Page: 1

14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
UNIT-III : MEASURES OF CENTRAL TENDENCY
An average or measure of central tendency gives a single representative
value for a set of usually unequal values. This value is the point around which all
the values cluster. So, the measure of central tendency is also called a measure of
central location.
Definition
An average is a value which is a representative of a set of data
Various important measures of central tendency are
A. Arithmetic mean
B. Geometric mean Mathematical Averages
C. Harmonic mean
D. Median and Quartiles
E. Mode Positional Averages
Objectives or Functions of an average
i. Averages provide a quick understanding of complex data.
ii. Averages enable comparison
iii. Average facilitate sampling techniques.
iv. Averages pave the way for further statistical analysis.
v. Averages establish the relationship between variables.
A. ARITHMETIC MEAN
Definition
Arithmetic mean is the total (sum) of all values divided by the number of
observations.
Calculation of Arithmetic mean for Raw data
When the observed values are given individually such as x1, x2, x3…. xn the
arithmetic mean is given by

Arithmetic mean 𝑋̅ = Total of all values

Number of the observations
= x1+ x2+x3+…. +xn = Σ xi
n n
̅
Example: Given 𝑋=1600 and n=5 find the total.
Σ xi= n * 𝑋̅= 5 *1600 =8000.

Example: Calculate the arithmetic mean for the following

1600, 1590, 1560, 1610, 1640, 10.
 Page: 2
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Solution:
1600 + 1590 + 1560 + 1610 + 1640+10
Arithmetic mean, 𝑋̅ = --------------------------------------------
6
8010
= --------- = 1335
6
Example: Calculate Arithmetic mean

S.No. 1 2 3 4 5 6 7 8 9 10
Sales in 1000’s(x) 34 55 45 62 48 57 28 57 62 78

Arithmetic mean, 𝑋̅ = 34+ 55 + 45 + 62 + 48 +57+28+57+62+78

10

= 526 = 52.6 (average sales)

10
Discrete data
Let xi, x2, x3…. xn be the n values of the variable x with corresponding frequencies
fi, f2, f3…. fn. then the arithmetic mean 𝑋̅= x1.f1 + x2. f2 + x3.f3 + …. + xn . fn
f1 + f2 + f3 + …. + fn
= Σ x i fi
Σ fi

Example: Calculate the arithmetic mean

x f xf
2 4 2x4= 8
4 6 24
6 10 60
8 12 96
10 8 80
12 7 84
14 3 42
Σ fi = Σ x i fi
50 = 394
Σ x i fi 394
Arithmetic mean, 𝑋̅= -------- = -------- =78.8
Σ fi 50
 Page: 3
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Continuous data
Let mi, m2, m3…. mn be the mid values of the class interval of the variable x
with corresponding frequency fi, f2, f3…. fn. then
the arithmetic mean 𝑋̅= m1.f1 + m2. f2 + m3.f3 + …. + mn . fn
f1 + f2 + f3 + …. + fn
Σ mi fi
= --------
Σ fi

Example: Calculate the arithmetic mean

Class m f mf
interval(x)
20-40 (20+40)/2 4 120
= 30
40-60 50 6 300
60-80 70 10 700
80-100 90 12 1080
100-120 110 8 880
Σ fi = Σ mi fi
40 = 3080
Σ mi fi 3080
̅
Arithmetic mean, 𝑋= -------- = -------- = 77.0
Σ fi 40

Merits and Demerits of Arithmetic Mean:

Merits:
i) It is rigidly defined.
ii) It is easy to understand and easy to calculate.
iii) If the number of items is sufficiently large, it is more accurate and more reliable.
iv) It is a calculated value and is not based on its position in the series.
v) It is possible to calculate even if some of the details of the data are lacking.
vi) Of all averages, it is affected least by fluctuations of sampling.
vii) It provides a good basis for comparison.

Demerits:
i) It cannot be obtained by inspection nor located through a frequency graph.
ii) It cannot be in the study of qualitative phenomena not capable of
numerical measurement i.e. Intelligence, beauty, honesty etc.,
iii) It can ignore any single item only at the risk of losing its accuracy.
iv) It is affected very much by extreme values.
v) It cannot be calculated for open-end classes.
vi) It may lead to fallacious conclusions, if the details of the data from
which it is computed are not given.
 Page: 4
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

B. MEDIAN
✓ It is the value which divides the data into two equal parts.
✓ 50% of the observations will be less than median value and 50% of the
values will be more than the median value.

Calculation for Raw data

Median = value of (n+1)/2 th observation after the values are arranged in ascending
order of magnitude.
For example, the median of 20,30,35,64,23,46,78,34,20
Arranging the data in ascending order; 20,20,23,30,34,35,46,64,78

Md = value of [(9+1)/2 = 5th observation] = 34

Suppose the given number of observations is even then median will be the average
of two central values
For example, if the data is the median of 20,30,35,64,23,46,78,34,20,56
Arranging the data in ascending order : 20,20,23,30,34,35,46,56,64,78
Md = value of (10+1)/2 =5.5th observation
= (value of 5th observation + value of 6th observation)/2
= (34+35)/2 =34.5

Discrete data
Md = value of x corresponding to the cumulative frequency just greater than or
equal to N/2
i) Arrange the data is in ascending order
ii) Find the c.f.; Calculate N/2
iii) In c.f. column see the value just ≥ N/2
iv) Md= value of x corresponding to this c.f.

Example: Find the median

x f
2 4
4 6
6 10
8 12
10 8
12 7
14 3
Σ fi = 50
 Page: 5
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Solution:
x f c.f.
2 4 4
4 6 10
6 10 20
8 12 32
10 8 40
12 7 47
14 3 50
Σ fi = 50
N/2= 50/2= 25.5 , Md=8

Continuous data
Md = L + {(N/2 – c.f) x c/f}
where
L= lower limit of the median class
c =class interval of the median class
f =frequency of the median class
c.f.= cumulative frequency of the class preceding the median class
N= Σ fi
Md class is the class corresponding to the c.f. just ≥ N/2.

Example: Find the median

Class f
interval(x)
20-40 4
40-60 6
60-80 10
80-100 12
100-120 8
Σ fi =
40

Solution:
Class f c.f
interval(x)
20-40 4 4
40-60 6 10
60-80 10 20
80-100 12 32
100-120 8 40
Σ fi = 40
 Page: 6
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
• N/2= 40/2 =20
• Median class is 60-80
• L=60, c=80-60=20, f= 10, c.f= 10
• Md = L + {(N/2 – c.f) x c/f} = 60 + {(20 -10)x (20/10)}
= 60 + {10x2} = 60+20 = 80.

Example: Find the median

Marks No. of c.f.
students
10-25 6 6
25-40 20 26
40-55 44 70
55-70 26 96
70-85 3 99
85-100 1 100
Σ fi = 100

• N/2= 100/2=50
• Median class is 40-55
• L= 40, f = 44, c = 55 – 40 =15, c.f. = 26
• Md = L + {(N/2 – c.f) x c/f}
= 40 + {[ 50 – 26] x 15/44}
=40 + {(24 x15)/44}
=40 + [360/44]
= 40+8.18 = 48.18

QUARTILES

✓ It is the value which divides the data into FOUR equal parts.
✓ There are three quartiles.
✓ Q1, the first quartile or the lower quartile divides the data in such a way that
25 percent of the observations will be less than Q1 value and 75% of the
values will be more than the Q1 value.
✓ Q3, the Third quartile or upper quartile divides the data in such a way that 75
percent of the observations will be less than Q3 value and 25% of the values
will be more than the Q3 value
✓ The second quartile is nothing but the median.
✓ 50% of the observations will be less than median value and 50% of the
values will be more than the median value.
 Page: 7
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

Calculation for Raw data

✓ Median = value of (n+1)/2 th observation in ascending order data.

✓ Q1 = value of (n+1)/4 th observation in ascending order data.
✓ Q3 = value of 3(n+1)/4 th observation in ascending order data.

For example, the median of 20,30,35,64,23,46,78,34,20

Arranging the data in ascending order : 20,20,23,30,34,35,46,64,78
Md = value of (9+1)/2 =5th observation
= 34

Example: Find Q1 and Q3, 20,30,35,64,23,46,78,34,20

Arranging the data in ascending order: 20,20,23,30,34,35,46,64,78
Q1 = value of (9+1)/4 =2.5th observation
= value of 2nd observation + 0.5(3rd value-2nd value)
= 20+0.5(23 -20) =20 + 0.5 x 3 = 20+ 1.5 = 21.5
Q3 = value of 3(9+1)/4 =7.5th observation
= 7th observation + 0.5 (8thvalue – 7th value)
= 46 + 0.5 (64-46) =46 +( 0.5 x 18) = 46 + 9 = 55

Suppose the given number of observations is even then median will be the
average of two central values.
Example: Find the median of 20,30,35,64,23,46,78,34,20,56.
Arranging the data in ascending order:
20,20,23,30,34,35,46,56,64,78
Md = value of (10+1)/2 =5.5th observation
= (value of 5th observation + value of 6th observation)/2
= (34+35)/2 =34.5

Example: Find Q1 and Q3 20,30,35,64,23,46,78,34,20,56

Solution: Arranging the data in ascending order: 20,20,23,30,34,35,46,56,64,78

Q1 = value of (10+1)/4 =2.75th observation

= 2nd value + 0.75 (3rd value – 2nd value)
= 20 + 0.75 (23-20)
= 20 + (0.75 x3) = 20 +2.25 =22.25
Q3= value of 3 (n+1\4)th observation
= (3 x2.75 =8.25th ) observation
= 8th value + 0.25 (9th value - 8th value)
= 56 + 0.25 (64-56)
=56 + 0.25 (8) = 56 + 2 = 58
 Page: 8
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Discrete data
o Md = value of x corresponding to the cumulative frequency just ≥ N/2
o Q1= value of x corresponding to the cumulative frequency just ≥ N/4
o Q3= value of x corresponding to the cumulative frequency just ≥ 3N/4

• Arrange the data is in ascending order

• Find the c.f.
• Calculate N/2
• In c.f. column see the value greater than or equal to N/2
• Md= value of x corresponding to this c.f.

Example: Find the median and the quartiles

x f
2 4
4 6
6 10
8 12
10 8
12 7
14 3
Σ fi = 50

Solution:
x f c.f.
2 4 4
4 6 10
6 10 20
8 12 32
10 8 40
12 7 47
14 3 50
Σ fi = 50
• N/2= 50/2= 25; Therefore Md=8
• N/4 =50/4 = 12.5
Q1= value of x corresponding to the cumulative frequency just greater than or
equal to N/4 = 20.
Q1 = 6
• 3 N/4 = 37.5
 Page: 9
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Q3= value of x corresponding to the cumulative frequency just greater than
or equal to 3N/4; Q3= value of x corresponding to the cumulative
frequency just greater than 37.5 i.e.,40
Q3 = 10

Continuous data
Md = L + {(N/2 – c.f) x c/f}
where L= lower limit of the median class
= class interval of the median class
f = frequency of the median class
c.f. = c.f. of the class preceding the median class
N= Σ fi
Md class is the class corresponding to the c.f. just ≥ N/2.

Q1 = L1 + {(N/4 – c.f1) x c1/f1}

L1 lower limit of the Q1 class
c1 class interval of the Q1 class
f1 frequency of the Q1 class
c.f.1 cumulative frequency of the class preceding the Q1 class
N= Σ fi
Q3 class is the class corresponding to the c.f. just greater than or
equal to N/4.

Q3 = L3+ {(3N/4 – c.f3) x c3/f3}

L3 lower limit of the Q3 class
c3 class interval of the Q3 class
f3 frequency of the Q3 class
c.f.3 cumulative frequency of the class preceding the Q3 class
N= Σ fi Q3 class is the class corresponding to the c.f. just greater
than or equal to 3N/4.

Example: Find Median:

Class f
interval(x)
20-40 4
40-60 6
60-80 10
80-100 12
100-120 8
Σ fi = 40
 Page: 10
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Solution:
Class f c.f
interval(x)
20-40 4 4
40-60 6 10
60-80 10 20
80-100 12 32
100-120 8 40
Σ fi = 40
o N/2= 40/2 =20
o Median class is 60-80
o L=60, c=80-60=20, f= 10, c.f= 10
o Md = L + {(N/2 – c.f) x c/f}
= 60 + {(20 -10) x (20/10)}
= 60 + {10x2}
= 60 + 20 = 80

marks No. of C.f.

students
10-25 6 6
25-40 20 26
40-55 44 70
55-70 26 96
70-85 3 99
85-100 1 100
Σ fi = 100

o N/2= 100/2=50
Median class is 40-55
L= 40, f = 44, c = 55 – 40 =15, c.f. = 26
Md = L + {(N/2 – c.f) x c/f}
= 40 + {[ 50 – 26] x 15/44}
=40 + {(24 x15)/44}
=40 + [360/44]
= 40+8.18 = 48.18

o Q1 = L1 + {(N/4 – c.f1) x c1/f1}

Q1 class 25-40, L1 = 25, c1 = 40 – 25 =15, f1= 20, c.f1=6
Q1= 25 + {(25- 6) (15/20)}
= 25 + {19 x 15 /20}
= 25 + 19x0.75
= 25 + 14.25 = 39.25
 Page: 11
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

o Q3 = L3+ {(3N/4 – c.f3) x c3/f3}

3N/4 = 3x25 = 75
Q3 class is 55-70
L3 = 55, c3 = 70 -55 =15, f3=26, c.f3 = 70
Q3 = L3+ {(3N/4 – c.f3) x c3/f3}
= 55 + {(75 – 70 ) x 15 / 26}
= 55 + { 5 x 0.57}
= 55 + 2.88 = 57.88.

Merits of Median:
i) Median is not influenced by extreme values because it is a positional average.
ii) Median can be calculated in case of distribution with open end intervals.
iii) Median can be located even if the data are incomplete.
iv) Median can be located even for qualitative factors such as ability, honesty etc.
Demerits of Median:
i) A slight change in the series may bring drastic change in median value.
ii) In case of even number of items or continuous series, median is an
estimated value other than any value in the series.
iii) It is not suitable for further mathematical treatment except its use in mean
deviation.
iv) It does not consider all the observations.

C. MODE
Mode is the value of x which is repeated more often or more frequently.

Raw data
Mode is found by observation. The number of times each value occurs ids
noted and the value which is repeated maximum number of times is the mode.

Example: Find mode 20,30,35,64,23,46,78,34,20,56

Mode is 20 as it is repeated twice while other values are repeated only once.

Case i) Unimodal – only one mode

In the series 40, 30, 20, 17, 18, 32, 29, 23, 17, 17, 24, 24, 12 mode is 17.
Case ii) Bimodal – two modes
In the series 40, 30, 20, 17, 18, 32, 29, 23, 17, 17, 24, 24, 12, 24, 23
Mode-1 =17, mode-2 is 24,
Case iii) No model:
In the series 40, 34, 45, 45, 34, 40 there is no mode or mode is ill-defined.
 Page: 12
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

Discrete data

Mode = value of x corresponding to the highest frequency

Case i) Unimodal – only one mode

x f
2 4
4 6
6 10
8 12
10 8
12 7
14 3
Σ fi = 50

Mode = value of x corresponding to the highest frequency 12

Mode =8.

Continuous data

Mode = l + [{(f1-f0)/(2f1- f0-f2) }xc]

where f1 is the frequency of the modal class
f0 is the frequency of the class preceding the modal class
f2 is the frequency of the class succeeding the modal class
c is the class interval of the modal class
l is the lower limit of the modal class

Modal class the class corresponding to the highest frequency.

marks No. of
students
10-25 6
25-40 20 f0
40-55 44 f1
55-70 26 f2
70-85 3
85-100 1
Σ fi = 100
 Page: 13
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

Modal class is 40 -55

L= 40, f1= 44, f0= 20, f2= 26, c =55-40 =15.

Mode = l + [ {(f1-f0)/ (2f1- f0-f2)} xc]

= 40 + [{(44 – 20)/ (2x44 – 20 – 26)}x 15]
= 40 + {[ 24/ (88-46)]x15}]
= 40 + [(24/42) x15]
= 40 + [0.5714 x15]
= 40 + 8.57
= 48.57.

Relationship between mean, median and mode : Mode = 3median - 2 mean

D. GEOMETRIC MEAN

Definition:
Geometric mean of n observations is the nth root of product of n observations.
If x1, x2, x3… xn be the n observations the G.M is (x1 . x2. x3.… .xn) (1/n)
For example, the G.M. of 2,4,8 is (2x4x8) (1/3) = (64) (1/3) = 4.

But in practice we use log to find G.M.

Raw Data
If x1, x2, x3… xn be the n observations
G.M. = (x1* x2* x3*… *xn) (1/n)
Taking log on both sides
Log (G.M.) = (1/n) [ log x1 + log x2+ log x3+… + log xn]
= (1/n) Σ [log xi]
G.M. = Antilog { (1/n) Σ [log xi] }

Example: Find the geometric mean for the following x: 3,6,24,48

x Log x
3 0.4771
6 0.7782
24 1.3802
48 1.6812
Σ [log xi]
=4.3167
G.M. = Antilog {(1/n) Σ [log xi]}
= Antilog {(1/4) x 4.3167}
= Antilog {1.0792} = 12.00
 Page: 14
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

Discrete data:
Let x1, x2, x3…. xn be the n values of the variable x with corresponding frequency
Σ [f log x]
f1, f2, f3…. fn. then G.M. = Antilog( )
Σf
Find the geometric mean for the data given below
x 10 15 25 40 50
f 4 6 10 7 3

Solution

x f log x f log x
10 4 1.0000 4.0000
15 6 1.1761 7.0566
25 10 1. 3979 13.9790
40 7 1.6021 11.2147
50 3 1.6990 5.0970
30 Σ [f log x]=41.3473

Σ [f log x]
G.M. = Antilog( ) =A.L. [41.3473/30] = A.L.(1.3782) = 23.89
Σf

Continuous data:
Let m1, m2, m3…. m n be the midpoints of the n classes of the variable x
with corresponding frequency f1, f2, f3…. fn. then
Σ [f log m]
G.M. = Antilog( )
Σf

Example: Compute the geometric mean

Marks (x) 0-10 10-20 20-30 30-40 40-50
No. of students(f) 5 7 15 25 8

Solution:

x f m log m f log m
0-10 5 5 0.6990 3.4950
10-20 7 15 1.1761 8.2327
20-30 15 25 1.3979 20.9685
30-40 25 35 1.5441 38.6025
40-50 8 45 1.6532 13.2256
Σf =60 84.5243
 Page: 15
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
Σ [f log m]
G.M. = Antilog( ) =A.L. [84.5243/60] =A.L. [1.4087] = 25.63
Σf

E. HARMONIC MEAN (HM)

Definition:
Harmonic mean is the reciprocal of the arithmetic mean of the reciprocal
of observation.
Example: Find HM for the data: 8, 10,40,26:
o Reciprocals: 8 is 1/8, 10is 1/10, 40 is 1/40 ,26 is 1/26
o A,M. of 1/8, 1/10,1/40 and 1/26 is (1/8 + 1/10+1/40+1/26)/4
o H.M. = 4/(1/8 + 1/10+1/40+1/26)

Raw data
n
If x1, x2, x3… xn be the n observations, then H.M. =
Σ(1/x)
Example: Find the harmonic mean for the following x: 3, 6, 24, 48
x 1/x
3 0.3333
6 0.1667
24 0.0417
48 0.0208
0.5625
n 4
H.M. = = = 7.11
Σ(1/x) (0.5625)

Discrete data:
Let xi, x2, x3…. xn be the n values of the variable x with corresponding
Σf
frequencies fi, f2, f3…. fn, then H.M. = [ ]
Σ(𝑓/𝑥)

Example: Find the harmonic mean for the data given below
x 10 15 25 40 50
f 4 6 10 7 3
Solution:
x f f/x
10 4 0.4000
15 6 0.4000
25 10 0.4000
40 7 0.1750
50 3 0.0600
 Page: 16
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
30 1.4350

Σf
H.M. = [ ] = 30/(1.4350) = 20.91
Σ(𝑓/𝑥)

Continuous data:
Let m1, m2, m3…. m n be the n values of the variable x with corresponding
Σf
frequency f1, f2, f3…. fn. then H.M. = [ ]
Σ(𝑓/𝑚)
Example: Compute the geometric mean

Marks (x) 0-10 10-20 20-30 30-40 40-50

No. of students(f) 5 7 15 25 8

Solution:

x f m f/m
0-10 5 5 1.0000
10-20 7 15 0.4667
20-30 15 25 0.6000
30-40 25 35 0.7143
40-50 8 45 0.1778
Σf =60 2.9588

Σf
H.M. = [ ]= 60/ 2.9588 = 20.28
Σ(𝑓/𝑚)

Weighted averages
The relative importance given to the given to the values is the weights W

Weighted arithmetic mean

Σ [xw]
̅
𝒙w = x is the variable and w is the weights
Σw
Find the weighted arithmetic mean for the following data
x w
8 2
12 5
25 1
13 2
45 3
 Page: 17
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics

Solution:
x w xw
8 2 16
12 5 60
25 1 25
13 2 26
45 3 135
13 262

Σ [xw]
̅w =
𝒙 = 262 /13 =20.15;
Σw
Σ [w log x]
Weighted G.M. = Antilog( )
Σw
Example: Calculate weighted geometric mean
commodity A B C D
weight 1 6 3 2
price 5 17 30 42
Solution:
x w Log x w logx
5 1 0.6990 0.6990
17 6 1.2304 7.3824
30 3 1.4771 4.4313
42 2 1.6232 3.2464
12 15.7591

Σ [w log x]
Weighted G.M. = Antilog( )
Σw
[15.7591]
= Antilog( ) =A.L. (1.3133) = 20.57
12

Σw
Weighted H.M. = [ Σ(𝑤/𝑥)]

Example: An aeroplane flies around a square the sides of which measures 100 km
each, it covers the first side at an average speed of 100 km. /hr. the second side at
200km/hr and the third with 300 kms/hr and the fourth side at 400 kms./hr. Use the
correct mean to find the average speed round the square.
Solution:
The average speed round the entire square is the H.M of 100, 200, 300, 400.
 Page: 18
14BGE14A: Allied: Statistics-I UNIT-III Handled & Prepared by: Dr.S.RaviSankar & Dr.P.Vasanthamani
I BSc Geography (English Medium) Dept.of Statistics
n 4
H.M. = [ Σ(1/𝑥) ] = 1 1 1 1
+ + +
100 200 300 400

4
= 0.0100+0.0050+0.0033+0.0025
H.M. = 4 / 0.0208 = 192 kms, /hr
Example: You can take a trip which entails travelling 900 kms, by train at an
average speed of 60km. /hr., 3000 kms by ship at an average speed of 25km./hr.,
400 kms by plane at 350km./hr. and finally 15 kms by taxi at an average speed of
25km./hr, what is the average speed for the entire distance.

Mode of Distance Speed (x) w/x

travel travelled(w)
Train 900 60 15.0000
Ship 3000 25 120.0000
Plane 400 350 1.1429
taxi 15 25 0.6000
4315 136.7429
Weighted H.M. is the best average to find the average speed
Σw 4315
Weighted H.M. = [ Σ(𝑤/𝑥)] =[ 136.7429] = 31.56
The average speed of the entire distance is 31.56 kms. /hr.

Characteristics or desirable properties of a good average.

A measure is said to be a good average if it possesses the following characteristics:
i) It should be simple to understand and easy to calculate.
ii) An average should be rigidly defined.
iii) It should be based on all items.
iv) It should not be unduly affected by extreme values.
v) It should lend itself for algebraic manipulation.
vi) It should have sampling stability.
Arithmetic Mean is the best measure among the measures of central tendency,
because it possesses almost all the characteristics of a good average.
@@@ End of UNIT-III @@@