Lesson 4: Predictions, interpolation and extrapolation
The danger of extrapolating a phone battery
SkillsInterpolation and extrapolationMaking predictions
Worked example
A student records the battery remaining on her phone after 1 to 8 hours of use. The least-squares line is
with battery in percent.
a) Use the line to predict the battery remaining after 20 hours of use.
b) Explain why this prediction is not sensible.
c) After how many hours does the model predict the battery will reach 0%? Comment on this prediction.
Step 1: Substitute 20 hours
Step 2: Explain the problem
A battery can't have a negative charge. 20 hours is far outside the data (1 to 8 hours), so this is extrapolation: the model assumes the straight-line trend continues forever, which is impossible.
Step 3: Solve for 0%
Step 4: Comment
17 hours is also extrapolation, so it is unreliable. As a battery runs low, phones switch to low-power mode and the drain rate changes, so the linear trend probably doesn't hold.
Answer
a) . b) A negative battery level is impossible; 20 hours is extrapolation far beyond the data. c) About 17.0 hours, but this is extrapolation and unreliable.
Try a similar one
A fresh question of the same kind, checked as you answer, with hints and a full solution.
Method
Make the prediction by substitution.
Check whether the explanatory value is inside the data and whether the answer is possible.
Explain that extrapolation assumes the trend continues, and give a reason in context why it might not.
Watch out for
Reporting an impossible prediction without comment.
Saying "it is extrapolation" without explaining why that matters.