Question

following are two weekly forecasts made by two different methods for the number of gallons of gasoline, in thousands, demanded at a local gasoline station. Also shown are actual demand levels in thousands of gallons:

Forecasts

week Method 1 Method 2 Actual Demand

1 0.90 0.80 0.70

2 1.05 1.20 1.00

3 0.95 0.90 1.00

4 1.20 1.11 1.00

The MAD method 1 = ??? thousand gallons... 2. The absolute deviatin based on the forecast developed using Method 1 adds to ??? thousand gallons. Mean squared error (MSE) is the average of (actual-Forecast). from the information given in method 1 , the value of n=4. the value E(autal-forecast) will be??? thousand gallons.

Answer 1

Method 1
Week	Method 1	Actual	E	E^2
1	0.9	0.7	0.2	0.04
2	1.05	1	0.05	0.0025
3	0.95	1	0.05	0.0025
4	1.2	1	0.2	0.04
			0.5	0.085

MAD = sum of error/n

           = 0.5/4

           =0.125

MSE = sum of squared error/n

         = 0.0.85/4

         = 0.02125

Method 2
Week	Method 2	Actual	E	E^2
1	0.8	0.7	0.1	0.01
2	1.2	1	0.2	0.04
3	0.9	1	0.1	0.01
4	1.11	1	0.11	0.0121
			0.51	0.0721

MAD = 0.51/4 = 0.1275

MSE = 0.0721/4 = 0.018