TREND EXTRAPOLATION AND CONSENSUS METHOD

Trend Extrapolation and Consensus Method



Trend Extrapolation and Consensus Method

This paper provides assessment of the trend extrapolation and consensus method of forecasting by using appropriate examples and scenarios.

Consensus Method

A simple method of overcoming some of the disadvantage of intuitive forecasting is the use of a "panel of experts." The presumption is that many experts are more likely to be accurate than one. Forecasts of GDP growth, inflation, and unemployment in the UK, made by a panel of forecasters, have been analysed. Annual outcomes are predicted, and forecasts are revised monthly over a period of 24 months up to the end of the year of interest. Consensus forecasts can be calculated as a simple average of all panel members' forecasts at any point in time. We find, as is to be expected, consensus forecasts evolve towards actual outcomes, with diminishing cross-section standard deviations. Strong evidence of non-normality in cross-sections of forecasts is found, with estimated kurtosis invariably exceeding three. The most surprising finding in our analysis is that month-to-month changes in consensus forecasts appear to be quite strongly auto-correlated. For all three variables there is very strong statistically significant evidence of predictability in the consensus forecast revisions. It then follows that the consensus forecasts cannot be optimal. However, this phenomenon was far less apparent when the records of particular individual forecasters were examined. Finally, we attempted to assess whether the magnitude of eventual consensus forecast errors could be predicted from cross-section standard deviations—that is, from the degree of consensus among individual forecasters. It emerged that forecaster variability of this sort was of very limited value in anticipating the reliability of the consensus forecasts.

Consensus forecast efficiency tests based on forecast revisions

Trend extrapolation Method

Trend extrapolation is one particular method of solving the prediction of the inflection problem associated with the "S" curve of the analogy method (when is the curve going to change slope, B). Instead of focusing on a single device and attempting to predict the future course of development of that device, the trend extrapolation method considers a series of successive devices while performing similar functions. These may be considered individual representations of a broad area of technology. The extrapolated trend will eventually reach a physical limit and will lose its validity as the trend approaches this limit.

[Extrapolation Method]

Doom and Gloom pervades the UK economy as we enter into 2008, which is 'usually' an excellent atmosphere for stocks, especially if that doom and gloom to date has not resulted in anything other than corrections. Not even the crash in the financial sector that has seen many big banks fall by as much as 50% off their 2007 highs has managed to dent the FTSE 100 Index with barely registerable declines on the long-run FTSE 100 chart.

Speculation is rife of a high risk of a recession for the UK economy during 2008. However the last analysis in this current series for 2008 on UK GDP growth concluded with the opinion that despite early year weakness the UK economy ...