Chapter No 3

Measures of Central Tendency

Measure of central tendency:

A measure that indicates the central position of the data is called measures of central
tendency or measure of location.

Average:

A central value that represents the whole data is called average.

Types of averages:

The commonly used types of averages are:

1. Arithmetic mean
2. Geometric mean
3. Harmonic mean
4. Median
5. Mode

Qualities of a good average:

1. It should be easy to calculate and simple to understand.

2. It should be defined by mathematical formula.
3. It should be based upon all the observations of data.
4. It should be capable of further mathematical treatment.
5. It should not be affected by extreme values.

Arithmetic mean:

Arithmetic mean is defined as the sum of all the observations divided by total number of
observations.

Formulae of Arithmetic mean:

Arithmetic mean using Ungroup data Group data

Direct method ∑ ∑
̅= ̅= ∑
Short cut method ∑ ∑
̅ =A + ̅ =A + ∑
Where D = x - A Where D = x - A
Step deviation or coding ∑ ∑
̅ =A + ×h ̅ =A + ×h
method ∑
Where u = Where u =

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 1

Mathematical properties of Arithmetic mean:

1. Arithmetic mean of a constant is constant itself.

2. Sum of deviations of values from their mean is zero.
That is: ∑( ̅) = 0
3. Sum of square of deviations of values form their mean is minimum.
That is: ∑( ̅ ) = minimum
4. If a constant is added or subtracted from the variable x, then the constant is also added
or subtracted from the mean of x.
That is: y = x a then, ̅ = ̅ a
5. If the variable x is multiplied by a constant, then the mean of x is also multiplied by
the same constant.
That is: y = ax then, ̅ = ̅

Merits / Advantages of Arithmetic mean:

1. It is easy to calculate.
2. It is defined by a mathematical formula.
3. It is defined upon all the values of the data.
4. It can be used for almost every kind of data.
5. It is capable of mathematical treatment.

Demerits / Disadvantages of Arithmetic mean:

1. It is affected by extreme values.

2. It cannot be calculated if any value in the data is missing.
3. It cannot be calculated in open ended classes without assuming the open ends.
4. It is not useful for qualitative data.

Combined mean:

If we want to calculate a single mean of more than one data then we calculate combined
mean. If we have k data sets then the combine mean is:
̅ ̅ ̅
̅ =

For three data sets the combined mean is:

̅ ̅ ̅
̅ =

Weighted mean:

The arithmetic mean of values by the considering the relative importance of each value is
called weighted mean.
∑
The formula to calculate the weighted mean is: ̅ =
∑

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 2

Geometric mean:

Geometric mean is defined as the position square root of the product of n positive values.

If , are n positive values then

The geometric mean for ungroup data is:

G = √( )( ) ( ) = [( )( ) ( )]

OR
∑
G = antilog ( )

And geometric mean for group data is:

∑
G = √( )( ) ( ) = [( )( ) ( )]∑

OR
∑
G = antilog ( )
∑

Merits / Advantages of geometric mean:

1. It is defined by mathematical formula.

2. It is based upon all the values of the data.
3. It is capable of further mathematical treatment.
4. It is less affected by extreme values.

Demerits / Disadvantages of geometric mean:

1. It is difficult to understand as compare to mean.

2. It cannot be calculated if any value in the data is missing.
3. It becomes zero if any of the value in the data is zero.
4. It cannot be calculated if any value in the data is negative.

Harmonic mean:

The harmonic mean is defined as the reciprocal of arithmetic mean of the reciprocal of
values.

The formula to calculate the harmonic mean for ungroup data is:

H.M =
∑

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 3

And for group data:

∑
H.M =
∑( )

Merits / Advantages of harmonic mean:

1. It is based upon all the values of data.

2. It is capable of mathematical treatment.
3. It does not give much weight to larger values.

Demerits / Disadvantages of harmonic mean:

1. It is not easy to calculate as compare to arithmetic mean.

2. It cannot be calculated if any value in the data is missing.
3. It gives much importance to smaller values.
4. It cannot be calculated if any value in the data is zero.

Median:

The value that divides the data into two equal parts is called median.

OR

It can also be defined as the central value in the array data is called median.

The formula to calculate the median is:

For ungroup data:

Median = ( ) value

For group data:

Median = l + ( )

Where

l = lower class boundary of the median class.

h = interval of the median class

f = frequency of the median class

n=∑

c = cumulative frequency of the class lower than the median class.

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 4

Merits / Advantages of median:

1. It is easy to calculate.
2. It is simple to understand.
3. It is not affected by extreme values.
4. It can be calculated in open ended class data.

Demerits / Disadvantages of median:

1. It is not based upon all the values of data.

2. It is necessary to arrange the data before the calculation of median.
3. It is not capable of further mathematical treatment.
4. It is necessary to convert the class limits into class boundaries in grouped data before
the calculation of median.

Mode:

The most repeated value in the data is called mode.

The formula to calculate the mode for group data is:

Mode = l + h
( ) ( )

l = lower class boundary of the model class

= frequency of the model class

= frequency of the class lower than the model class

= frequency of the class following the model class

h = interval of the model class

Merits / Advantages of mode:

1. It is easy to understand.
2. It is quick to calculate.
3. It is not affected by extreme values.
4. It is not necessary to arrange the data before the calculation.
5. It can be calculated in open ended class data.
6. It is suitable in case of qualitative data.

Demerits / Disadvantages of mode:

1. It is not defined by mathematical formula.

2. It is not based upon all the values of the data.
3. It is not capable of mathematical treatment.
4. Sometimes a distribution has no mode or more than one mode.

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 5

Quartiles:

The values that divided the data into four equal parts are called quartiles.

= first quartile or lower quartile

= second quartile

= third quartile or upper quartile

The formulae to calculate the quartiles are:

For ungroup data:

=( ) value

( )
=( ) value

( )
=( ) value

For the group data:

=l+ ( )

=l+ ( )

=l+ ( )

Deciles:

The values that divide the data into ten equal parts are called deciles.

The formulae to calculate the deciles are:

For ungroup data:

=( ) value

( )
=( ) value

( )
=( ) value

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 6

For group data:

=l+ ( )

=l+ ( )

=l+ ( )

Percentiles:

The values that divide the data into hundred equal parts are called percentiles.

The formulae to calculate the percentiles are:

For ungroup data:

=( ) value

( )
=( ) value

( )
=( ) value

For group data:

=l+ ( )

=l+ ( )

=l+ ( )

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 7

Uni-Model distribution:

A distribution having only one mode is called uni-model distribution.

Bi-Model distribution:

A distribution having two modes is called bi-model distribution.

Multi-Model distribution:

A distribution having more than two modes is called multi-model distribution.

Empirical relation between mean, median and mode:

For a moderately skewed distribution there exist an empirical relationship between mean,
median and mode. The difference between mean and median is half of the difference between
median and mode. That is:

Mean – Median =
( )

OR

Mode = 3Median – 2Mean

END CHAPTER

UMER NASEER / Lecturer in Statistics/ Contact : 03420074311 8