Question

Consider the following time series data. Week 1 N 3 4 5 6 Value 19 11 13 10 14 12 (a) Construct a time series plot. 20 18 20 18 14 12 10 Week 3 4 Week D 20 18+ 16 Time Series Value Time Series Value 5 Week 0 Wook What type of pattem exists in the data? The data appear to follow a cyclical pattern. The data appear to follow a trend pattem. The data appear to follow a horontal pattern The data appear to follow a seasonal patter (b) Develop the three week moving average forecasts for this time series. (Round your answers to two decimal places.) Tiene Series Value Forecast 1 2 33 .

Please help

Answer 1

Time Series Value 2 & Week

The data appear to follow a horontal patter.

b)

Time period	Actual Value(A)	Moving avg. Forecast(F)	Forecast error E=|A-F|	Squared Forecast Error
1	19
2	11
3	13
4	10	14.33	4.33	18.78
5	14	11.33	2.67	7.11
6	12	12.33	0.33	0.11
		Total	7.33	26.00
		Average	2.44	8.67
			MAD	MSE
MSE =			8.67
forecast for week 7 =			12.00

c)

Time period	Actual Value(A)	Forecast(F)	Forecast error E=A-F	Squared Forecast Error
1	19
2	11	19.00	8.00	64.00
3	13	17.40	4.40	19.36
4	10	16.52	6.52	42.51
5	14	15.22	1.22	1.48
6	12	14.97	2.97	8.84
		Average	4.62	27.24
			MAD	MSE
MSE =			27.24
forecast for week 7 =			14.38

d)

The three-week moving average provides a better forecast since thas a smaller MSE than the smoothing approach

e)

Time period	Actual Value(A)	Forecast(F)
1	19
2	11	19.00
3	13	15.80
4	10	14.68
5	14	12.81
6	12	13.28

The exponential smoothing using a 0.4 provides a better forecast since has a smaller HSE than the exponential soothing using c 0.2