Data Analysis
Total points 125. Submit through D2L in Word/Excel format, single or multiple files. Must show your work, answer all parts of the question, and write necessary explanations to earn full points. You have to use Excel to solve this numerical problem (project).
Part (A)- 65 points
The data below is for 20 periods of sales in $millions.
t Sales(Y)
1 10
2 11
3 14
4 14
5 12
6 15
7 18
8 16
9 16
10 17
11 16
12 20
13 24
14 22
15 20
16 24
17 26
18 28
19 28
20 26
21
Plot the time series data. Forecast for the 21st period using simple exponential smoothing with alpha 0.2 and 0.9 and plot the actual 20 period values with forecasted values. Compare the two forecasts using MSE and RMSE. Also calculate the errors and plot the errors for the two forecasts. Comment on the plots (about stationarity). Do you see systematic underestimation? Now perform the forecast using Holt’s two parameter model with alpha = 0.2 and beta = 0.5. Plot the Holt’s forecast with actual values. Also calculate the MSE for Holt’s forecast. Is it better than the simple exponential smoothing forecasts? Plot the errors for Holt’s model. Does it look nearly stationary.
Part (B)- 60 points
For the data below (Production = Y in million tons) plot the data and comment whether you see a seasonal pattern. Perform Holt-Winters’ seasonal forecast using alpha = 0.6, beta = 0.3 and gamma = 0.9. Make forecasts for 2007-q1 and 2007-q2 using Holt-Winters’ model. Calculate the errors and MSE and RMSE. Plot the errors and comment on the plot.
Year-q period=t Y
2001-1 1 79
2001-2 2 105
2001-3 3 95
2001-4 4 89
2002-1 5 95
2002-2 6 137
2002-3 7 132
2002-4 8 116
2003-1 9 115
2003-2 10 153
2003-3 11 142
2003-4 12 127
2004-1 13 142
2004-2 14 201
2004-3 15 179
2004-4 16 164
2005-1 17 200
2005-2 18 243
2005-3 19 230
2005-4 20 216
2006-1 21 222
2006-2 22 280
2006-3 23 265
2006-4 24 255
2007-1
2007-2