Relative accuracy of judgemental and extrapolative methods in forecasting annual earnings

Abstract

This paper identifies and analyses previously published studies on annual earnings forecasts. Comparisons of forecasts produced by management, analysts, and extrapolative techniques indicated that: (1) management forecasts were superior to professional analyst forecasts (the mean absolute percentage errors were 15.9 and 17.7, respectively, based on five studies using data from [1967][1968][1969][1970][1971][1972][1973][1974] and (2) judgemental forecasts (both management and analysts) were superior .to extrapolation forecasts on 14 of 17 comparisons from 13 studies using data from 1964-1979 (the mean absolute percentage errors were 21 .O and 28.4 for judgement and extrapolation, respectively).These conclusions, based on recent research, differ from those reported in previous reviews, which commented on less than half of the studies identified here. KEY WORDS Annual financial forecasts Judgement vs. extrapolation Management vs. analyst Amalgamated forecastsThis paper examines the accuracy of those methods currently used in forecasting annual earnings : management judgement, outside analyst judgement, and extrapolations. The first section draws upon research in finance and other fields to develop hypotheses concerning which forecasting methods would be most accurate for annual earnings forecasts. Section 2 presents a quantitative analysis of previously published studies, comparing management forecasts with analyst forecasts. In Section 3, a quantitative analysis is made of the evidence on judgement and extrapolative forecasts. The final sections offer proposals for further research and summarize the major conclusions.

Forecasters and rationality—A comment on Fritsche et al., Forecasting the Brazilian Real and Mexican Peso: Asymmetric loss, forecast rationality and forecaster herding

“…forecasts could outperform statistical model-based forecasts. Hogarth and Makridakis (1981) reached the unequivocal conclusion that quantitative methods outperform judgmental forecasts Even at the time this contrasted with the conclusions coming out of the accounting earnings forecasting literature where analysts forecasts, primarily judgmental, were proving more accurate than time series methods (Armstrong, 1983;Brown, Hagerman, Griffin, & Zmijewski, 1987)). Nor were such organisationally based judgmental forecasts executed in a vacuumthey were often based on a statistical forecast where judgment adjusted (or even overrode) the statistical forecast.…”

The impact of forecasting on operational performance: Mediation effects through flexibility enablers

“…The forecasting literature suggests the importance of relying on structured techniques to forecast demand (e.g., Armstrong 1983Armstrong , 1984Dalrymple 1987;Sanders and Manrodt 1994). Conforming with previous literature and to measure the adoption of structured techniques, we considered the extent to which companies use: (1) quantitative time series models (e.g., exponential smoothing) and…”

Weighted spatial dynamic shift‐share model as a forecasting tool for a regional economy: The case of South Korea

“…The best model by industry and region is selected here based on the mean absolute percentage error (MAPE) which was first suggested by Armstrong (1983). MAPE is one of the most common and useful measures of the prediction accuracy of a forecasting method, because it is a dimensionless metric (Carbone & Armstrong, 1982; Chu, 1998; Oyewole, 2001).…”