calculate mean I standard deviation

1) Mode x 2 -
1 SD

f
I stat clear-7
Al X F

2) Shift-mode -

class-marks
E**.uit
3) Raw data (4 Mt ↳

M+midpoint
Group data (C); f
-***
BAMS1733 QUANTITATIVE STUDIES 4) Shift-1:
Ifxz 4,2zXn 3
fx
SAX
S
#L
↳4

CHAPTER 2: DATA DESCRIPTION (A) 5) Shift-2:X 8x xx-> standard

deviation
Sample
↓ I 2 3
u mean

mean

MEASURES OF CENTRAL TENDENCY (LOCATION)

The measures of central tendency is usually called the

average. Central tendency is a single value situated at the
centre of a data and can be taken as a summary value for that
data set. Three types of averages are often used as measures
of central tendency. They are mean, median and mode.

Mean (arithmetic mean)

 Mean is the most commonly used measure of central

tendency. It is the average of a group of data. Mean is
calculated by summing up all the observations in the data set
and then dividing it by the number of data.

 Computation of the mean:

(a) Raw data

x
Mean 
n
where x = individual value; n = the total number of items;
 means summation of.

Example: Find the mean of 2, 2, 3, 4 0, 6, 2 and 1.

2  2  3  4  0  6  2  1 20
Solution: Mean = 
8 8 = 2.5
(b) Grouped data
 fx
Mean  where x = class mark or mid-point.
f

1
BAMS1733 QUANTITATIVE STUDIES
CHAPTER 2: DATA DESCRIPTION (A)

MEASURES OF CENTRAL TENDENCY (LOCATION)

The measures of central tendency is usually called the

average. Central tendency is a single value situated at the
centre of a data and can be taken as a summary value for that
data set. Three types of averages are often used as measures
of central tendency. They are mean, median and mode.

Mean (arithmetic mean)

 Mean is the most commonly used measure of central

tendency. It is the average of a group of data. Mean is
calculated by summing up all the observations in the data set
and then dividing it by the number of data.

 Computation of the mean:

(a) Raw data

x
Mean 
n
where x = individual value; n = the total number of items;
 means summation of.

Example: Find the mean of 2, 2, 3, 4 0, 6, 2 and 1.

2  2  3  4  0  6  2  1 20
Solution: Mean = 
8 8 = 2.5
(b) Grouped data
 fx
Mean  where x = class mark or mid-point.
f

1
 Example (Group Data)
The following frequency distribution shows the lengths of
plastic pipes produced on a particular day. Calculate the
mean length.

Length (cm) Number of plastic pipes

10 – under 20 3
20 – under 30 7
30 – under 40 10
40 – under 50 16
50 – under 60 34
60 – under 70 13
70 – under 80 7
80 – under 90 6
90 – under 100 4
Total 100

Solution:
Length (cm) Class Number of fx
mark, x plastic pipes,
f
10 – 20 15 3 45
20 – 30 25 7 175
30 – 40 35 10 350
40 – 50 45 16 720
50 – 60 55 34 1870
60 – 70 65 13 845
70 – 80 75 7 525
80 – 90 85 6 510
90 – 100 95 4 380
f =100 fx = 5420

 fx 5420
Mean    54.2 cm
f 100
Interpretation: The average length of a plastic pipe is 54.2 cm.
-
data

2
Example
The following frequency distribution shows the daily
production level in a production line. Calculate the arithmetic
mean.

Production (units) Number of days

13 – 17 2
18 – 22 22
23 – 27 10
28 – 32 14
33 – 37 3
38 – 42 4
43 – 47 6
48 – 52 1

Solution:
Production (units) Number Class mark, x fx
of days, f
13 – 17 2 15 30
18 – 22 22 20 440
23 – 27 10 25 250
28 – 32 14 30 420
33 – 37 3 35 105
38 – 42 4 40 160
43 – 47 6 45 270
48 – 52 1 50 50
Total 62 1725

 fx 1725
Mean    27.82 units
f 62

Interpretation: The average daily production is 27.82 units.

Note: The mean computed from population data is denoted by

the symbol  (pronounced as miu); the mean computed from
sample data is denoted by x.
3
Median

 Median is the middle value of the distribution. It is important

that the data has to be arranged in ascending or descending
order of magnitude before the median is to be located.

 The median being the middle value implies that 50% of the
observations will be more than or equal to the median and
50% of the observations will be less than or equal to the
median.

 Computation of the median:

(a) Raw data

1. Arrange the data into an array in ascending order of

magnitude.
2. Locate the median item as:
n1
Median = value of th item
2
where n = number of items in a data set.

Note: If the data set consists of even number of figures,

then median will be the average of the two middle values.

Example

Find the median for the distribution:

45, 35, 36, 43, 32, 45, 70, 60

Solution: Arrange the data in ascending order of magnitude

32, 35, 36, 43, 45, 45, 60, 70 n=8
n 1 8 1
Median = value of th item = value of th item
2 2
43  45
th
= value of 4.5 item = = 44
2

4
 cummulative frequency
~before the median class

EfrSequency
formula -
calculate median

8give - estimate median 2-

the median class
of

(b) Grouped data

1. Calculate the cumulative frequencies to position the
items in ascending order.
n
2. Locate the median class as: median = value of th
2
item
3. Find the median using (1) ogive;
(2) linear interpolation formula:
cm  n 
Median  Lm     f m1 
fm  2 
where Lm = lower class boundary of median class
Cm = class size of median class
fm = frequency of median class
f m-1 = cumulative frequency of the preceding
median class

Example
The following table shows the lengths of plastic pipes
produced on a particular day. Calculate the median length.

Length (cm) Number of plastic pipes

10 – under 20 3
20 – under 30 7
30 – under 40 10
40 – under 50 16
50 – under 60 34
60 – under 70 13
70 – under 80 7
80 – under 90 6
90 – under 100 4
Total 100

5
Solution:

Length (cm) Frequency Upper Class Cumulative

Boundaries Frequency
< 10 0
10 – 20 3 < 20 3
20 – 30 7 < 30 10
30 – 40 10 < 40 20
40 – 50 16 < 50 36
50 – 60 34 < 60 70
60 – 70 13 < 70 83
70 – 80 7 < 80 90
80 – 90 6 < 90 96
90 – 100 4 < 100 100
Total 100
Q2 2
= +Exfm) c
n 100 f
Median = value of th item = value of th item
- 36(0)
2 2 50
=

34
= value of 50th item =
54.1176
Median class boundaries: 50 – 60
cm  n 
Median  Lm     f m 1  = 50  10 (50  36) = 54.12
fm  2  34
Interpretation: 50% of the plastic pipes are having lengths less
than or equal to 54.12 cm and the other 50% are having
lengths more than or equal to 54.12 cm.

6
Example
The following frequency distribution shows the daily production
level in a production line.

Production (units) Number of days

13 – 17 2
18 – 22 22
23 – 27 10
28 – 32 14
33 – 37 3
38 – 42 4
43 – 47 6
48 – 52 1

Calculate the median using

(a) the linear interpolation method;
(b) an ogive.

Solution:
Production Frequency Upper Class Cumulative
(units) boundaries frequency
< 12.5 0
13 – 17 2 < 17.5 2
18 – 22 22 < 22.5 24
23 – 27 10 < 27.5 34
28 – 32 14 < 32.5 48
33 – 37 3 < 37.5 51
38 – 42 4 < 42.5 55
43 – 47 6 < 47.5 61
48 – 52 1 < 52.5 62
62 Total
n 62
Median = value of th item = value of th item
2 2
= value of 31st item
(a) Median class boundaries: 22.5 – 27.5
Median = 22.5  5 (31  24) = 26 units
10

7
(b)
Cumulative '<' ogive: Production in a production line for a period of
frequency 62 days
70

60

50

40

30

20

10
22=
31
=

0 class boundaries
median
12.5 17.5 22.5 27.5 32.5 37.5 42.5 47.5 52.5

Production (units)

From the ogive, median = 26 units.

Mode

 Mode is the most frequently occurred value in a set of

measures.
 Mode may not exist and even if it does, it may not be unique.
 Computation of the mode:
(a) Raw data
Arrange the data in ascending order of magnitude. Locate
the value with the highest occurrence.

8
 Example
The following data show the number of children in 8
families: 2, 2, 3, 4, 0, 7, 2, 1
Find the mode.
Solution:
Arranging data in ascending order: 0, 1, 2, 2, 2, 3, 4, 7
The mode = 2 children (occurs 3 times)

Example
Find the mode for the following data.
(1) 1, 2, 3, 4, 7, 8
(2) 1, 2, 2, 3, 4, 5, 5, 9
Solution:
(1) No mode.
(2) Two modes: 2 and 5.

(b) Grouped data

1. Locate the modal class (the class with the highest

frequency
frequency) adjusted frequency

I
2. Find the mode using (1) Histogram; not
↳

(
I class size
same

(2) Formula. depend on

dass size

f m  fb fm, fb, fa ->

Adjusted frequency
Mode  Lm   cm
2 f m   fb  f a  fr, fb, fa ->
frequency

where Lm = lower class boundary of the modal class

fm = frequency of the modal class
fb = frequency of the class before the modal class
fa = frequency of the class after the modal class.
Cm = class size of the modal class

Note: If the formula is used to compute the mode for

frequency distribution of unequal class size, then the

9
frequency will be replaced by the adjusted frequency of the
corresponding class.)

Example lequal class size)

The following frequency distribution shows the lengths of
plastic pipes produced on a particular day.
frequency
Length (cm) Number of plastic pipes
boundaries
10 – under 20 3 Lm. Lower

20 – under 30 7 38
=

30 – under 40 10 cm, class size

68 50 18
40 – under 50 16
=

frequency mode class

Mode- 50 – under 60 34 fin,

60 – under 70 13 34
=

70 – under 80 7 fb, before 16

=

80 – under 90 6 fa, after 13

=

90 – under 100 4
Total 100

Find the mode for the frequency distribution using

(a) Histogram; (b) Formula.

fr-fb
Mode =
(m+ * (m
2fm-(fb-fa)

134-16)
* 18
58
2134)
+
=

-
(16-13)

54.62(m
=

10
Solution:
(a)
Histogram: Length of plastic pipes produced on a
particular day
Frequency

40
35

%
30
25
20
15
10
5
0 class boundaries

10 20 30 40 50 60 70 80 90 100
Length (cm)
From the histogram, mode = 54 cm.

(b) Modal class boundaries: 50 – 60

f m  fb (34  16)
Mode  Lm   cm = 50  10
2 f m   fb  f a  2  34  (16  13)

Mode = 54.62 cm dat a

which shows the most common (or frequent) length of

plastic pipe or most of the plastic pipes produced are
having lengths 54.62 cm. frequency

Advantages and disadvantages of mean, median and mode

Mean
Advantages:
 It is easily understood.
 The value of each item is included in the computation, thus it
has the kind of exactness that the median and the mode lack
of.
 It is well suited for further analysis.

11
Disadvantages:
 Its value may not correspond to the actual value, e.g. the
average number of children in each family is 2.4 children.
 It may be distorted by a few extremely high or low values,
e.g. a distribution of 5 persons’ weekly income (in RM):
500, 200, 250, 300, 6000
The mean income per week = RM 1,450
The mean is now distorted or pulled up by one person’s
income of RM6,000 (being the extreme value). The majority
is only earning between RM200 to RM500. Certainly the
mean of RM1,450 is misleading.

Median
Advantages:
 It is of use where the middle value is of significance.
 It is not affected by extreme values. Thus, it is usually
preferred than mean when there are extreme values in the
distribution.
Extreme Extreme

Disadvantages:
 It does not reflect the full range of values. median

 It is not suitable for further analysis.

Mode
Advantages:
 It is the more appropriate average in situations where it is
useful to know the most common value, e.g. the purchasing
department in a shoe store will order the modal shoe size.
 It is easy to find and is not influenced by extreme values.
Disadvantages:
 It ignores the dispersion around the modal value.
 It is not suitable for further analysis.
 It is not unique.

12
Question 1:
A psychologist developed a new test for adult intelligence. The
test was administered to 10 adults, and the following scores
were obtained.

115 102 130 124 117 118 122 106 108 118

Calculate the mean, median and mode. Interpret your results.

(Answers: 116, 117.5, 118)

13
Question 2:
The following table shows the number of cars sold by a second
hand car dealer for the last 50 days.

Number of cars Number of days

1–2 8
3–4 14
5–6 18
7 – 10 6
11 and above 4

Calculate the mean, median and mode. Interpret your results.

(Answers: 5.22, 4.83, 4.92)

14
BAMS1733 QUANTITATIVE STUDIES
TUTORIAL 2 (Measures of Central Tendency)
1. Define the mean, median and mode. State one advantage
and one disadvantage of each measure of location.

2. The following array shows the amounts of money spent (in

RM) by a random sample of 15 students at a primary school
canteen:

''ll I 1.50, 1.90,

0.40, 0.50, 0.75, 0.75, 0.75, 0.85, 0.90,
1.90, 2.35, 2.45, 2.80, 3.00, 3.20.
Determine the
(a) mean;
(b) median;
(c) mode for the amounts spent.
Interpret your answers.

3. A manager observes the amount of time taken by the clerk to

prepare a sample of 10 invoices in the office and the results
are arranged in ascending order to the nearest minute:
1111 11 II
5, 5, 5, 7, 9, 14, 15, 15, 16, 300.
Determine the
(a) mean;
(b) median;
(c) mode.
Which measure of location calculated above can best
represent the data in this question? Explain your answer.

4. The following table shows the record on outgoing telephone

calls lasting for 10 minutes or longer.
Length of call (nearest minute) Number of calls
10 and under 12 40
&2 - 12 and under 14
14 and under 16
109
54 h
16 and under 18 22
18 and under 20 15 is
zar

15
 (a) Calculate the mean, median and modal values of the
length of calls.
(b) Draw the histogram for the data and estimate the mode.
(c) Draw the ‘ less than’ ogive and estimate the median.
(d) If the charges for telephone call is RM 0.30 per minute,
which of the 3 measures in part (a) above is most suitable
to estimate the total telephone charges? Explain.

5. A fast-food chain store has 73 outlets located at different

parts of the country. The profits of the outlets at the end of
the financial year were as follows:
Profit (RM million) Number of outlets
Under 2 8 2
-

30 38
2 and under 4 2 4
-

20 53
4 and under 6 4 6
-

10 68
68
6 and under 10 6-18 8
10 and under 15 10-15 5 73

(a) Draw a histogram to represent the information.

(b) Estimate the mode from the histogram.
(c) Calculate the mean, median and mode.
(d) Indicate the usefulness of each of the measures
calculated in part (c) above in understanding the
implications of the data.

6. The following table shows the weight distribution of a

random sample of 120 students in a business programme.
Weight (kg) Number of students
40 – < 45 4
45 – < 50 13
50 – < 55 17
55 – < 60 40
60 – < 70 39
70 – < 80 7
(a) Construct a histogram to represent the data and
estimate the mode from it. Justify the answer of the
mode by calculation.

16
 (b) Construct a ‘<’ cumulative frequency polygon,
(i) estimate the median from it. Justify the answer of the
median by calculation.
(ii) if a student having weight 65 kg or more is classified
as overweight, estimate the percentage of overweight
students.

7. The following cumulative frequency distribution table shows

the number of ordinary shares held by a random sample of
300 shareholders in a company.

Number of ordinary shares held Number of shareholders

(’00)
Less than 10 49
Less than 20 139
Less than 30 217
Less than 40 259
Less than 50 285
Less than 60 300
(a) Draw an ogive for the above data and estimate the
median. Interpret the answer of the median.
(b) Find the sample mean.

Answers:
2. (a) RM1.60 (b) RM1.50 (c) RM0.75
3. (a) 39.1 minutes (b) 11.5 minutes (c) 5 minutes
4. (a) 13.86 min.,13.47 min.,13.11 min. (d) mean
5. (b) 1.5 (RM million) (c) 3.65 (RM million), 2.65 (RM million),
1.5 (RM million)
6. (a) 57.6 kg (b)(i) 58.25 kg (ii) 22.5%
7. (a) 21.5 (’00) shares (b) 23.367 (’00) shares

17