The only two models that give a fairly close approximation are A and C. Here is a table comparing their values with those for the given function E.
Year t | 6 (1976) | 8 | 10 | 12 | 14 | 16 | 18 | 20 | 22 | 24 | 26 (1996) |
Expenditure E (Billions) | $2.5 | 3.0 | 3.0 | 3.1 | 3.0 | 3.1 | 3.2 | 3.3 | 3.4 | 3.3 | 3.1 |
Model A | 2.48 | 2.54 | 2.6 | 2.66 | 2.72 | 2.78 | 2.84 | 2.9 | 2.96 | 3.02 | 3.08 |
Model C | 2.528 | 2.672 | 2.8 | 2.912 | 3.008 | 3.088 | 3.152 | 3.2 | 3.232 | 3.248 | 3.248 |
From the table, we can see that, for the most part, Model C gives a better approximation.
(One could actually make this claim precise by computing the "sum of squares error" for each model: square and add the errors (quantity predicted by the model minus actual quantity). Model C gives a much smaller sum-of-squares-error,)
Just close this window to return to the tutorial.
Lost the tutorial? Press here.