In: Statistics and Probability
Consider the following time series data.
Week | 1 | 2 | 3 | 4 | 5 | 6 |
Value | 18 | 12 | 16 | 11 | 17 | 14 |
Using the naïve method (most recent value) as the forecast for the next week, compute the following measures of forecast accuracy.
(a) | Mean absolute error |
If required, round your answer to one decimal place. | |
(b) | Mean squared error |
If required, round your answer to one decimal place. | |
(c) | Mean absolute percentage error |
If required, round your intermediate calculations and final answer to two decimal places. | |
(d) | What is the forecast for week
7? = 14 |
week | value | forecast | absolute error | squared error | percentage error |
1 | 18 | ||||
2 | 12 | 18 | 6 | 36 | 0.5 |
3 | 16 | 12 | 4 | 16 | 0.25 |
4 | 11 | 16 | 5 | 25 | 0.454545455 |
5 | 17 | 11 | 6 | 36 | 0.352941176 |
6 | 14 | 17 | 3 | 9 | 0.214285714 |
7 | 14 | ||||
mean | 4.8 | 24.4 | 0.354354469 |
formulas used
week | value | forecast | absolute error | squared error | percentage error |
1 | 18 | ||||
=1+A2 | 12 | =B2 | =ABS(C3-B3) | =D3^2 | =D3/B3 |
=1+A3 | 16 | =B3 | =ABS(C4-B4) | =D4^2 | =D4/B4 |
=1+A4 | 11 | =B4 | =ABS(C5-B5) | =D5^2 | =D5/B5 |
=1+A5 | 17 | =B5 | =ABS(C6-B6) | =D6^2 | =D6/B6 |
=1+A6 | 14 | =B6 | =ABS(C7-B7) | =D7^2 | =D7/B7 |
7 | =B7 | ||||
mean | =AVERAGE(D3:D7) | =AVERAGE(E3:E7) | =AVERAGE(F3:F7) |
a)
mean absolute error = 4.8
b)
mean squared error = 24.4
c)
MAPE = 0.35
d) forecast for week 7 = 14