Contents
What is the problem with extrapolation?
The problem of extrapolation is the problem of inferring something about a phenomenon of interest in one context, based on what is known about it in another. For example, we may want to infer that a medicine works in pop- ulation Y , based on the fact that we know it works in population X.
Why is extrapolation dangerous?
The problem with extrapolation – Extrapolation is an exercise in simple forecasting: Our explanation for what happened in the past quickly becomes our prediction for the future. This is dangerous because we cannot accurately explain the past let alone predict the future.
What is the problem with extrapolation in regression analysis?
Extrapolation of a fitted regression equation beyong the range of the given data can lead to seriously biased estimates if the assumed relationship does not hold in the region of extrapolation. This is demonstrated by some examples that lead to nonsensical conclusions.
How reliable is extrapolation?
In general, extrapolation is not very reliable and the results so obtained are to be viewed with some lack of confidence. In order for extrapolation to be at all reliable, the original data must be very consistent.
When to use extrapolation beyond the relevant range?
Extrapolation beyond the relevant range is when values of Y are estimated beyond the range of the X data. If the unobserved data (data outside the range of the X data) is nonlinear then the estimates of Y can be significantly outside the confidence interval of the estimated Y values. Consider the production cost example (Example 11.1).
How is extrapolation used in a statistical forecast?
Extrapolation involves making statistical forecasts by using historical trends that are projected for a specified period of time into the future. Extrapolation involves making statistical forecasts by using historical trends that are projected for a specified period of time into the future. It is only used for time-series forecasts.
What’s the problem with using extrapolation in regression?
The reason is that in many cases extrapolation (unfortunately and unavoidably) relies on untestable assumptions about the behaviour of the data beyond their observed support. When extrapolating one must do two judgement calls: First, from a quantitative perspective, how valid is the model outside the range of the data?
Why do we need to be skeptical of extrapolation?
Although the fit of a model might be ” good “, extrapolation beyond the range of the data must be treated skeptically. The reason is that in many cases extrapolation (unfortunately and unavoidably) relies on untestable assumptions about the behaviour of the data beyond their observed support.