Lesson 4: Predictions, interpolation and extrapolation
Predict solar output and judge the predictions
SkillsMaking predictionsInterpolation and extrapolation
Worked example
A Toowoomba household's solar data, for days with 4.5 to 10.2 hours of sunshine, gives the least-squares line
with energy in kWh and sunshine in hours, and .
a) Predict the energy generated on a day with 7 hours of sunshine, and comment on the reliability of the prediction.
b) Predict the energy generated on a day with 13 hours of sunshine, and comment on the reliability.
Step 1: Substitute 7 hours
Step 2: Judge the first prediction
7 hours is within the data (4.5 to 10.2 hours), so this is interpolation. With (a strong linear association), the prediction is reliable.
Step 3: Substitute 13 hours
Step 4: Judge the second prediction
13 hours is outside the data, so this is extrapolation and less reliable. We have no evidence the trend continues: on long summer days high panel temperatures reduce efficiency, and a system's inverter caps its output.
The line only describes the association where there is data. Beyond it, other factors can change the relationship.
Answer
a) 16.26 kWh — reliable: strong linear association and interpolation. b) 28.14 kWh — less reliable, because it is extrapolation beyond 10.2 hours.
Try a similar one
A fresh question of the same kind, checked as you answer, with hints and a full solution.
Method
Substitute into the least-squares line and show the working.
Compare the explanatory value with the range of the data.
Comment using strength ( or ) and interpolation or extrapolation.
Watch out for
Calling a prediction reliable only because is close to 1, while ignoring extrapolation.