Measures of Central Tendency

• A measure of central tendency is a typical

value around which other figures concentrate.
• An average is a single value within the range
of the data that is used to represent all the
values in the series.
 Objectives of an Average
• It reduces the mass information into a single
value.
• Average provides facility to make
comparisons.
• Average is very useful in statistical analysis.
• Average is also used in sampling. We can get a
clear picture of a group or population by the
help of a sample.
 Types of Averages
• Arithmetic Mean
• Median
• Mode
 Arithmetic Mean
• It is defined as the sum of the observations
divided by the number of observations.
• It is denoted by x
 1. Individual Series
(i) Direct Method (ii) Short Cut Method
1 1
x 
n
x x  A
n
 d ; d  x A

where, where,
x denotes the value of the A is assumed mean
variable n denotes number of
n denotes the number of terms.
observations.
Ques 1. The number of new orders received by a company over the last 25 working days
were recorded as follows:

3, 0, 1, 4, 4, 4, 2, 5, 3, 6, 4, 5, 1, 4, 3, 2, 0, 2, 0, 5, 4, 2, 3, 3, 1.

Calculate the average number of orders received over all similar working days.
Ques 2. The following data gives the equity holdings of 10 of the India’s billionaires.

Name Equity Holdings(millions of Rs)

Kiran Mazumdar-Shaw 2717
The Nilekani family 2796
The punj family 3098
Karsanbhai K. Patel 3144
Shashi Ruia 3527
K.K.Birla 3534
B.Ramalinga Raju 3862
Habil F. Khorakiwala 4187
The Murthy family 4310
Keshub Mahindra 4506
Calculate the average equity holding.
 2. Discrete Series
(i) Direct Method (ii) Short Cut Method
1 1
x 
N
 f x x  A
N
fd
where, where,
x denotes the values of d=x-A
the variable A is assumed mean
f denotes the frequency N = ∑f ; denotes the no. of
N = ∑f ; denotes the no. terms
of observations.
Ques 1. The HR manager at a city hospital began a study of the overtime hours of the
registered nurses. The following data was recorded during a month.

Overtime No. of
hours nurses
5 3
6 4
7 2
9 4
10 2
12 5
13 3
15 2

Calculate the arithmetic mean of overtime hours during the month.

Ques 2. The following are the figures of profits earned by 1,400 companies during
2008-2009.

Profits(Rs. No. of
Lakhs) companies
300 500
500 300
700 280
900 120
1100 100
1300 80
1500 20

Calculate the average profit for all the companies.

 3. Continuous Series
(i) Direct Method:

1
x
where,
x denotesN
 f x
the mid point of various class interval
f denotes the frequency of each class
N = ∑f ; denotes the total frequency
(ii) Short Cut Method:
1
x  A
N
 f d

where,
d=x–A
x denotes the mid point of various class interval
A is assumed mean
f denotes the frequency of each class
N = ∑f ; denotes the total frequency
(iii) Step Deviation Method:
1
x  A
N
 f uh
where,
u = (x - A)/h
h denotes the width of class interval
A is assumed mean
N = ∑f ; denotes the no. of terms
Ques 1. Calculate mean for the following frequency table:

Weekly rent No. of persons

paying rent
200-400 6
400-600 9
600-800 11
800-1000 14
1000-1200 20
1200-1400 15
1400-1600 10
1600-1800 8
1800-2000 7
Ques 2. In an examination of 675 candidates the examiner supplied the following
information:

Marks obtained No. of

candidates
(less than)
10 7
20 39
30 95
40 201
50 381
60 545
70 631
80 675
Combined Arithmetic Mean

If we have the arithmetic mean and the number of observations of two or more
than two related groups, we can compute combined average of these groups by
applying the formula:

N1 X 1  N 2 X 2
X 12 
N1  N 2
X 12  Combined mean of the two groups
X 1  Arithmetic mean of the first group
X 2  Arithmetic mean of the sec ond group
N1  Number of terms in the first group
N 2  Number of terms in the sec ond group
QUESTIONS:

1.There are two branches of a company employing 100 and 80 employees respectively. If
arithmetic means of the monthly salaries paid by two branches are Rs. 4570 and Rs.
6750 respectively, find the arithmetic mean of the salaries of the employees of the
company as a whole.

2.The average turnover of 200 small and medium enterprises financed by ‘X’ bank in a
state is Rs.50 crores, and the average turnover of 300 small and medium enterprises
financed by ‘Y’ bank in the same state is Rs.60 crores. Find the combined mean for the
small and medium enterprises financed by both the banks.

3. The mean of marks in statistics of 100 students of a class was 72. The mean of marks
of boys was 75, while their number was 70. Find out the mean marks of girls in the class.
Ques. Six types of workers are employed in each of two workshops but at different rates
of wages as follows:

Workshop A No. of Workshop B No. of

Daily wages workers Daily wages workers
per worker per worker
92.50 2 93.00 11
93.50 14 93.25 50
94.00 20 93.50 8
93.00 7 94.25 10
94.25 6 94.50 10
94.00 1 95.00 2

In which of the two workshops is the average rate of wages per worker higher and by
how much?
Ques. Calculate mean from the following data pertaining to the profits(in crore Rs.) of
125 companies:

Profits(Rs. crore) No. of companies

(less than)
10 4
20 16
30 40
40 76
50 96
60 112
70 120
80 125
Correcting Incorrect Values:

Ques 1. The average weekly wage for a group of 25 persons working in a company was
calculated to be Rs.378.40. It was later discovered that one figure was figure was
misread as 160 instead of the correct value Rs.200. Calculate the correct average wage.

Ques 2. The mean of 200 observations was 50. Later on, it was discovered that two
observations were wrongly read as 92 and 8 instead of 192 and 88. Find out the correct
mean.
 Merits & Demerits
• Merits
– All values are used
– It has unique value & easy to calculate
– The sum of the deviations from the mean is 0
• Demerits
– The mean is affected by extreme values
E.g., average salary at a company
12,000; 12,000; 12,000; 12,000; 12,000; 12,000;
12,000; 12,000; 12,000; 12,000; 20,000; 390,000
Mean = $44,167
– It is not suitable for open end classes
 MEDIAN
The median is the measure of central tendency
which appears in the middle of an ordered
sequence of values. That is, half of the
observations in a set of data are lower than it
and half of the observations are greater than
it.
 1. Individual Series
• Arrange the data in increasing or decreasing
order.
• Median is given by:

( n  1)
Median= th term
2
Questions:
1.From the following data of wages of 7 workers, compute the
median wage:
2600, 2650, 2580, 2690, 2660, 2606, 2640
 2. Discrete Series
• Calculate the cumulative frequency.
• Find (N+1)/2th term.
• Select the cumulative frequency in which that
value lies.
• The value of the variable corresponding to
that cumulative frequency is the median.
2. Calculate the median for following data:

X f
45 10
55 20
65 20
75 15
85 15
95 20
 3. Continuous Series
• Calculate the cumulative frequency.
• The value corresponding to N/2th term gives the median class.
• Then median is calculated by the formula:
1N 
Median  l    cf   h
f  2 
where,
l  lower lim it of the median class
f  frequency of the median class
cf  cumulative frequency of the class preceeding
the median class
h  width of class int erval
3. Calculate the median for following data:

Class interval Frequency

10 - 15 11
15 – 20 20
20 – 25 35
25 – 30 20
30 – 35 8
35 - 40 6
4. Calculate the median from the following data pertaining to the profits (in crore Rs.) of
125 companies:

Profits (less than) No. of companies

10 4
20 16
30 40
40 76
50 96
60 112
70 120
80 125
• Merits
– Median is unique
– Median is less affected by extreme values as compared to
mean
– It can be used for open–end distribution
– Graphical presentation of median is possible
– Median is used for studying qualitative attributes
• Demerits
– For median, it is necessary to arrange the data
– It is not capable for further algebraic treatment
– It does not use each and every observation of the data set
 Mode
• The most frequent score in the distribution.

• A distribution where a single score is most frequent has one mode

and is called unimodal.

• A distribution that consists of only one of each score has n modes.

• When there are ties for the most frequent score, the distribution is
bimodal if two scores tie or multimodal if more than two scores
tie.
 Mode (con’t)

2
2 Number of Words Recalled in Performance Study
3
3
The mode is 4.
4
4
4
4
4
10
 Mode (con’t)

72 72 73 76 78
81 83 85 85 86
87 88 90 91 92

This distribution is bimodal.

1. Individual Series:
In Individual series we guess mode by inspection. We observe that term in the series
which occurs maximum number of times. This term is called mode.

2. Discrete Series:
In discrete series mode is that value of variable whose frequency is maximum.

3. Continuous Series:
The class interval that is corresponding to the maximum frequency is the modal class.
Then mode is calculated by the formula:
f1 f 0
z l h
2 f1  f 0  f 2
where,
l  lower lim it of mod al class
f1  frequency of mod al class
f 0  frequency of class preceeding mod al class
f 2  frequency of class suceeding the mod al class
h  width of mod al class
Ques 1. Find the mode of following data:

Class Frequency
0–5 29
5 – 10 195
10 – 15 241
15 – 20 117
20 – 25 52
25 – 30 10
30 – 35 6
35 – 40 3
40 – 45 2
Ques 2. Find the mode of following data:

Class Frequency
0 – 10 5
10 – 20 15
20 – 30 20
30 – 40 20
40 – 50 32
50 – 60 14
60 – 70 14
70 – 80 5
Merits of Mode:

• It is easy to understand. Sometimes it is found only by inspection.

• It is least affected by extreme values.
• It can also be located graphically.
• It is also useful when items related to fashion are considered.

Demerits of Mode:

• It is not based on all the observations.

• Equal intervals are needed for the calculation of mode.
Empirical relation between mean, median
and mode

The relationship between arithmetic mean, median and mode is

given by following formula:

Mode = 3 Median – 2 Mean

Ques 1. Find out an estimate of mode, when mean and median are 12 and 16.5

Ques 2. If mean = 26, mode = 28.5. Find an estimate of median.

 Measures of Dispersion(Why it is
important?)
• Since an average is a single value representing a
group of variables, it must be properly interpreted.
• An average may give us a value that does not exist in
data.
• At times an average may give absurd results.
• Average may fail to give us any idea about the
formation of the series.
 Absolute & Relative measures
• Measures of variation may be either absolute
or relative.
• Absolute measures are expressed in the same
statistical units as the original data is given.
• Relative measures, also known as “coefficient”
are pure numbers, independent of the units of
measurement.
 Measures of variation
• Range
• Quartile deviation
• Mean deviation
• Standard deviation
 Range
• It is defined as the difference between the value of the
smallest observation and the value of the largest observation
in the data.
• Range is given by,
Range = L – S
where, L is the largest value
S is the smallest value.
• Relative measure of range is given by,
Coefficient of range = L  S
LS
Ques 1. The following are the prices of shares of a company from Monday to
Saturday.

Day Price(Rs)
Monday 200
Tuesday 210
Wednesday 208
Thursday 160
Friday 220
Saturday 250

Calculate Range and Coefficient of range.

Ques 2. Calculate coefficient of range from the following data.

Profits(Rs. lakhs) No. of

Companies
10 – 20 8
20 – 30 10
30 – 40 12
40 – 50 8
50 – 60 4
 Quartiles
• Quartiles are the values which divides a
distribution into 4 equal parts.
• There are 3 quartiles Q1 , Q2 , Q3.
• Calculation is:
 iN 
Qi is given by  th term.
 4 
1  iN 
Then, Qi  l    cf   h
f  4 
 Quartile deviation

Quartile deviation is given by,

Q3  Q1
Q.D 
2
Q3  Q1
Coefficient of Q.D 
Q3  Q1
Ques 1. You are given the frequency distribution of 292 workers of a factory according
to their average weekly income. Calculate quartile deviation and its coefficient from the
following data:

Weekly Income No. of Workers

Below 350 8
350 – 370 16
370 – 390 39
390 – 410 58
410 – 430 60
430 – 450 40
450 – 470 22
470 – 490 15
490 – 510 15
510 – 530 9
530 & above 10
 Mean deviation
• Also known as average deviation.
• It is the average of the absolute deviations
taken from mean or median.
• So we have,
M.D from mean
M.D from median
 Individual Series
1
M .D( x )   xx
n
M .D( x )
Coefficient of M .D about mean 
x
1
M .D( M e )   x  Me
n
M .D( M e )
Coefficient of M .D about median 
Me
Ques 1. Calculate the average deviation and the coefficient of average deviation about
mean and median .

Income(Rs)
3000
4000
4200
4400
4600
4800
5800
 Discrete Series
1
M .D( x ) 
N
f xx

M .D( x )
Coefficient of M .D about mean 
x
1
M .D( M e ) 
N
f x  Me

M .D( M e )
Coefficient of M .D about median 
Me
 Continuous Series
1
M .D( x ) 
N
f xx

M .D( x )
Coefficient of M .D about mean 
x
1
M .D( M e ) 
N
f x  Me

M .D( M e )
Coefficient of M .D about median 
Me
where, x is the mid po int of class int ervals.
Ques 1. Calculate average deviation from mean and median from the following data.
Also calculate coefficients of average deviation.

Sales No. of days

(in thousand Rs.)
10 – 20 3
20 – 30 6
30 – 40 11
40 – 50 3
50 – 60 2
 Standard Deviation
• It is defined as the square root of the mean of the
squared deviations from the arithmetic mean
• It is denoted by Greek letter σ (sigma)
• Smaller the value of S.D, higher the stability of
the observation as well as homogeneity of series
• The square of standard deviation is called
variance
Variance = 
2
1. Individual series :

 
1
n
 
xx 
2
or
1
n
 2
x x
2

2. Discrete series :

 
N
1
 
f xx 
2
or
1
N
 f x2  x
2

where , N   f

3. Continuous series :

 
N
1
 
f xx 
2
or
1
N
f 2
x x
2

where , N   f
x  mid po int of class int erval
1. Ten students obtained following marks (out of 100). Calculate standard deviation.

5, 10, 20, 25, 40, 42, 45, 48, 70, 80

2. Calculate standard deviation from following data:

Daily Wages Frequency

30 2
50 10
70 12
90 15
110 20
130 13
150 12
170 10
190 4
3. Calculate standard deviation:

Size Frequency
0 – 10 1
10 – 20 2
20 – 30 4
30 – 40 3
 Coefficient of Variation
• Standard deviation was an absolute measure of
dispersion.
• C.V is relative measure of dispersion
corresponding to standard deviation
• C.V is used to compare the variability of two or
more data set

C.V   100
X
Ques. Calculate variance and coefficient of variation from following data.

Profits(less No. of
than) companies
10 8
20 20
30 40
40 70
50 90
60 100
Q1: An analysis of the monthly salaries paid to
employees in two companies X and Y, belonging to
the same industry, the following results.
company X company Y
No. of employees : 1200 1500
Average salary : Rs12000 Rs9000
S.D : Rs 200 Rs 225
Find that which company have greater variability and
which is more consistent.
Q3. The weekly sales of two products A and B were recorded as given below:

Product 59 75 27 63 27 28 56
A
Product 150 200 125 310 330 250 225
B

Find out which of the two shows greater fluctuations in sales.

Combined Standard deviation
Correcting Incorrect Values:
Ques1. The mean and standard deviation of a series of 17 items are 25 and 5
respectively. While calculating these measures a measurement 53 was wrongly read
as 35. Correct this error and find out the correct standard deviation.

Ques2. The mean and standard deviation of a sample of size 100 are found to be 40
and 10. At the time of calculation, two items were wrongly taken as 30 and 72 instead
of 3 and 27. Find the correct mean and correct standard deviation.
 Skewness
• Skewness means lack of symmetry or
departure from symmetry.
• A symmetric distribution has its mean,
median, mode equal and the frequency curve
is symmetrically situated about these values.
• When distribution has longer tail on right side,
it is positively skewed.
• When longer tail is on left side, it is negatively
skewed.
• If there is no skewness or the distribution is
symmetric like the bell-shaped normal curve then
the
mean = median = mode.
 Shape of a Distribution

Negatively-Skewed Symmetric Positively-Skewed

Mean < Median < Mode Mean = Median = Mode Mean < Median < Mode
(Longer tail extends to left) (Longer tail extends to right)
 Karl Pearson coefficient of
skewness
It is given by the formula:

Mean  Mode xz

S .K P  
S tan dard deviation 
Since, mod e is not always unique,
3( Mean  Median)
S .K P 
S tan dard deviation
Q1. Calculate Karl Pearson Coefficient of Skewness:

Marks Frequency
0 – 20 18
20 – 40 22
40 – 60 30
60 – 80 20
80 - 100 10
Q2. Calculate Karl Pearson Coefficient of Skewness:

Marks(Below) Frequency
20 8
40 20
60 50
80 64
100 70