Statistics for Managerial Decision

STAT20029
Term 1, 2015

Prepared and Submitted by:

Submitted to:
Question 1

42 45 44 45 49 50 55 56 59 42 40 44
28 34 38 51 54 56 48 51 51 52 52 44
49 50 53 55 62 68 68 71 78 77 81 74

a)

2 8
3 4 8
4 0 2 2 4 4 4 5 5 8 9 9
5 0 0 1 1 1 2 2 3 4 5 5 6 6 9
6 2 8 8
7 1 4 7 8
8 1

b)

Class Frequency Relative frequency (%)

$20 to less than $30 1 2.8

$30 to less than $40 2 5.5
$40 to less than $50 11 30.6
$50 to less than $60 14 38.9
$60 to less than $70 3 8.3
$70 to less than $80 4 11.1
$80 to less than $90 1 2.8
Total 36 100
 Histogram
45.00%
40.00%
35.00%
30.00%
Frequency

25.00%
20.00%
15.00%
10.00%
5.00%
0.00%
$25 $35 $45 $55 $65 $75 $85
Midpoints

c) The above chart of the histogram shows the highest relative frequency is between $50 and
$60 at 38.9% and furthermore, the lowest relative frequency is between $20 to $30 at 2.8% as
well as $80 to $90. If the number of the columns in the histogram is halved, then we will lose
half of the data.
20
d) 𝑃 = 36 = 0.55556 = 55.56%

Question 2
Make Miles per gallon
Chevrolet Malibu 20.1 22.0 22.0 24.7 26.0 26.1 29.1 29.3 31.8 33.2
Mazda 6 26.2 28.6 29.6 30.7 31.4 32.5 33.2 40.5
Toyota Camry 22.1 24.1 25.5 26.4 27.0 27.7 30.6 31.3 32.0 32.5 37.2
Honda Accord 24.9 25.4 27.9 28.3 28.7 31.3 32.4 33.2 38.6

Note: the above data are rearranged in ascending order.

a)
 Mean is
∑ni=1 Xi
𝑋̅ =
n
 Chevrolet Malibu:
 20.1 + 22 + 22 + 24.7 + 26 + 26.1 + 29.1 + 29.3 + 31.8 + 33.2
𝑋̅ = = 26.43
10

 Mazda 6:
26.2 + 28.6 + 29.6 + 30.7 + 31.4 + 32.5 + 33.2 + 40.5
𝑋̅ = = 31.5875
8

 Toyota Camry:
22.1 + 24.1 + 25.5 + 26.4 + 27 + 27.7 + 30.6 + 31.3 + 32 + 32.5 + 37.2
𝑋̅ =
11

= 28.7636

 Honda Accord:
24.9 + 25.4 + 27.9 + 28.3 + 28.7 + 31.3 + 32.4 + 33.2 + 38.6
𝑋̅ = = 30.07778
9

 Median is
n+1
Median = th
2

 Chevrolet Malibu:
10 + 1
Median = = 5.5𝑡ℎ
2
5th + 6th 26 + 26.1
Median = = = 26.05
2 2

 Mazda 6:
8+1
Median = = 4.5𝑡ℎ
2
4th + 5th 30.7 + 31.4
Median = = = 31.05
2 2

 Toyota Camry:
11 + 1
Median = = 6𝑡ℎ = 27.7
2
  Honda Accord:
9+1
Median = = 5𝑡ℎ = 28.7
2

 First Quartile
n+1
Q1 = th
4

 Chevrolet Malibu:
10 + 1
Q1 = th = 2.75th = 22 + 0.75(22 − 22) = 22
4

 Mazda 6:
8+1
Q1 = th = 2.25th = 28.6 + 0.25(29.6 − 28.6) = 28.85
4

 Toyota Camry:
11 + 1
Q1 = th = 3th = 25.5
4

 Honda Accord:
9+1
Q1 = th = 2.5th = 25.4 + 0.5(27.9 − 25.4) = 26.65
4

 Third Quartile
3(n + 1)
Q3 = th
4

 Chevrolet Malibu:
3(10 + 1)
Q3 = th = 8.25th = 29.3 + 0.25(31.8 − 29.3) = 29.925
4

 Mazda 6:
3(8 + 1)
Q3 = th = 6.75th = 32.5 + 0.75(33.2 − 32.5) = 33.025
4
  Toyota Camry:
3(11 + 1)
Q3 = th = 9th = 32
4

 Honda Accord:
3(9 + 1)
Q3 = th = 7.5th = 32.4 + 0.5(33.2 − 32.4) = 32.8
4

b)
Make Miles per gallon n ∑𝑿 (∑ 𝑿)𝟐 ∑ 𝑿𝟐

Chevrolet 20.1 22.0 22.0 24.7 26.0 26.1 29.1 29.3 31.8 33.2 10 264.3 69,854.49 7,158.09
Malibu

Mazda 6 26.2 28.6 29.6 30.7 31.4 32.5 33.2 40.5 8 252.7 63,857.29 8,107.75

Toyota 22.1 24.1 25.5 26.4 27.0 27.7 30.6 31.3 32.0 32.5 37.2 11 316.4 100,108.96 9,292.86
Camry

Honda 24.9 25.4 27.9 28.4 28.7 31.3 32.4 33.2 38.6 9 270.7 73,278.49 8,289.81
Accord

 Standard deviation

(∑ X)2
∑ X2 −
S= √ n
n−1

 Chevrolet Malibu:

(264.3)2

S= √7158.09 − 10
= 4.37976
10 − 1

 Mazda 6:
(252.7)2
8107.75 −
S=√ 8
= 4.2357
8−1
 Toyota Camry:
(316.4)2

S= √9292.86 − 11
= 4.3823
11 − 1
  Honda Accord:
(270.7)2

S= √8289.81 − 9
= 4.2976
9−1

 Range=𝑋𝑙𝑎𝑟𝑔𝑒𝑠𝑡 − 𝑋𝑠𝑚𝑎𝑙𝑙𝑒𝑠𝑡

 Chevrolet Malibu:
33.2 − 20.1 = 13.1

 Mazda 6:
40.5 − 26.2 = 14.3

 Toyota Camry:
37.2 − 22.1 = 15.1

 Honda Accord:
38.6 − 24.9 = 13.7

 Coefficient of variation
𝑆
𝐶𝑉 = × 100%
𝑋

 Chevrolet Malibu:
4.37976
𝐶𝑉 = × 100% = 16.57%
264.3/10

 Mazda 6:
4.2357
𝐶𝑉 = × 100% = 13.41%
315.875

 Toyota Camry:
4.3823
𝐶𝑉 = × 100% = 15.22%
316.4/11
  Honda Accord:
4.2976
𝐶𝑉 = × 100% = 14.3%
270.7/9

c)

Box-and-Whisker PlotBox-and-Whisker Plot

Chevrolet Malibu

Mazda 6

Toyota Camry

Honda Accord

0 5 10 15 20 25 30 35 40 45

d)
From the above box plot figure, we can conclude that the Chevrolet Malibu is the most
balanced compare with the other three cars, and it got the lowest rate of using petrol in those
four types of cars. On the other hand, to illustrate the Mazda 6, it got the highest rate of using
petrol compare with those three types of cars, as well as it shows the most unbalanced using of
the petrol. In the above figure, Toyota and Honda have similar data and hence are equivalent to
each other.
Question 3

2013 survey data in '000 persons

Occupation major
group Males full-time Males part-time Females full-time Females part-time
Managers 909.9 70 385.6 133.4
Professionals 1043.1 158.2 835.7 526
Technicians and trades
workers 1344.9 138.7 131.6 109.7
Community and personal
service workers 225.8 129.8 303.7 502
Clerical and administrative
workers 354.4 58.3 738.7 510
Sales workers 232.4 161.3 207.8 471.6
Machinery operators and
drivers 604.4 101.4 52.3 19.2
Labourers 464.4 272.7 129.2 247.5
Total 5179.4 1090.4 2784.6 2519.4

a)

232.4 + 161.3 + 207.8 + 471.6 1,073.1

𝑝= = = 0.0927 = 9,27%
5179.4 + 1090.4 + 2784.6 + 2519.4 11,573.8

b)

58.3 + 510
𝑝= = 0.03393 = 33.93%
1661.4

909.9
𝑝= = 0.0607 = 60.7%
1498.9

c)

1090.4 + 2519.4
𝑝= = 3,609.8 = 31.19%
11,573.8

Question 4
a)
Number of wrong
Observed frequency Probability
connection daily
0
0 0 =0
267
0
1 0 =0
267
1
2 1 = 0.003745
267
5
3 5 = 0.018727
267
11
4 11 = 0.041199
267
14
5 14 = 0.052434
267
22
6 22 = 0.082397
267
43
7 43 = 0.161049
267
31
8 31 = 0.116105
267
40
9 40 = 0.149813
267
35
10 35 = 0.131086
267
20
11 20 = 0.074906
267
18
12 18 = 0.067416
267
12
13 12 = 0.044944
267
7
14 7 = 0.026217
267
6
15 6 = 0.022472
267
2
16 2 = 0.007491
267
Total 267
 N

μ = E(X) = ∑ Xi P(Xi )
i=1

μ = 0 × 0 + 1 × 0 + 2 × 0.003745 + 3 × 0.018727 + 4 × 0.041199 + 5 × 0.52434

+6 × 0.082397 + 7 × 0.161049 + 8 × 0.116108 + 9 × 0.149813 + 10 × 0.131086
+11 × 0.074906 + 12 × 0.067416 + 13 × 0.044944 + 14 × 0.026217
+15 × 0.022472 + 16 × 0.007491
μ = 8.741573 ≅ 9
Thus we can expect the number of wrong connection is about 9 times each day.

b) Assuming that the data follows a Poisson distribution:

λ = 8.7

i) P(4 < 𝑋 < 6) = P(X = 5)

P(4 < 𝑋 < 6) = 0.0692

ii) P(X > 10) = P(X = 11) + P(X = 12) + P(X = 13) + P(X = 14) + P(X = 15) +
P(X = 16)

P(X > 10) = 0.0902 + 0.0654 + 0.0438 + 0.0272 + 0.0158 + 0.0086

P(X > 10) = 0.251
Notice: the P(X) value is from book table A.3

Question 5
Name of Country GDP in billion USD Name of Country GDP in billion USD
USA 17,416 Netherlands 880
China 10,355 Indonesia 856
Japan 4,770 Turkey 813
Germany 3,820 Saudi Arabia 778
France 2,902 Switzerland 679
UK 2,848 Nigeria 594
Brazil 2,244 Sweden 559
Italy 2,129 Poland 552
Russia 2,057 Argentina 536
India 2,048 Belgium 528
Canada 1,794 Norway 512
Australia 1,483 Taiwan 505
South Korea 1,449 Austria 436
Spain 1,400 UAE 416
Mexico 1,296 Iran 403
n=30
∑ X = 403 + 416 + 436 + ⋯ + 4770 + 10355 + 17416 = 67,058

∑ X 2 = 4032 + 4162 + 4362 + ⋯ + 47702 + 103552 + 174162 = 499385022

a)
15th +16th 880+1296
Median = = = 1088
2 2

 First Quartile
n+1 30 + 1
Q1 = th = th = 7.75th = 536 + 0.75(552 − 536) = 548
4 4

 Third Quartile
3(n + 1) 3(30 + 1)
Q3 = th = th = 23.25th = 2129 + 0.25(2244 − 2129) = 2157.75
4 4

 Mean is
∑ni=1 Xi 403 + 416 + 436 + ⋯ + 4770 + 10355 + 17416
μ= = = 2235.267
n 30

 Standard deviation

∑ X = 403 + 416 + 436 + ⋯ + 4770 + 10355 + 17416 = 67058

∑ X 2 = 4032 + 4162 + 4362 + ⋯ + 47702 + 103552 + 174162 = 499385022

(∑ X)2 (67058)2
∑ X2 −
S=√ n
= √499385022 − 30
= 3471.522
n−1 30 − 1
  Mode is the data value that occurs most often (by the data that is given, there is no
Mode occurring)
We begin with a five number summary:

Five number summary

Minimum 403
First Quartile 548
Median 1088
Third Quartile 2157.75
Maximum 17416

And the mean and standard deviation:

Mean 2235.267
Std. Deviation 3471.522

The mean (2235.267) is very over two times of the median (1088). The mode is appear so it
is not to compare with the mean and median.

Comparing the interquartile range to 1.33 standard deviations.

 The interquartile range is:
IQR = UQ − LQ = 2157.75 − 548 = 1609.75

 The standard deviation is 3471.522, so 1.33 standard deviations are:

1.33𝑆 = 1.33(3471.522) = 4617.12

Since IQR (1609.75) is approximately equal 1.33 standard deviations (4617.12), so this is not
fit with characteristic of the normal distribution.

Box spot of GDP in billion USA

0 2000 4000 6000 8000 10000 12000 14000 16000 18000 20000

By looking at Box spot, it is be able to see that this data set is not symmetric.
 20000

18000

16000

14000

12000

10000

8000

6000

4000

2000

0
-2.5 -2 -1.5 -1 -0.5 0 0.5 1 1.5 2 2.5

GDP

We can conclude that the data is probably not well described by the normal distribution.
b)
𝛼 = 1 − 0.95 = 0.05

𝛼
= 0.025
2

Degree of freedom (df)=30-1=29

𝑆 3471.522
𝑋 ± 𝑡0.025,29 = 2235.266 ± 2.045 2235.266 ± 1296.14
√𝑛 √30

𝑆
𝑋 + 𝑡0.025,29 = 2235.266 + 1296.14 = $939.126
√𝑛
𝑆
𝑋 − 𝑡0.025,29 = 2235.266 − 1296.14 = $3531.406
√𝑛

$939.126 ≤ 𝜇 ≤ $3531.406