S. No.

Season Attendance Forecast Error

1 1990-1991 7.3 6.9909 0.095543
2 1991-1992 7.4 7.5254 0.015725
3 1992-1993 7.9 8.0599 0.025568
4 1993-1994 8.1 8.5944 0.244431
5 1994-1995 9 9.1289 0.016615
6 1995-1996 9.5 9.6634 0.0267
7 1996-1997 10.6 10.1979 0.161684
8 1997-1998 11.5 10.7324 0.58921
9 1998-1999 11.7 11.2669 0.187576
10 1999-2000 11.4 11.8014 0.161122
11 2000-2001 11.9 12.3359 0.190009
12 2001-2002 12.8704
Mean error 0.155835
a. y=0.5345x+6.4564
b. Average increase in
attendace = 0.5345
d. 12.8704
 Trendline

f(x) = 0.5345454545x + 6.4563636364

R² = 0.9482830499

2 4 6 8 10 12
 Utilization Forecast (n=3) Forecast (n=4) Mean Square Error (n=3)
2000 1 82.5
2 81.3
3 81.3
4 79 81.7 7.29
2001 1 76.6 80.533333333 81.025 15.4711111111
2 78 78.966666667 79.55 0.9344444444
3 78.4 77.866666667 78.725 0.2844444444
4 78 77.666666667 78 0.1111111111
2002 1 78.8 78.133333333 77.75 0.4444444444
2 78.7 78.4 78.3 0.09
3 78.4 78.5 78.475 0.01
4 80 78.633333333 78.475 1.8677777778
2003 1 80.7 79.033333333 78.975 2.7777777778
2 80.7 79.7 79.45 1
3 80.8 80.466666667 79.95 0.1111111111
4 80.733333333 80.55

2.5326851852

It provides a better forecast as MSE is less for n=3

Mean Square Error (n=4)

19.580625
2.4025
0.105625
0
1.1025
0.16
0.005625
2.325625
2.975625
1.5625
0.7225

2.8130113636
 Utilization Forecast (alpha=0.4) Forecast (alpha=0.5)
2000 1 82.5
2 81.3 82.5 82.5
3 81.3 82.02 81.9
4 79 81.732 81.6
2001 1 76.6 80.6392 80.3
2 78 79.02352 78.45
3 78.4 78.614112 78.225
4 78 78.5284672 78.3125
2002 1 78.8 78.31708032 78.15625
2 78.7 78.510248192 78.478125
3 78.4 78.5861489152 78.5890625
4 80 78.5116893491 78.49453125
2003 1 80.7 79.1070136095 79.247265625
2 80.7 79.7442081657 79.9736328125
3 80.8 80.1265248994 80.3368164063
4 80.3959149396 80.5684082031
Mean Square Error (alpha=0.4) Mean Square Error (alpha=0.5)

1.44 1.44
0.5184 0.36
7.463824 6.76
16.31513664 13.69 b. MSE is lesser when alpha=0.5, hence it
1.0475931904 0.2025 provides a better forecast
0.0458439485 0.030625 c. Exponential smoothning method is better
of the two methods as error value is lesser
0.2792775815 0.09765625
for it.
0.2332114173 0.4144140625
0.0360057486 0.0492285156
0.0346514186 0.0357446289
2.2150685935 2.2664361572
2.5376056404 2.1104371643
0.9135380305 0.5276092911
0.4535687111 0.2145390415

2.3952660658 2.0142278651
when alpha=0.5, hence it
forecast
moothning method is better
ods as error value is lesser
S. No. Date Month NO2 valueCMA cma seasonal-irregular seasonal component
1 Jul-15 1 25 0.7699400413
2 2 28 0.8622868609
3 3 35 0.9520683321
4 4 50 1.3897561727
5 5 60 1.5684872525
6 6 60 1.6638884948
7 7 40 36.08333 36.20833 1.1047180667 1.2052426025
8 8 35 36.33333 36.41667 0.9610983982 0.992276278
9 9 30 36.5 36.5 0.8219178082 0.8484589041
10 10 25 36.5 36.41667 0.6864988558 0.6456687828
11 11 25 36.33333 36.33333 0.6880733945 0.5779548259
12 12 20 36.33333 36.54167 0.5473204105 0.5026678388
13 Jul-16 1 28 36.75 37.16667 0.7533632287 0.7699400413
14 2 30 37.58333 37.79167 0.7938257993 0.8622868609
15 3 35 38 38.20833 0.9160305344 0.9520683321
16 4 48 38.41667 38.41667 1.2494577007 1.3897561727
17 5 60 38.41667 38.20833 1.5703380589 1.5684872525
18 6 65 38 38 1.7105263158 1.6638884948
19 7 50 38 38.29167 1.3057671382 1.2052426025
20 8 40 38.58333 39.08333 1.0234541578 0.992276278
21 9 35 39.58333 40 0.875 0.8484589041
22 10 25 40.41667 41.33333 0.6048387097 0.6456687828
23 11 20 42.25 42.75 0.4678362573 0.5779548259
24 12 20 43.25 43.66667 0.4580152672 0.5026678388
25 Jul-17 1 35 44.08333 44.5 0.7865168539 0.7699400413
26 2 42 44.91667 45.125 0.9307479224 0.8622868609
27 3 45 45.33333 45.54167 0.9881061299 0.9520683321
28 4 70 45.75 45.75 1.5300546448 1.3897561727
29 5 72 45.75 45.95833 1.5666364461 1.5684872525
30 6 75 46.16667 46.375 1.6172506739 1.6638884948
31 7 60 46.58333 1.2052426025
32 8 45 0.992276278
33 9 40 0.8484589041
34 10 25 0.6456687828
35 11 25 0.5779548259
36 12 25 0.5026678388
37 Jul-18 1 0.7699400413
38 2 0.8622868609
39 3 0.9520683321
40 4 1.3897561727
41 5 1.5684872525
42 6 1.6638884948
43 7 1.2052426025
44 8 0.992276278
45 9 0.8484589041
46 10 0.6456687828
47 11 0.5779548259
48 12 0.5026678388

Deseasonalised a. The hourly seasonal indexe

b. Using the trend equation, t
60
c. The trend forecast has also

50
f(x) = 0.3930214981x + 33.0146658499
40 R² = 0.6083845757

30

20

10

0
0 5 10 15 20 25 30 35 40

Trend Forecast
90

80

70

60

50
f(x) = 0.2696003561x + 35.7061934525
40 R² = 0.0534281559
30

20

10

0
0 10 20 30 40 50 60
deseasonalised Forecasted Values Trend Forecast
32.4700608599 33.3752 25.6969028669
32.4717924742 33.7674 29.1171853464
36.7620671948 34.1596 32.5222733984 seasonal index
35.9775340316 34.5518 48.0185773289 average
38.2534189586 34.944 54.8092185504 1 0.786517 0.753363 0.76994
36.0601087072 35.3362 58.7954966307 2 0.930748 0.793826 0.862287
33.1883389436 35.7284 43.061389798 3 0.988106 0.916031 0.952068
35.272434479 36.1206 35.8416145263 4 1.530055 1.249458 1.389756
35.3582240161 36.5128 30.979610274 5 1.566636 1.570338 1.568487
38.7195426938 36.905 23.8284064276 6 1.617251 1.710526 1.663888
43.2559758645 37.2972 21.5560967327 7 1.104718 1.305767 1.205243
39.7877056277 37.6894 18.9452492449 8 0.961098 1.023454 0.992276
36.3664681631 38.0816 29.3205486774 9 0.821918 0.875 0.848459
34.7912062224 38.4738 33.1754522284 10 0.686499 0.604839 0.645669
36.7620671948 38.866 37.0030877967 11 0.688073 0.467836 0.577955
34.5384326703 39.2582 54.5593257803 12 0.54732 0.458015 0.502668
38.2534189586 39.6504 62.1911469554
39.0651177662 40.0426 66.6264214428
41.4854236795 40.4348 48.7337435823
40.3113536903 40.827 40.5116636009
41.2512613522 41.2192 34.9727972603
38.7195426938 41.6114 26.8671819868
34.6047806916 42.0036 24.2761833253
39.7877056277 42.3958 21.3110051616
45.4580852038 42.788 32.9441944878
48.7076887113 43.1802 37.2337191105
47.2655149648 43.5724 41.4839021951
50.3685476442 43.9646 61.1000742316
45.9041027503 44.3568 69.5730753604
45.075135884 44.749 74.4573462548
49.7825084154 45.1412 54.4060973666
45.3502729016 45.5334 45.1817126756
47.1442986882 45.9256 38.9659842466
38.7195426938 46.3178 29.905957546
43.2559758645 46.71 26.9962699179
49.7346320346 47.1022 23.6767610783
47.4944 36.5678402983
47.8866 41.2919859926
48.2788 45.9647165935
48.671 67.6408226829
49.0632 76.9550037655
49.4554 82.2882710668
49.8476 60.0784511508
50.2398 49.8517617503
 50.632 42.9591712329
51.0242 32.9447331051
51.4164 29.7163565105
51.8086 26.042516995

a. The hourly seasonal indexes has been depicted above.

b. Using the trend equation, the forecast for July 18 has been depicted above.
c. The trend forecast has also been depicted in coloumn K.