision Analysis and Behavioral Research , 1986 .

[16]  R. Dawes.  Judgment under uncertainty: The robust beauty of improper linear models in decision making , 1979 .

[17]  J. Scott Armstrong,et al.  Long-Range Forecasting: From Crystal Ball to Computer , 1981 .

[18]  J. Armstrong.  The Use of the Decomposition Principle in Making Judgments , 1975 .

[19]  A. Tversky,et al.  Judgment under Uncertainty: Heuristics and Biases , 1974, Science.

[20]  R. Dawes,et al.  Linear models in decision making. , 1974 .

[21]  Paul Slovic,et al.  Comparison of Bayesian and Regression Approaches to the Study of Information Processing in Judgment. , 1971 .

[22]  W. Allen Spivey,et al.  Analysis and Prediction of Telephone Demand in Local Geographical Areas , 1971 .

[23]  J. Scott Armstrong,et al.  Exploratory Analysis of Marketing Data: Trees vs. Regression , 1970 .

[24]  Lewis R. Goldberg,et al.  Man versus model of man: A rationale, plus some evidence, for a method of improving on clinical inferences. , 1970 .

[25]  L. R. Goldberg.  Simple models or simple processes? Some research on clinical judgments. , 1968, The American psychologist.

[26]  Paul E. Meehl,et al.  When shall we use our heads instead of the formula , 1957 .