MEASURES OF CENTRAL TENDENCY

According to Bowley ‘ Statistics is the science of averages’

An ‘Average’ or measure of central tendency is a figure which
represents the large number of observations in a concise or single
numerical data.
Or
It is a typical size which describe the central tendency.
Or
It is representative value around which all the values of variable cluster
or concentrate.
Conclusion: It is clear from the above definitions that an average is a
single value that represents a group of values. Such a value is of great
significance because it depicts the characteristics of the whole group.
VARIOUS MEASURES OF CENTRAL TENDENCY
Different methods of measuring ‘Central Tendency’ provide us with
different kinds of averages. The following are the averages which
are commonly used:
 Mathematical Averages:
(1) Arithmetic Mean
(2) Geometric Mean
(3) Harmonic Mean
(4) Quadratic Mean
 Positional Averages:
(1) Median
(2) Mode
 Business Averages:
(1) Moving Average
(2) Progressive Average
 Mathematical averages are calculated on the basis of
arithmetic or algebraic methods. It is not essential that value
of such average are located in the series.
 Positional averages are located in the series and they are
calculated on the basis of their repetition within the series or
on the position of oberservation.
 Business averages are such averages which are calculated
for forecasting and better operation of business.
 ARITHMETIC MEAN
The arithmetic mean is so much in our everyday use that nearly
all of us are familiar with the concept. When we speak of
average cost of production , average income or average price, we
mean the arithmetic mean.
Arithmetic mean may be defined as the sum of aggregate of a
series of items divided by their numbers
CALCULATION OF ARITHMETIC MEAN
 Individual series:
(i) Direct Method: X = ∑ X = X1 + X2 + X3 + -----------+ XN
N N
Where, X = Arithmetic mean
∑ X = Sum of values of all items
N= Number of items
(ii) Short –Cut Method: If the number of items is large
and values of variable big in size, short cut method of
computing mean is adopted.

X= A+∑d
N
Where, X = Arithmetic mean
A = Assumed mean
d = X-A (Deviation from assumed mean)
∑ d = Sum of deviation from assumed mean
N= Number of items
 Discrete series:
(i) Direct Method :
X = ∑fX
N
Where, X = Arithmetic mean
∑f X = Sum of product of values and
frequencies of all items
N = Sum of frequencies

(ii) Short –Cut Method:

X=A+ ∑fd
N
Where, A = Assumed mean
d = X-A
∑ f d = Sum of product of deviations and their frequencies
N = Sum of frequencies
 Continuous Series:
In continuous series , the exact frequency with which each value of the
variable occur in the distribution is unknown. We only know the limits
within which a certain numbers of frequencies occur. Infact, while
computing mean in continuous series the mid points of various classes
are taken as representative of that particular class. Thus after
calculating the mid value of each class, continuous series changed into
discrete series. After that, calculation of mean in continuous series
would be same as in discrete series.
(i) Direct Method :
X = ∑fX
N
(ii) Short –Cut Method:
X=A+ ∑fd
N
Individual Series Discrete Series Continuous Series
Marks Marks No. of Students Marks No. of Students
45 10 10 0-10 8
60 25 15 10-20 10
55 30 8 20-30 15
42 35 5 30-40 12
50 40 12 40-50 5
62 46 13 50-60 13
65 50 18 60-70 18
70 65 12 70-80 5
75 70 5 80-90 12
80 90 2 90-100 2
 WEIGHTED ARITHMETIC MEAN

In a calculation of simple average each item of the series is

considered equally important but there may be some cases
where all items may not have equal importance and some of
them may be comparatively more important than others.
The weighted mean enables us to calculate an average that takes
into account the importance of each value to the overall total.
The term ‘weight’ stands for the relative importance of different
observations. The formula for weighted arithmetic mean is:
Xw = X1w1 + X2w2 + X3w3 + -----------+ XNwN
w1 + w2 + w3 + -----------------+ wN
Xw = ∑ X w
∑w
DEMERITS OF ARITHMETIC MEAN:
 Effect of extreme values: Since the value of arithmetic mean
depends upon each and every item of the series. Therefore
extreme values affect the average figure disproportionately.
 Unrealistic: Sometimes it may represent such figure which
seems to be unrealistic. For example average person, average
animal represent the fractional figures then it may create
confusion.
 More Difficult Calculations: In comparison to positional
averages, calculation of arithmetic mean is more difficult
 Fallacious Conclusions: Sometimes it gives the fallacious and
inconsistent conclusions.
 Not suitable in the study of rate, ratio and percentage
 MEDIAN
Median is the value of the item in a series which divides the array
into two equal parts, one consisting of all the values less than it and
the other consisting of all the values more than it.
It means, when the values of variable are arranged in a array form( in
an ascending or descending order of magnitude), the value of middle
item of the array is the median.
Properties of median: The median has the following characteristics:
(i) The sum of the deviations of items from the median(ignoring
negative signs) will be least or smaller than the one obtained from
any other value.
(ii) It is only a positional average calculated with the help of
mathematical formula based on interpolation.
 CALCULATION OF MEDIAN

Individual series:
To calculate median in individual series, the following process
has to be followed:
(i) Arrange the data in ascending or descending order
(ii) Apply the following formula:
Median = Size of (N + 1)th item,
2
where N(No. of items) is odd. But the median value for a
group composed of even number of items is estimated by
finding the arithmetic mean of two middle values.
Discrete series
Calculate Median
X f cf
10 5 5
20 10 15
30 12 27
40 13 40
50 10 50
N= 50
Median =Size of (N+1)th item = 25.5th item = 30
2
Continuous series:
To calculate median in continuous series, the following formula
is used:
Median= L+ (N/2 – c) x h
f
Where L = lower limit of median class,
c = cumulative frequency preceding the median class
f = frequency of median class
h = class interval of median class
N = sum of frequencies
Que. Calculate median from the following data:
Sol. Marks(x) No. of students(f) cf
0-10 5 5
10-20 3 8
20-30 7 15
30-40 5 20
40- 50 10 30
50- 60 3 33
60- 70 2 35 N=35
Median= Size of (N/2)th item = 35/2 = 17.5th item = 30-40 is the median
class
Median= L+ (N/2 – c) x h
f
Where L = lower limit of median class,
c = cumulative frequency preceding the median class
f = frequency of median class
h = class interval of median class
= 30 + (17.5- 15)x10 = 35
5
Que. Calculate median from the following data:
Sol. Marks(x) No. of students(f) cf
0-10 10 10
10-20 8 18
20-30 12 30
30-40 10 40
40- 50 20 60
50- 60 8 68
60- 70 7 75
N=75
Median= Size of (N/2)th item = 75/2 =37.5th item = 30-40 is the
median class
Median= L+ (N/2 – c) x h
f
= 30 + (37.5- 30)x10 = 37.5
10
MERITS OF THE MEDIAN:
 Easy to compute and understand
 Known by simple inspection only
 Computation is also possible in incomplete data
 Not affected by extreme items
 Definite and clearly defined
 Most appropriate in study of qualitative features
DEMERITS OF MEDIAN:
 Necessary to arrange the data
 Equal importance to all items
 It cannot be determined precisely when its size falls
between the two values
 MODE
Mode of a distribution is the value at the point around
which the items tend to be most heavily concentrated.
The mode is often said to be that value which occurs most
often in the data, that is with highest frequency.
While this statement is quite helpful in interpreting the
mode, it cannot safely be applied to any distribution,
because of vagaries of sampling.
Continuous series:
Mode = L + f1 –fo xh
2f1- fo – f2
Where, L= Lower limit of modal class
f1 = Frequency of modal class
fo = Frequency of the class preceding
the modal class
f2 = Frequency of the class succeeding
the modal class
h = Class interval of modal class
Que. Calculate mode from the following data:
Sol. Marks(x) No. of students(f)
0-10 5
10-20 3
20-30 7
30-40 9
40- 50 15
50- 60 6
60- 70 2
Mode = L + f1 –fo xh
2f1- fo – f2
By inspection modal class may be 40-50
Mode = 40 + (15 – 9) x 10
(30 -9- 6)
Find out mode from the following data:
Marks 0-10 10-20 20-30 30-40 40-50 50-60
No. of students 3 5 9 3 2 7
MERITS OF THE MODE:
 Easy to compute and understand
 Not affected by extreme values
 Best representative average
 Application in qualitative facts
 Graphical determination
EMPIRICAL RELATIONSHIP BETWEEN MEAN, MEDIAN
AND MODE
The relationship between arithmetic mean, median and mode
depends upon the nature of frequency distribution, which may be
symmetrical or asymmetrical.
In a symmetrical distribution the values of mean, median and
mode are alike i.e., Mean = Median = Mode
If a frequency distribution is not symmetrical, it is referred to as
asymmetrical or skewed.
The empirical relationship between arithmetic mean, median and
mode is expressed as:
Mode = 3 Median – 2 Mean