BEMM460

UNIVERSITY OF EXETER

BUSINESS SCHOOL

Mock exam paper 2022

Maths and Statistics for Business Analytics

Module Convenor: Professor Stephen Disney

Duration: TWO HOURS

Answer any four of the six questions.

All questions are worth equal marks.

Materials to be supplied:
Statistical tables in one appendix
Answer booklet

Materials to be supplied on request:

None

Approved calculators are permitted.

This is a closed note paper.

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

Q1

1a) Using a standard normal table (see Appendix A), find the z-factor that corresponds to the area
under the pdf curve being 80%. (20%)

1b) A plumbing company have found that the length of time, in minutes, for installing a bathtub is
normally distributed with mean = 160 minutes and standard deviation, = 25 minutes. 80% of the
bathtubs are installed by the company within how many minutes? (40%)

1c) Student IQ scores have been found to be normally distributed with mean = 100 and standard
deviation, = 15. Find the following percentiles for the distribution of IQ scores.

i) 90th, ii) 20th iii) 14th iv) 60th v) 3rd

(40%)

Q2.

The following contingency table (Table 1) summarises to outcomes of a recent survey on the
popularity of Pokemon Go.

Frequency Plays Pokemon Go Does not play Pokemon Go

Aged 25 and over 500 2500

Under 25 2000 5000

Table 1. Pokemon Go survey results

2a) Calculate the joint, marginal, and conditional probabilities described by Table 1. (30%)

2b) Draw a probability tree of the Pokemon survey results and populate your tree with your calculated
joint, marginal, and conditional probabilities. (30%)

2c) How many unique ways are there to arrange the letters in POKEMON? What is the probability of
the first two letters being OO? What is the probability that an arrangement of all the letters has 2 O’s
next to each other? (40%)

Turn Over
MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460
Q3.

Imagine you are the working on a dangerous construction site where there is a history of a high level of
personal injuries to the employees. You wish to obtain an accurate estimate of whether the
employees are properly obeying the companies health and safety polices and you are willing to spend
up to three months conducting an Activity Sampling study of the construction site in order to assign
some statistical rigour to your findings.

3a) Describe how you would go about designing this Activity Sampling study. Justify any choices made.
(50%)

3b) After you have designed your sampling tour to you start collecting the samples. The results from
your first 150 observations are given below in Table 2. Using the confidence level and desired interval
half width that you specified above determine the:
• Nominal probability
• Upper limit of your confidence interval
• Lower limit of your confidence interval
• Number of samples that needs to be collected in order to achieve your desired
confidence level and interval half-width.
(50%)

High Using phone Safe

No H&S Safety Materials
visibility when Working
Description issues helmet left in
jacket not operating Limit
identified not worn walkways
worn machinery exceeded

Observations 78 9 15 24 18 6

Table 2. 150 observations from an unsafe construction site sampling tour

Q4)

Table 3 shows the numbers of times students visited the gym each week and their weight. Determine

determination, .
the least square error estimate of the regression line from this data and calculate the coefficient of
(100%)

Student x = Weekly gym visits y = Weight

A 6 78
B 4 65
C 0 115
D 3 70
E 5 59
Table 3. Gym visits and weight

Turn Over

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

Q5)

5a) Define the following concepts.

i) Nominal data
ii) Ordinal data
iii) Interval data
iv) Ratio data (40%)

5b) With an illustration, discuss the geometry of a Box Plot. (30%)

5c) Define some of the notation and symbols of set theory. Use examples and an illustration is
necessary. (30%)

6a) Forecast the following time series in Table 4 with the following forecasting methods:

i) an overall average forecast

ii) a moving average forecast with m = 4

iii) an exponential smoothing forecast with α = 0.25. (60%)

Time Demand
0 12
1 20
2 10
3 24
4 9
5 15
6 9
7 14
8 13
9 19
10 20
11 15
Figure 4. Time series data to be forecasted.

6b) Discuss the qualitative differences between exponential smoothing forecasts and moving average
forecasts. (40%)

Turn Over
MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460
Appendix A. The standard normal distribution

z ϕ [ z] Φ [ z] L [ z] z ϕ [ z] Φ [ z] L [ z] z ϕ [ z] Φ [ z] L [ z]

-6 6.07E-09 9.86E-10 6 -1.1 0.217852 0.135666 1.16862 1.15 0.205936 0.874928 0.062104
-5 1.48E-06 2.86E-07 5 -1.05 0.229882 0.146859 1.12568 1.15035 0.205854 0.875 0.06206
-4 0.000134 3.17E-05 4.000007 -1.03643 0.233159 0.15 1.11413 1.2 0.194186 0.88493 0.056102
-3.95 0.000163 3.91E-05 3.950009 -1 0.241971 0.158655 1.083315 1.25 0.182649 0.89435 0.050587
-3.9 0.000199 4.81E-05 3.900011 -0.95 0.254059 0.171056 1.041556 1.28155 0.175498 0.9 0.047343
-3.85 0.000241 5.91E-05 3.850014 -0.93458 0.257775 0.175 1.02881 1.3 0.171369 0.9032 0.045528
-3.8 0.000292 7.23E-05 3.800017 -0.9 0.266085 0.18406 1.000431 1.34076 0.162391 0.91 0.041723
-3.75 0.000353 8.84E-05 3.750021 -0.85 0.277985 0.197663 0.959972 1.35 0.160383 0.911492 0.040898
-3.71902 0.000396 0.0001 3.71904 -0.84162 0.279962 0.2 0.953259 1.4 0.149727 0.919243 0.036668
-3.7 0.000425 0.000108 3.700026 -0.8 0.289692 0.211855 0.920207 1.40507 0.148666 0.92 0.03626
-3.65 0.00051 0.000131 3.650032 -0.75541 0.299913 0.225 0.885359 1.43953 0.141555 0.925 0.033590
-3.6 0.000612 0.000159 3.600039 -0.75 0.301137 0.226627 0.881167 1.45 0.139431 0.926471 0.032813
-3.55 0.000732 0.000193 3.550048 -0.7 0.312254 0.241964 0.842879 1.47579 0.134268 0.93 0.030962
-3.5 0.000873 0.000233 3.500058 -0.67449 0.317777 0.25 0.823644 1.5 0.129518 0.933193 0.029307
-3.45 0.001038 0.00028 3.450071 -0.65 0.322972 0.257846 0.805372 1.55 0.120009 0.939429 0.026124
-3.4 0.001232 0.000337 3.400087 -0.6 0.333225 0.274253 0.768673 1.55477 0.119123 0.94 0.025836
-3.35 0.001459 0.000404 3.350105 -0.59776 0.333672 0.275 0.767048 1.6 0.110921 0.945201 0.023242
-3.3 0.001723 0.000483 3.300127 -0.55 0.342944 0.29116 0.732806 1.64485 0.103136 0.95 0.020893
-3.25 0.002029 0.000577 3.250154 -0.52440 0.347693 0.3 0.714773 1.65 0.102265 0.950529 0.020637
-3.2 0.002384 0.000687 3.200185 -0.5 0.352065 0.308538 0.697797 1.7 0.094049 0.955435 0.018288
-3.15 0.002794 0.000816 3.150223 -0.45376 0.359915 0.325 0.666204 1.75 0.086277 0.959941 0.016174
-3.1 0.003267 0.000968 3.100267 -0.45 0.360527 0.326355 0.663667 1.75069 0.086174 0.96 0.016146
-3.09023 0.003367 0.001 3.09051 -0.43073 0.363599 0.333333 0.650753 1.8 0.07895 0.96407 0.014276
-3.05 0.00381 0.001144 3.05032 -0.4 0.36827 0.344578 0.630439 1.85 0.072065 0.967843 0.012575
-3 0.004432 0.00135 3.000382 -0.35 0.37524 0.363169 0.598131 1.88079 0.068042 0.97 0.011618
-2.95 0.005143 0.001589 2.950455 -0.31863 0.379195 0.375 0.578345 1.9 0.065616 0.971283 0.011054
-2.9 0.005953 0.001866 2.900542 -0.3 0.381388 0.382089 0.566761 1.95 0.059595 0.974412 0.009698
-2.85 0.006873 0.002186 2.850643 -0.25334 0.386343 0.4 0.538351 1.95996 0.058445 0.975 0.009446
-2.8 0.007915 0.002555 2.800761 -0.25 0.386668 0.401294 0.536345 2 0.053991 0.97725 0.008491
-2.75 0.009094 0.00298 2.750899 -0.2 0.391043 0.42074 0.506895 2.05 0.048792 0.979818 0.007418
-2.7 0.010421 0.003467 2.70106 -0.18911 0.391871 0.425 0.500615 2.05375 0.048418 0.98 0.007343
-2.65 0.011912 0.004025 2.651247 -0.15 0.394479 0.440382 0.478422 2.1 0.043984 0.982136 0.006468
-2.6 0.013583 0.004661 2.601464 -0.12566 0.395805 0.45 0.464919 2.15 0.03955 0.984222 0.005628
-2.57583 0.01446 0.005 2.57741 -0.1 0.396953 0.460172 0.450935 2.17009 0.03787 0.985 0.005319
-2.55 0.015449 0.005386 2.551715 -0.06270 0.398159 0.475 0.43108 2.2 0.035475 0.986097 0.004887
-2.5 0.017528 0.00621 2.502004 -0.05 0.398444 0.480061 0.424441 2.25 0.03174 0.987776 0.004235
-2.45 0.019837 0.007143 2.452337 0 0.398942 0.5 0.398942 2.3 0.028327 0.989276 0.003662
-2.4 0.022395 0.008198 2.40272 0.05 0.398444 0.519939 0.374441 2.32635 0.026652 0.99 0.003389
-2.35 0.025218 0.009387 2.353159 0.062706 0.398159 0.525 0.368373 2.35 0.025218 0.990613 0.003159
-2.32635 0.026652 0.01 2.32974 0.1 0.396953 0.539828 0.350935 2.4 0.022395 0.991802 0.00272
-2.3 0.028327 0.010724 2.303662 0.125661 0.395805 0.55 0.339257 2.45 0.019837 0.992857 0.002337
-2.25 0.03174 0.012224 2.254235 0.15 0.394479 0.559618 0.328422 2.5 0.017528 0.99379 0.002004
-2.2 0.035475 0.013903 2.204887 0.189118 0.391871 0.575 0.311496 2.55 0.015449 0.994614 0.001715
-2.17009 0.03787 0.015 2.17541 0.2 0.391043 0.57926 0.306895 2.57583 0.01446 0.995 0.001581
-2.15 0.03955 0.015778 2.155628 0.25 0.386668 0.598706 0.286345 2.6 0.013583 0.995339 0.001464
-2.1 0.043984 0.017864 2.106468 0.253347 0.386343 0.6 0.285004 2.65 0.011912 0.995975 0.001247
-2.05375 0.048418 0.02 2.06109 0.3 0.381388 0.617911 0.266761 2.7 0.010421 0.996533 0.00106
-2.05 0.048792 0.020182 2.057418 0.318639 0.379195 0.625 0.259705 2.75 0.009094 0.99702 0.000899
-2 0.053991 0.02275 2.008491 0.35 0.37524 0.636831 0.248131 2.8 0.007915 0.997445 0.000761
-1.95996 0.058445 0.025 1.96941 0.38532 0.370399 0.65 0.235537 2.85 0.006873 0.997814 0.000643
-1.95 0.059595 0.025588 1.959698 0.4 0.36827 0.655422 0.230439 2.9 0.005953 0.998134 0.000542
-1.9 0.065616 0.028717 1.911054 0.43073 0.363599 0.666666 0.220023 2.95 0.005143 0.998411 0.000455
-1.88079 0.068042 0.03 1.89241 0.447214 0.360978 0.67264 0.214578 3 0.004432 0.99865 0.000382
-1.85 0.072065 0.032157 1.862575 0.45 0.360527 0.673645 0.213667 3.05 0.00381 0.998856 0.00032
-1.8 0.07895 0.03593 1.814276 0.453762 0.359915 0.675 0.212442 3.09023 0.003367 0.999 0.000277
-1.75069 0.086174 0.04 1.76683 0.5 0.352065 0.691462 0.197797 3.1 0.003267 0.999032 0.000267
-1.75 0.086277 0.040059 1.766174 0.524401 0.347693 0.7 0.190372 3.15 0.002794 0.999184 0.000223
-1.7 0.094049 0.044565 1.718288 0.55 0.342944 0.70884 0.182806 3.2 0.002384 0.999313 0.000185
-1.65 0.102265 0.049471 1.670637 0.57735 0.337697 0.718149 0.17497 3.25 0.002029 0.999423 0.000154
-1.64485 0.103136 0.05 1.66575 0.59776 0.333672 0.725 0.169288 3.3 0.001723 0.999517 0.000127
-1.6 0.110921 0.054799 1.623242 0.6 0.333225 0.725747 0.168673 3.35 0.001459 0.999596 0.000105
-1.55477 0.119123 0.06 1.58061 0.65 0.322972 0.742154 0.155372 3.4 0.001232 0.999663 8.67E-05
-1.55 0.120009 0.060571 1.576124 0.67449 0.317777 0.75 0.149154 3.45 0.001038 0.99972 7.13E-05
-1.5 0.129518 0.066807 1.529307 0.7 0.312254 0.758036 0.142879 3.5 0.000873 0.999767 5.85E-05
-1.47579 0.134268 0.07 1.50675 0.707106 0.310697 0.76025 0.141168 3.55 0.000732 0.999807 4.79E-05
-1.45 0.139431 0.073529 1.482813 0.75 0.301137 0.773373 0.131167 3.6 0.000612 0.999841 3.91E-05
-1.43953 0.141555 0.075 1.47312 0.755415 0.299913 0.775 0.129944 3.65 0.00051 0.999869 3.19E-05
-1.40507 0.148666 0.08 1.44133 0.8 0.289692 0.788145 0.120207 3.7 0.000425 0.999892 2.59E-05
-1.4 0.149727 0.080757 1.436668 0.841621 0.279962 0.8 0.111638 3.71902 0.000396 0.9999 2.39E-05
-1.35 0.160383 0.088508 1.390898 0.85 0.277985 0.802337 0.109972 3.75 0.000353 0.999912 2.1E-05
-1.34076 0.162391 0.09 1.38248 0.9 0.266085 0.81594 0.100431 3.8 0.000292 0.999928 1.7E-05
-1.3 0.171369 0.0968 1.345528 0.934589 0.257775 0.825 0.094222 3.85 0.000241 0.999941 1.37E-05
-1.28155 0.175498 0.1 1.32889 0.95 0.254059 0.828944 0.091556 3.9 0.000199 0.999952 1.11E-05
-1.25 0.182649 0.10565 1.300587 1 0.241971 0.841345 0.083315 3.95 0.000163 0.999961 8.91E-06
-1.2 0.194186 0.11507 1.256102 1.03643 0.233159 0.85 0.077694 4 0.000134 0.999968 7.15E-06
-1.15035 0.205854 0.125 1.21241 1.05 0.229882 0.853141 0.07568 5 1.48E-06 1-(2.86E-07) 5.34E-08
-1.15 0.205936 0.125072 1.212104 1.1 0.217852 0.864334 0.06862 6 6.07E-09 1-(9.86E-10) 1.56E-10
End of paper.

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

Appendix B. Clopper-Pearson confidence intervals

n=50 pL = y ( pU =1− y) pU = y ( pL =1− y) n=150 pL = y ( pU =1− y) pU = y ( pL =1− y)

x 99% 95% 90% 90% 95% 99% x 99% 95% 90% 90% 95% 99%
0 (50) y=0 0 0 0.058155079 0.071121736 0.100545083 0 (150) y=0 0 0 0.019773438 0.024292597 0.03470557
1 (49) 0.000100246 0.000506228 0.00102534 0.091398131 0.106469546 0.139404125 1 (149) 3.34164E-05 0.000168771 0.000341897 0.031233817 0.036583168 0.048485953
2 (48) 0.002088725 0.004881433 0.00715372 0.120614155 0.137137626 0.17250176 2 (148) 0.000692036 0.001618827 0.002374192 0.04137497 0.047333019 0.060345774
3 (47) 0.006872485 0.012548588 0.016551859 0.147837176 0.165481947 0.202706269 3 (147) 0.002265007 0.004143625 0.00547293 0.050877068 0.057334222 0.071262464
4 (46) 0.013768445 0.022227964 0.027787668 0.173791158 0.192342784 0.23105085 4 (146) 0.004516558 0.007312546 0.009158928 0.05998104 0.066867877 0.081586214
5 (45) 0.022217815 0.033275094 0.04023659 0.198833003 0.218135366 0.258049729 5 (145) 0.007257229 0.010910186 0.013224408 0.068805184 0.076072323 0.091490565
6 (44) 0.031862914 0.045335321 0.053571403 0.22316999 0.243101317 0.284003704 6 (144) 0.010366487 0.014818521 0.017560962 0.077417997 0.085027815 0.101076706
7 (43) 0.042468787 0.0581917 0.067596699 0.246935202 0.267396002 0.309106966 7 (143) 0.013765426 0.01896557 0.02210405 0.08586338 0.093785865 0.110409837
8 (42) 0.053873602 0.071700767 0.082185062 0.270220078 0.291126307 0.333493522 8 (142) 0.017399794 0.02330381 0.026811658 0.094171482 0.102381896 0.119534935
9 (41) 0.065961072 0.085762078 0.097248095 0.293090581 0.314369411 0.357260386 9 (141) 0.021230608 0.027799978 0.031654647 0.102364084 0.11084152 0.128484599
10 (40) 0.078644691 0.100302237 0.112721613 0.315596061 0.337183108 0.380480351 10 (140) 0.025228817 0.032429728 0.036611832 0.110457532 0.119183977 0.137283372
11 (39) 0.091858295 0.115265826 0.128557379 0.337774485 0.359611889 0.403209554 11 (139) 0.029372118 0.037174615 0.041667235 0.118464471 0.127424162 0.145950285
12 (38) 0.105550132 0.130609916 0.144718155 0.359655697 0.381690748 0.425492219 12 (138) 0.033642958 0.042020265 0.046808451 0.126394927 0.13557389 0.154500458
13 (37) 0.119679002 0.146300584 0.161174597 0.381263556 0.403447679 0.447363763 13 (137) 0.038027232 0.04695522 0.052025622 0.134257008 0.143642723 0.162946142
14 (36) 0.134211639 0.162310601 0.177903198 0.402617382 0.424905357 0.468852912 14 (136) 0.04251341 0.051970172 0.057310755 0.142057385 0.151638531 0.171297434
15 (35) 0.149120897 0.178617846 0.194884897 0.423732967 0.446082326 0.48998318 15 (135) 0.047091922 0.057057435 0.062657265 0.149801626 0.159567885 0.17956277
16 (34) 0.164384449 0.195204195 0.212104098 0.444623296 0.46699384 0.510773932 16 (134) 0.051754723 0.062210574 0.068059646 0.157494434 0.167436339 0.18774929
17 (33) 0.179983844 0.212054713 0.229547962 0.465299081 0.487652488 0.531241159 17 (133) 0.056494972 0.06742414 0.073513243 0.165139829 0.175248639 0.195863098
18 (32) 0.195903809 0.229157067 0.247205894 0.485769151 0.508068648 0.551398063 18 (132) 0.061306798 0.072693467 0.079014074 0.172741273 0.183008877 0.203909461
19 (31) 0.21213172 0.246501078 0.265069158 0.506040748 0.528250837 0.571255486 19 (131) 0.066185114 0.078014525 0.084558705 0.18030178 0.190720614 0.211892966
20 (30) 0.228657206 0.264078395 0.283130591 0.526119749 0.548205972 0.590822246 20 (130) 0.071125481 0.083383807 0.090144145 0.187823988 0.198386968 0.219817631
21 (29) 0.245471848 0.281882241 0.301384377 0.546010837 0.567939565 0.610105383 21 (129) 0.076123996 0.088798232 0.095767775 0.195310223 0.206010689 0.227687004
22 (28) 0.262568945 0.299907221 0.319825889 0.565717627 0.587455877 0.629110348 22 (128) 0.081177208 0.094255085 0.101427285 0.20276255 0.213594219 0.235504232
23 (27) 0.279943342 0.318149179 0.338451559 0.585242759 0.606758024 0.647841147 23 (127) 0.086282047 0.099751951 0.107120622 0.210182807 0.221139733 0.243272126
24 (26) 0.297591302 0.336605092 0.35725879 0.604587965 0.625848055 0.666300434 24 (126) 0.09143577 0.105286678 0.112845957 0.217572646 0.228649184 0.250993204
25 0.315510421 0.355272997 0.376245891 0.623754109 0.644727003 0.684489579 25 (125) 0.096635913 0.110857332 0.118601649 0.22493355 0.236124327 0.258669737
26 (124) 0.101880252 0.116462173 0.12438622 0.232266861 0.24356675 0.266303776
n=100 pL = y ( pU =1− y) pU = y ( pL =1− y) 27 (123) 0.107166776 0.122099628 0.130198336 0.239573797 0.250977895 0.273897184

x 99% 95% 90% 90% 95% 99% 28 (122) 0.112493654 0.127768266 0.136036784 0.246855466 0.258359073 0.281451656
0 (100) y=0 0 0 0.02951305 0.036216693 0.05160403 29 (121) 0.117859222 0.133466786 0.14190046 0.25411288 0.265711481 0.288968742
1 (99) 5.01242E-05 0.000253146 0.000512801 0.046559811 0.054459385 0.071957682 30 (120) 0.123261954 0.139193999 0.147788357 0.261346965 0.273036218 0.296449862
2 (98) 0.001039619 0.002431337 0.003565153 0.0616192 0.070383932 0.089430673 31 (119) 0.128700453 0.144948816 0.153699551 0.268558571 0.280334289 0.303896318
3 (97) 0.00340707 0.006229972 0.008225829 0.075710794 0.085176053 0.105481254 32 (118) 0.134173435 0.150730237 0.159633196 0.275748483 0.287606623 0.311309311
4 (96) 0.006801694 0.011004494 0.013776612 0.08919625 0.099257157 0.120632699 33 (117) 0.139679717 0.156537338 0.16558851 0.282917421 0.294854074 0.318689949
5 (95) 0.010940334 0.016431879 0.019905564 0.102253378 0.112834911 0.135144683 34 (116) 0.145218205 0.162369272 0.171564774 0.290066054 0.302077433 0.326039255
6 (94) 0.015642513 0.022334886 0.026449713 0.114985256 0.126029935 0.149168804 35 (115) 0.15078789 0.168225251 0.177561322 0.297195 0.309277432 0.333358178
7 (93) 0.02078993 0.028605289 0.033311916 0.127458016 0.138919728 0.162802856 36 (114) 0.156387835 0.174104547 0.183577538 0.304304832 0.316454751 0.340647598
8 (92) 0.026301152 0.035171563 0.040428871 0.139717119 0.151557636 0.176114355 37 (113) 0.16201717 0.180006485 0.189612851 0.311396082 0.32361002 0.347908333
9 (91) 0.032117617 0.041983596 0.047756636 0.151795429 0.163982255 0.18915228 38 (112) 0.167675086 0.185930437 0.195666728 0.318469248 0.330743828 0.355141143
10 (90) 0.038195653 0.049004689 0.055263238 0.163717623 0.176222598 0.201953521 39 (111) 0.173360831 0.191875818 0.201738676 0.325524789 0.337856721 0.362346739
11 (89) 0.044501714 0.05620702 0.06292455 0.175502803 0.188301132 0.214546698 40 (110) 0.179073703 0.197842083 0.207828234 0.332563138 0.344949209 0.369525782
12 (88) 0.051009388 0.063568903 0.070721838 0.18716611 0.200235684 0.226954552 41 (109) 0.184813047 0.203828725 0.213934972 0.339584697 0.352021771 0.37667889
13 (87) 0.057697454 0.071073046 0.078640204 0.198719793 0.212040677 0.239195508 42 (108) 0.190578251 0.209835269 0.220058489 0.346589841 0.35907485 0.383806642
14 (86) 0.064548563 0.078705405 0.086667578 0.210173925 0.223727981 0.251284745 43 (107) 0.196368742 0.215861271 0.226198409 0.353578923 0.366108864 0.390909577
15 (85) 0.071548325 0.086454386 0.094794012 0.221536908 0.2353075 0.26323494 44 (106) 0.202183986 0.221906316 0.232354382 0.36055227 0.373124204 0.397988202
16 (84) 0.078684647 0.09431029 0.1030112 0.232815835 0.246787597 0.275056809 45 (105) 0.208023481 0.227970016 0.23852608 0.367510193 0.380121234 0.405042991
17 (83) 0.08594726 0.10226491 0.11131212 0.244016756 0.258175411 0.286759506 46 (104) 0.213886757 0.234052006 0.244713194 0.37445298 0.387100297 0.412074389
18 (82) 0.093327359 0.110311229 0.119690778 0.255144881 0.269477086 0.298350915 47 (103) 0.219773374 0.240151946 0.250915436 0.3813809 0.394061714 0.419082811
19 (81) 0.10081733 0.118443196 0.128142008 0.266204729 0.280697958 0.309837888 48 (102) 0.225682918 0.246269516 0.257132537 0.38829421 0.401005786 0.426068649
20 (80) 0.108410541 0.126655552 0.136661325 0.27720025 0.291842689 0.321226413 49 (101) 0.231615003 0.252404415 0.263364242 0.395193146 0.407932795 0.433032269
21 (79) 0.116101179 0.134943696 0.145244808 0.288134916 0.302915379 0.332521761 50 (100) 0.237569265 0.258556363 0.269610314 0.402077931 0.414843006 0.439974014
22 (78) 0.123884115 0.143303577 0.153889007 0.299011796 0.313919654 0.343728594 51 (99) 0.243545363 0.264725097 0.275870531 0.408948776 0.421736667 0.446894207
23 (77) 0.131754807 0.151731611 0.162590871 0.309833617 0.324858733 0.354851056 52 (98) 0.249542979 0.270910368 0.282144683 0.415805876 0.428614011 0.453793149
24 (76) 0.139709209 0.160224613 0.171347691 0.320602811 0.335735489 0.365892843 53 (97) 0.255561812 0.277111945 0.288432575 0.422649414 0.435475255 0.460671123
25 (75) 0.147743708 0.168779738 0.180157047 0.331321554 0.346552496 0.37685727 54 (96) 0.261601583 0.283329612 0.294734024 0.429479563 0.442320603 0.467528394
26 (74) 0.15585506 0.177394438 0.189016773 0.341991802 0.357312063 0.387747312 55 (95) 0.267662029 0.289563165 0.301048858 0.436296482 0.449150245 0.474365209
27 (73) 0.164040349 0.186066422 0.197924924 0.352615316 0.368016273 0.398565651 56 (94) 0.273742905 0.295812415 0.307376916 0.443100324 0.455964359 0.481181799
28 (72) 0.172296944 0.194793627 0.206879746 0.363193686 0.378667005 0.40931471 57 (93) 0.279843981 0.302077184 0.31371805 0.449891226 0.462763112 0.487978379
29 (71) 0.180622466 0.203574189 0.215879657 0.373728351 0.389265959 0.419996682 58 (92) 0.285965043 0.308357307 0.320072119 0.456669319 0.469546658 0.494755152
30 (70) 0.189014762 0.21240642 0.224923224 0.384220613 0.399814676 0.430613554 59 (91) 0.292105893 0.31465263 0.326438993 0.463434726 0.47631514 0.501512302
31 (69) 0.197471878 0.221288792 0.23400915 0.394671654 0.410314554 0.441167127 60 (90) 0.298266345 0.32096301 0.332818551 0.470187557 0.483068692 0.508250004
32 (68) 0.205992042 0.230219917 0.243136257 0.405082547 0.420766862 0.45165904 61 (89) 0.304446228 0.327288314 0.339210683 0.476927916 0.489807436 0.514968417
33 (67) 0.214573641 0.239198535 0.252303477 0.415454267 0.431172751 0.46209078 62 (88) 0.310645384 0.33362842 0.345615283 0.4836559 0.496531487 0.521667688
34 (66) 0.223215213 0.248223502 0.261509839 0.425787697 0.441533268 0.472463697 63 (87) 0.316863666 0.339983214 0.352032256 0.490371595 0.503240947 0.528347952
35 (65) 0.231915427 0.257293779 0.270754462 0.436083641 0.451849362 0.482779016 64 (86) 0.323100942 0.346352595 0.358461516 0.497075081 0.509935912 0.535009334
36 (64) 0.240673076 0.266408423 0.280036546 0.446342825 0.462121893 0.49303785 65 (85) 0.329357088 0.352736466 0.364902983 0.503766432 0.516616468 0.541651944
37 (63) 0.249487067 0.27556658 0.289355367 0.456565907 0.472351641 0.503241203 66 (84) 0.335631994 0.359134742 0.371356583 0.510445713 0.523282692 0.548275884
38 (62) 0.258356408 0.284767476 0.29871027 0.46675348 0.482539306 0.513389984 67 (83) 0.34192556 0.365547347 0.377822252 0.517112981 0.529934654 0.554881244
39 (61) 0.267280206 0.294010415 0.308100663 0.476906079 0.49268552 0.523485007 68 (82) 0.348237698 0.371974211 0.384299933 0.523768288 0.536572414 0.561468103
40 (60) 0.276257658 0.303294769 0.317526015 0.48702418 0.50279085 0.533527004 69 (81) 0.354568328 0.378415274 0.390789572 0.53041168 0.543196027 0.568036531
41 (59) 0.285288045 0.312619977 0.32698585 0.497108208 0.512855796 0.543516626 70 (80) 0.360917384 0.384870482 0.397291127 0.537043194 0.549805536 0.574586586
42 (58) 0.294370727 0.321985539 0.336479745 0.507158539 0.522880804 0.553454447 71 (79) 0.367284806 0.391339792 0.403804559 0.543662861 0.55640098 0.581118318
43 (57) 0.30350514 0.331391017 0.346007327 0.5171755 0.532866262 0.563340969 72 (78) 0.373670547 0.397823166 0.410329836 0.550270708 0.562982389 0.587631766
44 (56) 0.312690792 0.340836024 0.355568269 0.527159374 0.542812503 0.573176625 73 (77) 0.380074569 0.404320573 0.416866933 0.556866752 0.569549785 0.594126959
45 (55) 0.321927257 0.350320229 0.36516229 0.537110399 0.552719811 0.582961783 74 (76) 0.386496843 0.410831993 0.423415833 0.563451007 0.576103182 0.600603916
46 (54) 0.331214178 0.359843353 0.374789154 0.547028772 0.56258842 0.592696745 75 0.392937351 0.41735741 0.429976521 0.570023479 0.58264259 0.607062649
47 (53) 0.34055126 0.369405164 0.384448663 0.55691465 0.572418515 0.602381754 .
48 (52) 0.349938269 0.37900548 0.394140663 0.56676815 0.582210235 0.612016989
49 (51) 0.359375032 0.388644165 0.403865039 0.576589349 0.591963671 0.621602571
50 0.368861437 0.39832113 0.413621715 0.586378285 0.60167887 0.631138563

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

 Appendix C: Clopper-Pearson sample size requirements

90% Confidence 95% Confidence 99% Confidence

p or L p or L p or L
(1-p) 0.1 0.09 0.08 0.07 0.06 0.05 0.04 0.03 0.02 0.01 (1-p) 0.1 0.09 0.08 0.07 0.06 0.05 0.04 0.03 0.02 0.01 (1-p) 0.1 0.09 0.08 0.07 0.06 0.05 0.04 0.03 0.02 0.01
0 29 32 36 42 49 59 74 99 149 299 0 36 40 45 51 60 72 91 122 183 368 0 51 57 64 74 86 104 130 174 263 528
0.01 31 35 40 47 56 69 90 128 216 569 0.01 39 44 50 59 70 87 114 164 279 753 0.01 57 65 74 87 104 131 172 250 433 1204
0.02 34 38 44 52 63 79 106 157 280 829 0.02 42 48 56 66 80 102 137 204 371 1124 0.02 63 72 84 99 122 156 212 321 593 1844
0.03 36 41 48 57 69 89 121 184 343 1083 0.03 45 52 61 73 90 115 159 244 461 1484 0.03 69 79 93 112 138 180 250 389 748 2468
0.04 38 44 51 61 76 98 136 211 405 1332 0.04 49 56 66 79 99 129 180 282 548 1837 0.04 74 86 102 123 155 203 287 455 898 3077
0.05 40 46 54 66 82 107 151 237 464 1574 0.05 52 60 71 86 108 142 201 319 632 2181 0.05 80 93 110 135 170 226 323 520 1045 3672
0.06 42 49 58 70 88 116 165 263 523 1811 0.06 55 63 75 92 116 155 221 356 715 2517 0.06 85 99 118 145 185 248 358 583 1189 4254
0.07 44 51 61 74 94 125 179 288 579 2042 0.07 57 67 80 98 125 167 240 391 796 2846 0.07 90 105 126 156 200 270 392 644 1329 4822
0.08 46 54 64 78 100 133 192 312 635 2268 0.08 60 70 84 104 133 179 260 425 875 3167 0.08 94 111 134 166 214 290 425 704 1465 5377
0.09 48 56 67 83 105 142 205 336 689 2488 0.09 63 74 89 110 141 191 278 459 952 3480 0.09 99 117 142 176 228 311 457 762 1598 5919
0.1 50 58 70 86 111 150 218 359 742 2704 0.1 65 77 93 115 149 202 296 492 1027 3786 0.1 104 123 149 186 242 330 489 819 1728 6447
0.11 51 60 73 90 116 157 230 381 793 2913 0.11 68 80 97 121 156 213 314 524 1100 4084 0.11 108 128 156 196 255 350 519 874 1855 6962
0.12 53 63 76 94 121 165 242 403 843 3117 0.12 70 83 101 126 164 224 331 555 1171 4374 0.12 112 134 163 205 267 368 549 928 1978 7463
0.13 55 65 78 97 126 172 254 424 892 3316 0.13 73 86 105 131 171 234 348 585 1241 4656 0.13 116 139 170 214 280 386 578 980 2098 7952
0.14 56 67 81 101 131 179 265 445 939 3509 0.14 75 89 108 136 177 244 364 614 1308 4931 0.14 120 144 176 222 292 404 606 1031 2214 8427
0.15 58 69 83 104 136 186 276 465 985 3697 0.15 77 92 112 141 184 254 379 643 1373 5198 0.15 124 149 182 231 303 421 633 1080 2327 8888
0.16 59 70 86 107 140 193 287 484 1030 3880 0.16 79 94 116 145 191 264 395 670 1437 5457 0.16 128 153 188 239 314 437 659 1128 2437 9337
0.17 61 72 88 111 144 199 297 503 1073 4057 0.17 81 97 119 150 197 273 409 697 1498 5709 0.17 131 158 194 246 325 453 685 1174 2543 9772
0.18 62 74 90 114 149 205 307 521 1115 4228 0.18 83 99 122 154 203 282 423 723 1558 5953 0.18 135 162 200 254 336 469 709 1219 2647 10194
0.19 63 76 92 116 153 211 317 538 1155 4394 0.19 85 102 125 158 209 290 437 748 1615 6189 0.19 138 166 205 261 346 484 733 1262 2746 10602
0.2 64 77 94 119 157 217 326 555 1194 4555 0.2 87 104 128 162 214 298 450 772 1671 6418 0.2 141 170 210 268 355 498 756 1304 2843 10998
0.21 66 79 96 122 160 223 335 572 1232 4711 0.21 88 106 131 166 219 306 463 795 1725 6639 0.21 144 174 215 275 365 512 778 1345 2936 11380
0.22 67 80 98 124 164 228 343 587 1269 4861 0.22 90 108 134 170 225 314 475 818 1777 6852 0.22 147 178 220 281 374 525 800 1384 3026 11748
0.23 68 81 100 127 167 233 352 602 1304 5005 0.23 92 110 136 173 230 321 487 839 1827 7057 0.23 150 181 225 287 382 538 820 1421 3112 12104
0.24 69 83 102 129 171 238 360 617 1338 5144 0.24 93 112 139 177 234 328 498 860 1875 7255 0.24 152 185 229 293 391 550 840 1457 3196 12446
0.25 70 84 103 131 174 243 367 631 1370 5278 0.25 94 114 141 180 239 335 509 880 1921 7445 0.25 155 188 233 299 398 562 858 1491 3275 12774
0.26 71 85 105 134 177 247 374 644 1401 5406 0.26 96 116 143 183 243 341 520 899 1965 7628 0.26 157 191 237 304 406 573 876 1524 3352 13090
0.27 72 86 106 136 180 251 381 657 1431 5529 0.27 97 117 145 186 247 347 529 917 2007 7802 0.27 159 193 241 309 413 583 894 1556 3425 13392
0.28 72 87 108 137 182 255 388 669 1459 5647 0.28 98 119 147 188 251 353 539 934 2048 7970 0.28 161 196 244 314 420 593 910 1586 3495 13682
0.29 73 88 109 139 185 259 394 681 1486 5759 0.29 99 120 149 191 255 359 548 951 2086 8129 0.29 163 199 247 318 426 603 925 1614 3562 13957
0.3 74 89 110 141 187 263 400 691 1511 5865 0.3 100 121 151 193 258 364 556 966 2123 8281 0.3 165 201 251 322 432 612 940 1641 3625 14220
0.31 74 90 111 142 189 266 405 702 1536 5967 0.31 101 123 153 196 261 369 564 981 2157 8425 0.31 167 203 253 326 438 620 954 1667 3685 14469
0.32 75 91 112 144 191 269 411 711 1559 6063 0.32 102 124 154 198 264 373 571 995 2190 8561 0.32 168 205 256 330 443 628 967 1691 3742 14705
0.33 75 91 113 145 193 272 415 721 1580 6153 0.33 103 125 155 200 267 377 578 1008 2220 8690 0.33 169 207 259 333 448 636 979 1714 3795 14928
0.34 76 92 114 146 195 275 420 729 1600 6238 0.34 103 126 157 201 269 381 585 1020 2249 8811 0.34 171 208 261 336 452 643 990 1735 3845 15138
0.35 76 93 115 147 197 277 424 737 1619 6318 0.35 104 127 158 203 272 385 591 1031 2276 8924 0.35 172 210 263 339 456 649 1001 1755 3891 15334
0.36 77 93 116 148 198 280 428 744 1637 6392 0.36 105 127 159 204 274 388 596 1042 2301 9030 0.36 173 211 265 342 460 655 1010 1773 3935 15517
0.37 77 94 116 149 199 282 431 751 1653 6460 0.37 105 128 160 206 276 391 601 1051 2324 9128 0.37 174 212 266 344 463 660 1019 1790 3975 15686
0.38 77 94 117 150 201 284 435 757 1668 6524 0.38 105 128 160 207 278 394 606 1060 2345 9218 0.38 174 213 268 346 467 665 1027 1805 4012 15842
0.39 77 94 117 151 202 285 437 763 1681 6582 0.39 106 129 161 208 279 396 610 1068 2364 9300 0.39 175 214 269 348 469 669 1034 1819 4045 15986
0.4 78 94 118 151 203 287 440 767 1693 6634 0.4 106 129 162 209 280 398 614 1075 2382 9375 0.4 175 215 270 349 471 673 1041 1831 4075 16115
0.41 78 95 118 152 203 288 442 772 1704 6682 0.41 106 130 162 209 281 400 617 1081 2397 9442 0.41 176 215 271 351 473 676 1046 1842 4102 16232
0.42 78 95 118 152 204 289 444 775 1713 6723 0.42 106 130 162 210 282 401 619 1086 2410 9502 0.42 176 216 271 352 475 678 1051 1851 4125 16335
0.43 78 95 118 152 204 290 445 778 1721 6760 0.43 106 130 163 210 283 403 621 1091 2422 9554 0.43 176 216 271 352 476 680 1055 1859 4145 16425
0.44 78 95 118 152 204 290 446 781 1728 6790 0.44 106 130 163 210 283 403 623 1094 2432 9598 0.44 176 216 272 353 477 682 1058 1865 4162 16502
0.45 77 94 118 152 205 290 447 783 1733 6816 0.45 106 130 163 210 283 404 624 1097 2439 9634 0.45 176 216 272 353 477 683 1060 1870 4176 16566
0.46 77 94 118 152 205 291 448 784 1737 6836 0.46 106 129 162 210 283 404 625 1099 2445 9663 0.46 175 215 271 353 477 683 1061 1874 4186 16616
0.47 77 94 118 152 204 290 448 785 1740 6851 0.47 105 129 162 210 283 404 625 1100 2449 9684 0.47 175 215 271 352 477 683 1062 1876 4193 16653
0.48 77 94 117 152 204 290 447 785 1741 6860 0.48 105 129 162 209 283 404 625 1100 2451 9698 0.48 174 214 270 351 476 683 1061 1876 4196 16677
0.49 76 93 117 151 203 290 447 784 1741 6864 0.49 104 128 161 209 282 403 624 1100 2451 9703 0.49 173 213 269 351 475 682 1060 1875 4196 16687
0.5 76 93 116 151 203 289 446 783 1739 6862 0.5 104 127 160 208 281 402 623 1098 2449 9701 0.5 172 212 268 349 474 680 1058 1873 4193 16684

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

Standard answers

Question 2

2a)

Plays Pokemon Does not play

Go Pokemon Go
Aged 25 and over 500 2500 3000
Under 25 2000 5000 7000
2500 7500 10000

Plays Pokemon Does not play

Probabilities
Go Pokemon Go
Aged 25 and over 0.05 0.25 0.3
Under 25 0.2 0.5 0.7
0.25 0.75 1
Red Joint Probabilities Blue Marginal Probabilities

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

 Conditional probabilities
P(A|B) = 0.2
P(A'|B) = 0.8
P(B|A)= 0.166666667
P(B'|A)= 0.833333333
P(A|B') = 0.333333333
P(A'|B') = 0.666666667
P(B|A')= 0.285714286
P(B'|A')= 0.714285714

2b)

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

2c)

• 2ci) There are seven letters in POKEMON. The important letter is O which appears
twice and reduces the total number of combinations possible by a factor of 2!=2
(7!/2!)= 2520.
• 2cii) The only way this is possible if the 1st letter is O and second letter is also O,
(2/7)(1/6)=1/21= 0.04761.
• 2ciii) If we assume that an “OO” is one single letter there are 6! ways of ordering the
“six” letters. We know that total number of unique combinations is 7!/2! from the first
part of this question. Bringing these together we have 6!/(7!/2!)=2/7=0.285714.
Another way to do this is with the following sum;

⎛ 5− −1 2 1 ⎞ 2
⎜ × × = = 0.285714
7− −1 7− 6− ⎟ 7
⎝ ⎠

Q3

3a) This is a safety critical scenario, the purpose of the Activity Sampling study is to collect an
“accurate estimate” of whether the employees are obeying company health and safety rules. Thus,
we should specify quite a high level of confidence (say 99%, thus α = 0.01 ) and a small interval half-
width (say L = 0.05). This would require perhaps 700 observations over the study of 3 months. As for
a sampling strategy, I would suggest that random sampling strategy should be used as people are
the subjects. Thinking about the context of the study, I would also try to conduct the study without
telling the employees what I was doing as they might change their behaviour and make a special
effort to obey the safety rules. This approach would be facilitated by the fact that an H&S breach
would probably be quite easy to spot. When I made the observations I would conduct a small tour of
the site and mentally note the “first” H&S issue that I spotted to record on my sampling form, any
further H&S violations on that observation tour would be ignored. If no H&S violations where
spotted I would record “No H&S issues identified” when I returned to my office. Implicitly here I am
assuming that there is no structural “systematic” effect in the first observation that I spot.

3b) The summary statistics given by the Activity Sampling procedure for α = 0.01 and L = 0.05 are
given in the Table below.

High Using phone Safe

No H&S Safety Materials
visibility when Working
Description issues helmet left in
jacket not operating Limit
identified not worn walkways
worn machinery exceeded

Observations 78 9 15 24 18 6

p̂ 0.52 0.06 0.1 0.16 0.12 0.04

pU 0.6264 0.12848 0.17956 0.25099 0.203909 0.101076

pL 0.41237 0.02123 0.04709 0.09143 0.0613 0.010366

N 683 248 330 437 368 203

Summary Activity Sampling results after the first 150 samples

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

4)

+
MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460
5a

i) Nominal-scaled data indicate into which category a data element should be placed or
labels
• For example, country, gender, race, hair colour

ii) Ordinal-scaled data have all the properties of nominal scaled data but in addition have the
quality that the order is meaningful (Rank)

• For example, numbers represent greater than or less than, position or rank (1st, 2nd,
3rd, …), Likert scale

Nominal and ordinal scaled data are examples of qualitative data.

iii) Interval-scaled data express intervals between values in terms of fixed units of
measurement
• For example, +2oC is one degree warmer than +1oC
iv) Ratio-scaled data have the properties of interval-scaled data plus the quality that zero
indicates the absence of whatever is being measured
• For example, 50 kilometres is twice the distance of 25 kilometres

Interval and ratio scaled data are examples of quantitative data. Items can represented in terms of
how many or how much. Data items can be characterized by a metric rather than a nominal.

5b Something like the following figure should be presented and discussed.

5c) Set theory symbols

Let A and B be sets. Sets contain zero or more elements.

A∈ B A is a member of the set B

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460
A∉ B A is not a member of the set B
A⊂ B A is a proper subset of B. A is a subset of B, but A is not equal to B (i.e. there
exists at least one element of B not contained in A).
A⊆ B A is a subset of B. Every element of A is also an element of B. This means that
any set is a subset of itself, but not a proper subset.
A⊄ B A is not a subset of B
A=∅ A is an empty set, a set with no elements
A∩ B The intersection of A and B all the elements that are in both A and B
A∪ B The union of A and B. All the elements of A and B combined, but with no
elements repeated
A The compliment of A. All the elements not in A
A− B All the elements in A but not in B
n ( A) The number of elements in A
A=B A is equal to B. A and B both contain the same elements
A≅ B A is equivalent to B. A and B both contain the same number of elements

Examples.

Let the universal set U = {0,1,2,3,4,5,6,7,8,9}, set A = {0, 2, 4, 6,8} and set B = {0,1, 2,3, 4} . The
following Venn diagram illustrates this scenario and all of the following statements are true.

Figure Error! No text of specified style in document..1. Venn diagram to illustrate set theory notation

0∈ A 0 is a member of A.
1∈ B 1 is a member of B.
1∉ A 1 is not a member of A.
A⊂U A is a subset of U.
A⊄ B A is not a subset of B.
A≅ B A is equivalent to B, both have the same number of elements.
n ( A) = 5 A has 5 elements.
A≠ B A is not equal to B, some of the elements are different.
A − B = {6,8} All the elements in A, but not in B.
A ∩ B = {0, 2, 4} The intersection of A and B; all the elements that are in both A
and B.
MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460
A ∪ B = {0,1, 2,3, 4, 6,8} The union of A and B; a list of all the element in A and B, but
with nothing repeated.

6a i, ii, and iii)

Overall
Time Demand average Moving average Exponential smoothing
0 12 12 12 12
1 20 16 16 14
2 10 14 14 13
3 24 16.5 16.5 15.75
4 9 15 15.75 14.0625
5 15 15 14.5 14.29688
6 9 14.14285714 14.25 12.97266
7 14 14.125 11.75 13.22949
8 13 14 12.75 13.17212
9 19 14.5 13.75 14.62909
10 20 15 16.5 15.97182
11 15 15 16.75 15.72886

6b)

The major advantage of the moving average forecast is that it is conceptually very easy to
understand and thus is a relatively popular forecasting technique in practice. However, it requires a
lot of data storage. For example, a “n period” moving average forecast requires the storage of n
data points in a computer file. If any of those data points is missing or corrupt then the forecast can
not be generated. Furthermore, if you wish to change your forecast from a “n period” moving
average forecast to a “n+x period” moving average, you need x new data points. Are they available?
Well actually, in many practical situations it is just not possible to retain all the information that may
be required. Thus, it is relatively difficult to change the dynamic response of a moving average
forecast.

In the extremes of n, we have two cases. The first is when n=1, and the moving average forecast is
simply equal to the last observed data point. This is also known as a “naïve forecast”. When n is
equal to the number of all the previous data points (say y is the number of previous observation of
the data series we are forecasting), then the moving average forecast is equal to the average of all
observed data points. Between these two extremes there are y − 2 different moving average
forecasts that could be made, each one becoming more “smooth” as n increases.

Exponential smoothing forecast is a special case of the weighted average forecasting mechanism.
Hence, sometimes exponential smoothing is sometimes called the “Exponentially Weighted Moving
Average”.

Exponential smoothing forecasting method only requires two pieces of information to generate the
new forecast: The new data point in the time series being forecasted, dt and the previous forecast

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460

generated dˆt −1 . This fact allows the exponential smoothing forecast to be implemented in
computer systems easily with rather small data storage requirements.

This may seem rather trivial in this the modern world with all of our powerful computers, but it is
still important. Consider for example a modern supermarket. It may sell 25000 different products
in each store. Perhaps the supermarket chain has 1000 stores that are replenished three times a day
(these figures are representative of at least three UK grocery supermarkets). If a 40 period moving
average forecast was used then ( 40 × 3 ×1000 × 25000 = 3,000,000,000) three thousand million
pieces of data have to be processed every eight hours, just to generate a forecast. This is a lot of
data processing even on the latest computers (plus remember, the replenishment orders that use
the forecast also need to be generated), and this is a problem for large companies.

However, if exponential smoothing forecasts were used then only ( 2 × 3 ×1000 × 25000 =
150,000,000) one hundred and fifty million pieces of data need to be processed – a considerable
reduction. Furthermore, requiring less data to generate the forecast will mean the forecasting
system will have less missing and corrupt data. The exponential smoothing process is also a close
match to how humans intuitively forecast according to psychology experts, Brown (1962).
Exponential smoothing is also capable of representing industrial performance when responding to a
step change in demand, Coyle (1977).

MATHS AND STATISTICS FOR BUSINESS ANALYTICS BEMM460