Chapter 3: MEASURES OF CENTRAL TENDENCY
Mr R MOYO
Chinhoyi University of Technology
Department of Mathematics
29 March 2023
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 1 / 14
Introduction
▶ Most sets of data show a distinct tendency to group or cluster about
a central point. Thus for any particular set of data, a typical value
can be used to describe the entire set. Such a descriptive value is
referred to as a measure of central location.
▶ After having presented and communicated information or any other
kind of information on graphs, charts, histograms and many other
display methods, there is need to calculate various numerical values
known as measures of central location/tendency, which quantify
where the majority of observations are concentrated/clustered.
▶ Therefore, measures of central location are descriptive statistics,
which are used to describe and summarize a data set.
▶ Thus, a central location statistic represents a middle data point of a
set of observations and this is crucial in comparing data sets.
Basically, the three main measures of central location are the
Arithmetic Mean, Median and Mode.
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 1 / 14
Arithmetic Mean
▶ The mean is the most commonly used of the three because it is
obtained by summing up all the observations and dividing by their
number (n). In light of this, it is the most favoured since it considers
all the observations in a data set.
▶ However because its computation is based on every observation,
sometimes it is greatly affected by extreme values or outliers. In such
instances, the arithmetic mean presents a distorted representation of
what the data is conveying.
▶ Hence the mean is not the best measure of central location to use for
describing and summarizing a set of data that has outliers in it. NB
Outliers (extreme values) are values that are significantly smaller or
bigger than majority of the observations in a set of data.
▶ If the observations in a sample of size n are x1 , x2 , ..., xn then the
sample mean is calculated as :
Pn
xi
x̄ = i=1 (1)
n
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 2 / 14
Example 3.1
The data, 3652, 4125, 9526, 2546&2328 are salaries of company
executives. Calculate the mean.
Solution
Pn
i=1 xi 3652 + 4125 + ... + 2328 22177
x̄ = = = = 4435.4
n 5 5
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 3 / 14
Arithmetic Mean for Grouped Data
▶ Sometimes we may have to work with data in the form of a frequency
distribution, called grouped data, when the raw data are not available.
We do not have the data values used to make this frequency
distribution and so we are forced to approximate the sample statistics.
▶ Suppose data is grouped into k classes with frequencies f1 , f2 , .., fk
and midpoints x1 , x2 , .., xk , then the arithmetic mean for grouped
data is defined as: Pk
fi xi
x̄ = Pi=1
k
(2)
i=1 fi
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 4 / 14
Example 3.2
The following data is amount spent on basic commodities by households
of a certain location:
Money Spent frequency
0-25 36
25-50 24
50-75 12
75-100 9
100-125 9
125-150 5
150-175 3
175-200 2
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 5 / 14
Solution
Pk
fi xi
x̄ = Pi=1
k
i=1 fi
12.5 × 36 + 37.5 × 24 + ... + 187.5 × 2
=
100
5450
=
100
= 54.5
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 6 / 14
Median
▶ This is the middle value/observation in an ordered array of data. It is
the value, which divides an ordered data set into two equal parts.
This means that half (50%) the observations will be smaller than the
median and the other half will be larger.
▶ The median, unlike the mean, is not affected by any outlier in a data
set. Therefore, whenever an extreme observation is present in a data
set, the median is a better representative of the majority of the
observations in a data set than the mean.
▶ When the number of observations in a data set is odd, the median
value is obtained as follows:
th
M (Q2 ) = the value of the (n+1)
2 observation
th th
▶ If n is even the median values are (n)
2 and (n+1)
2 observations and
the M (Q2 ) = mean of these two observations.
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 7 / 14
Example 3.3
Find the median of the following numbers :
356, 147, 216, 215, 191, 209, 187, 153, 278&133
Solution
We rank our observations either in ascending or descending order, that is
133, 147, 153, 187, 191, 209, 215, 216, 278, &356
n = 10 which is even, hence :
(n) th (n + 1) th
M = mean and observations
2 2
= mean of 5th & 6th observation
191 + 209
= = 200
2
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 8 / 14
Median for grouped data
▶ We can compute the median for grouped data using the cumulative
frequency distribution. We determine the location of the median class
by calculating n2 . Then we determine the frequency of the median
class, the lower limit of the median class, the class width of the
median class and the cumulative frequency just before the median
class. Then the median is calculated using the following formula:
cm ( n2 − Fm−1 )
M = Lm + (3)
fm
Where : Lm is the lower limit of the median class, cm is the class
width of the median class, fm is the frequency of the median class,
Fm−1Pis the cumulative frequency before the median class and
n = ki=1 fi .
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 9 / 14
Example 3.4
Using data on example 3.2 calculate the median.
Solution
Money Spent frequency Cumulative Frequency
0-25 36 36
25-50 24 60
50-75 12 72
75-100 9 81
100-125 9 90
125-150 5 95
150-175 3 98
175-200 2 100
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 10 / 14
n= 100, hence median class is 25-50. Also Lm = 25, cm = 25, fm = 24
and Fm−1 = 36. Thus,
cm ( n2 − Fm−1 )
M = Lm +
fm
100
( − 36)
= 25 + 25 2
24
350
= 25 +
24
= 39.5833
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 11 / 14
Mode
▶ Mode for ungrouped data is simply the observation that occurs most
frequently. This value is found by inspection.
▶ Mode for grouped data is computed by determining the modal class,
that is, the class with the highest frequency. Then the mode is given
by:
cm (fm − fm−1 )
M ode = Lm + (4)
2fm − (fm+1 + fm−1 )
Where : Lm is the lower limit of the median class, cm is the class
width of the median class, fm is the frequency of the median class,
fm−1 is the frequency before the median class and fm+1 is the
frequency after the median class
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 12 / 14
Example 3.5
Using data on example 3.2 calculate the mode.
Solution
The modal class 0-25, that is the class with the highest frequency. We can
also note that Lm = 0, cm = 25, fm = 24, fm−1 = 0, fm+1 = 24 and
hence :
cm (fm − fm−1 )
M ode = Lm +
2fm − (fm+1 + fm−1 )
(36 − 0)
= 0 + 25
2 × 36 − (0 + 24)
900
=
48
= 18.75
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 13 / 14
THE END
Mr R MOYO (CUT) Chapter 3: MEASURES OF CENTRAL TENDENCY 29 March 2023 14 / 14