An analyst must decide between two different forecasting techniques for weekly s
ID: 446492 • Letter: A
Question
An analyst must decide between two different forecasting techniques for weekly sales of roller blades: a linear trend equation and the naive approach. The linear trend equation is Ft= 126+ 2.1 t, and it was developed using data from periods 1 through 10. Based on data from periods 11 through 20 as shown in the table, which of these two methods has the greater accuracy if MAD and mse are used? (Round your intermediate calculations and final answers to 2 decimal places). t= 11, 12, 13, 14, 15, 16, 17, 18, 19, 20 Units Sold 146, 146, 148, 144, 153, 149, 154, 157, 162, 166. MAD (Naive) , MAD (Linear) , MSE (Naive) , MSE (Linear) . Blank provides forecasts with less average error and less average squared error?
Explanation / Answer
MAD and MSE (Linear)
MAD = Sum of Abs(Error) / n = 60.5 / 10 = 6.05
MSE = Square of error / n = 452.05 / 10 = 45.205
MAD and MSE (Naive)
MAD = 36 /9 = 4
MSE = 192 / 9 = 21.33
t Units Sold Forecast(linear) Error Abs(Error) Square of Error 11 146 149.1 -3.1 3.1 9.61 12 146 151.2 -5.2 5.2 27.04 13 148 153.3 -5.3 5.3 28.09 14 144 155.4 -11.4 11.4 129.96 15 153 157.5 -4.5 4.5 20.25 16 149 159.6 -10.6 10.6 112.36 17 154 161.7 -7.7 7.7 59.29 18 157 163.8 -6.8 6.8 46.24 19 162 165.9 -3.9 3.9 15.21 20 166 168 -2 2 4 Sum 60.5 452.05