You are on page 1of 10

# SQQS3163 Forecasting Methods Matric No.: …………………..

QUESTION 1 (10 MARKS)

a) Describe the differences between qualitative forecasting techniques and quantitative
forecasting techniques.
(2 marks)

b) Complete the following sentences:

i. The overall upward or downward pattern of the data in annual time series will be
contained in the ____________ component.
(1 mark)

ii. The effect of an unpredictable, rare event will be contained in the ___________
component.
(1 mark)

iii. Based on the Mean Absolute Error (MAE) criterion in TABLE 1, the most appropriate
model is _____________.

TABLE 1

Model
Error measure
Linear trend Quadratic trend Exponential trend AR(2)
MAE 1.38 1.22 1.39 0.71
(1 mark)

c) Is the plot Y versus T in FIGURE 1 shows a stationary time series? Explain.

500

400

300

200

100

0
Y

1 5 9 13 17 21 25 29 33 37 41 45 49 53 57 61 65

T

FIGURE 1
(2 marks)

1

SQQS3163 Forecasting Methods Matric No.: …………………. d) A study was conducted to forecast the number of visitors in BBC Garden for a few weeks. TABLE 2 Year Quarter Time (t) Profit (yt) 2013 1 1 58 2 2 63 3 3 65 4 4 77 2014 1 5 79 2 6 81 3 7 88 4 8 95 2 .. explain the pattern of data and state the TWO (2) suitable techniques to analyze the data. (3 marks) QUESTION 2 (15 MARKS) Quarterly profit of paper sales (MYR thousands) for the years 2013 to 2014 displayed in TABLE 2. The OUTPUT 1 and OUTPUT 2 represents the result of time series regression for deseasonalize data and trend respectively. number of visitors (Y) 20000 18000 16000 14000 12000 10000 8000 6000 4000 2000 0 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 week (T) FIGURE 2 Based on the FIGURE 2.

(13 marks) b) Based on part (a).: ………………….42399 6. OUTPUT 1: Time series regression for profit of paper sales (yt) and time (t) Coefficients Standard Error t Stat P-value Intercept 52.000 a) By choosing the suitable information given in OUTPUT 1 and OUTPUT 2. (2 marks) QUESTION 3 (20 MARKS) a) Give the appropriate situation to use Holt’s method.411 1.166667 0. analyze the data in TABLE 2 using the multiplicative decomposition method and produce the estimated trend.000 t 4.5 1.808819 29. (2 marks) b) What is the range for smoothing constants in Holt’s method? (1 mark) c) Show that SSE   et2 using Holt’s method formula.271 18. (Assume there is no cycle component).358199 14. (4 marks) 3 .11E-07 t 5.SQQS3163 Forecasting Methods Matric No. calculate the predicted value at the time period sixth.02447 1.318 0.369 39.027 0.964 0.96E-06 OUTPUT 2: Time series regression for deseasonalize data (Dt) and time (t) Coefficients Standard Error t Stat P-value Intercept 53..

1000 D E 22. Based on the output.8000 1992 3 29.9999 and 0.2974 29.8000 A B C 1991 2 26. (2 marks) QUESTION 4 (15 MARKS) a) State THREE (3) assumptions used when estimating a regression model. Your answer should be based on the given information in APPENDIX A.. E. (1 mark) ii. (3 marks) b) What is the effect of the model if the error terms for a time series model are autocorrelated? (1 mark) c) The computer output in APPENDIX A represents the result of time series regression analysis on PSC printer sales. Write the equation of the estimate model.9000 147. By using Holt’s method. i.SQQS3163 Forecasting Methods Matric No. C.1000 150.9675.2695 153.4000 3.3105 2012 23 147. D.1001 2.2344 F G i. Forecast the number of passengers who will fly on ABC planes in year 2017. the numbers of passengers who fly on ABC planes from year 1990 to 2013 have been analyzed. answer the following questions. (Use formula: St  yt  1   St 1  Tt 1  and Tt   St  St 1   1   Tt 1 ). (11 marks) ii. (Use α = 0.05) (10 marks) 4 . d) ABC Airlines would like to know the number of passengers who will fly on ABC planes. Comment on the model obtained.: …………………. B. TABLE 3 Year Time Number of Smoothed Trend Forecast m Forecast period passengers series estimate period into the error (thousands) future t yt S t  Tt  Ft m  et 1990 1 22. F. Find the value for A.1104 2013 24 150.4000 29. G. TABLE 3 display the results when smoothed series () and trend estimate (β) values are respectively equal to 0.9005 3.

(9 marks) END OF QUESTIONS 5 .9.5.25 t 1  0. Assume Yˆ1  35 and  0  0 .3 t  2 i. Determine if this model is a reasonable model for forecasting shampoo sales at α = 0. Name the model in part 5(b) and state the stationary condition of the model. calculate forecast value for periods three if period two is the forecast origin.SQQS3163 Forecasting Methods Matric No. QUESTION 5 (20 MARKS) a) Build a flow diagram or pseudocode to display the Box-Jenkins model-building strategy. The first four observations are Y1=32. Write a brief report to support your argument. (2 marks) ii.. diagnostic checking and forecasting of shampoo sales using model zt  1 zt 1  at where zt  yt  yt 1. (5 marks) b) Suppose the following time series model has been fit to historical data and found to be an adequate model. (4 marks) c) APPENDIX B presents the estimation. Y2=36.3 and Y4=31.6. Yˆt  35  0.: …………………. Y3=33.05.

71 <.0001 timesq 1 -0.27 0.28292 -2.14608 Corrected Total 23 1945945 Root MSE 59.0340 Durbin-Watson D 1.64147 0.682 Number of Observations 24 1st Order Autocorrelation 0. The REG Procedure Model: MODEL2 Dependent Variable: y Analysis of Variance Sum of Mean Source DF Squares Square F Value Pr > F Model 2 1872232 936116 266.28554 7.0001 Error 21 73713 3510.145 6 . Legend: A = 1 obs.: ………………….19070 7.9621 Dependent Mean 671.52936 2. B = 2 obs. APPENDIX A Notes: time = time = t timesq = (time)2 = t2 Plot of y*time.69 <.66667 Adj R-Sq 0.54 0.9585 Coeff Var 8.25000 39.82082 Parameter Estimates Parameter Standard Variable DF Estimate Error t Value Pr > |t| Intercept 1 100.24649 R-Square 0. etc..0192 time 1 56. y | 1500 + | | | | | A 1000 + A A A A A | A A | A A A | | A | A A A A 500 + A A | A A | A | A | A A | 0 + --+-------+-------+-------+-------+-------+-------+-------+-- 0 4 8 12 16 20 24 28 time NOTE: 4 obs had missing values.SQQS3163 Forecasting Methods Matric No.

y | | 500 + | | A | 450 + AAAA A A | | A A A | A A A 400 + A AA A | AA AA AA A A | A | 350 + A | A | A A | 300 + | --+---------+---------+---------+---------------------------- 0 10 20 30 time Plot of z*time. etc. diagnostic checking and forecasting of shampoo sales using model zt  1 zt 1  at where zt  yt  yt 1 Plot of y*time.. Legend: A = 1 obs. APPENDIX B Notes: SAS output of estimation.SQQS3163 Forecasting Methods Matric No. 7 .: …………………. B = 2 obs. B = 2 obs. z | | 100 + | | | A A 50 + A | A A A | A | A A A A A 0 + AA A A A A A | A A | A A A A A | A -50 + A A | | | -100 + | --+---------+---------+---------+---------------------------- 0 10 20 30 time NOTE: 1 obs had missing values. Legend: A = 1 obs. etc.

941E-8 ARIMA Estimation Optimization Summary Estimation Method Conditional Least Squares Parameters Estimated 1 Termination Criteria Maximum Relative Change in Estimates Iteration Stopping Value 0.1 -0.8542 Number of Residuals 29 * AIC and SBC do not include log determinant.169 0.072 -0.14765 -4.001 Iterations 2 Conditional Least Squares Estimation Standard Approx Parameter Estimate Error t Value Pr > |t| Lag AR1.144 -0.225 0.7600 0.129 -0.020 0.02 5 0.043 -0.041 0..001 Criteria Value 2.64031 0.042 -0.47 11 0.64181 0.347E-8 Alternate Criteria Relative Change in Objective Function Alternate Criteria Value 3.4869 SBC 265. The ARIMA Procedure Conditional Least Squares Estimation Iteration SSE AR1.64031 1E-6 0.014 -0.107 0.000357 R-Square Change from Last Iteration 1.74267 AIC 264.012 0.77E-16 Maximum Absolute Value of Gradient 0.8464 0.SQQS3163 Forecasting Methods Matric No.193 12 7.7156 0.56 23 0.0002 1 Variance Estimate 517.056 -0.30 17 0.154 0.130 18 13.141 -0.34 0.941E-8 Objective Function Sum of Squared Residuals Objective Function Value 14482.029 0.: ………………….081 0.030 -0. Pr > Lag Square DF ChiSq ------------------Autocorrelations----------------- 6 2.137 8 .001924 2 14482 -0.2288 Std Error Estimate 22.64031 1E-7 1.061 24 21.045 0.5468 -0.1 Lambda R Crit 0 14482 -0.236 -0.41 Marquardt's Lambda Coefficient 1E-7 Numerical Derivative Perturbation Delta 0.00001 1 1 14482 -0. Autocorrelation Check of Residuals To Chi.

| 11 0. |** . | 7 0.442400 -. | 6 0. |* . *| ..10581 | .02878 | .885433 0. *| .411342 0.399418 -.207544 11 -79. | 0. |* . *| . | 14 -0. | 0.212275 13 87.16864 | .188593 6 -99.111720 0.08716 | .13546 | .06574 | . |* . | 4 -0.961053 0. |* . | 0. | 0.01167 | . *****| . *| . | 0.12984 | .06732 | . |*** . ****| .923700 -. | . | 11 -0.22476 | . | 7 -0." marks two standard errors Inverse Autocorrelations Lag Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 1 -0. | 8 0. | 10 0.07233 | .19902 | .05306 | .219509 ".05082 | . | 3 0.155623 0.05594 | . | 4 -0. | Partial Autocorrelations Lag Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 1 0.10655 | . | 12 0.208411 12 67. | 0. | 13 -0. |**** . | 5 0. |**** .19448 | .18770 | . |* . |** . | 2 -0.04452 | . | 13 0. |*** . | .15822 | .03443 | .187944 4 -10. |** .18720 | . | 9 . ****| . ***| .214996 14 23. |*** .185695 2 55. **| . | 5 0.19319 | .12068 | .08359 | .15351 | .10322 | . |*** . **| . ****| . | .02878 | . | 0.198974 10 37. | 2 0. |* .15690 | . |**** . | 0. |* . | 3 -0.117856 0.SQQS3163 Forecasting Methods Matric No. | 9 0.185849 3 28. | 9 -0. | 0. | 0. ****| . ***| .20818 | . | . |** .23420 | .01667 | .16755 | . | 14 0. | 6 -0. **| . | 10 -0.14136 | . | 0. |*** .06092 | .02019 | .05599 | .038524 0.251 -.00000 | |********************| 0 1 14.: ………………….195480 9 -116. | 0. | 0. *| . ***| . |*** . Autocorrelation Plot of Residuals Lag Covariance Correlation -1 9 8 7 6 5 4 3 2 1 0 1 2 3 4 5 6 7 8 9 1 Std Error 0 517.195456 8 73.224109 0.02017 | .494169 0. | 8 -0. |* . | 0.229 1.02996 | .188757 7 6.07793 | . | 12 -0.188518 5 15.01984 | .027297 0. | .12655 | .

181 1.106 1.360 1.046 1.991 21 1.390 1.128 0.553 1.400 .356 0.510 1.964 22 1.391 1.579 0.180 1.656 1.570 1.210 1.206 1.861 1.580 1.879 1.685 1.310 1.824 1.133 1.535 0.933 1.967 1.779 1.604 0.230 1. .556 1.873 27 1. .946 1.368 2.538 1.953 1.361 0.104 1.814 1.320 1.302 1.469 1.940 23 1.567 1.897 1.536 0.110 1.160 1.078 1.935 0.580 1.730 1.101 1.896 .455 2.320 0.401 1.610 1.895 1.090 1.331 0.296 2.476 1.650 1.864 0.829 1.927 1.669 0.539 0. .767 1.162 1.062 1.381 1.130 1.376 2.390 14 1.841 30 1.777 0.316 1.500 1. - 8 0.240 1.894 1. .685 0.792 1.506 13 1.123 1.104 18 1.872 0.177 0.560 1.905 1.525 2.979 1.857 1.016 0.370 1.822 11 0.023 20 1. .454 1.563 1.220 16 1.863 1.352 1.429 1.284 1.812 1.013 1.240 1.158 1.150 1.094 0.982 1.270 1.300 1.077 1.861 28 1.660 0.074 1.925 1.651 1. APPENDIX C Durbin-Watson Statistic Critical values at 5% level of significance n = number of observations k' = number of explanatory variables excluding the intercept k’ = 1 k’ = 2 k’ = 3 k’ = 4 k’ = 5 n dL dU dL dU dL dU dL dU dL dU 6 0.260 1.562 0.710 0.641 0.902 25 1. .859 1.658 1.280 1.820 1..332 0.445 2.050 1.632 2.288 1.053 1.752 2.180 1.920 24 1.699 0.224 1.201 1.650 1.400 1.816 0.537 0.483 1.971 1.: ………………….562 2.650 1.536 0.650 1.767 0.977 0.380 1.273 1.143 1.124 1.038 1.797 0.763 1.779 0.650 1.512 2.785 0.243 2.296 15 1. .645 12 0.580 1.750 0.710 2.759 0.489 1.444 2.330 1.730 1.015 1. - 9 0.287 .045 1.574 2.654 1.700 1.379 2.820 33 1.812 0.028 1.664 2.283 0.775 0.559 1.220 1.143 1.810 35 1.255 1.541 1.190 1. - 10 0.100 1.414 0.551 0. .188 1.270 1.753 1.350 0.570 1.828 0.157 17 1.320 0.697 1.030 0.900 0.743 1.747 1.998 1. .520 1.986 1.198 1.595 1.505 2.147 1.958 1.125 1.341 1.543 0.340 0.739 1.734 1.160 1.437 1.800 10 .650 1. .928 0.257 1. .927 1.715 1.728 0.588 .650 1.060 19 1.371 0.543 1.500 1.676 0.658 1.340 1.467 1.071 1.629 1.084 1.168 1.546 1.026 1.830 32 1.550 1.420 1.214 1.850 29 1.650 1.446 1.328 1.848 0.730 1.730 1.664 0.004 1.411 1.740 1. - 7 0.SQQS3163 Forecasting Methods Matric No.461 1.652 1.510 1.221 1. .239 1.833 31 1.810 34 1.696 0.886 26 1.615 2.010 1.324 0.316 2.