INTRODUCTION

Central tendency is a method of describing the spread of the distribution of scores around a

central measure of the frequency distribution. A measure of central tendency is a single value

that attempts to describe a set of a data by identifying the central position, they are also classed

as summary statistics. The three most commonly used measures of central tendency or

‘averages’ are: Arithmetic Mean, Median, Mode. And they are valid measures of central

tendency, but under different conditions.

Some measure of central tendency become more appropriate to use than other

OBJECTIVES OF AVERAGES

1. To present huge data in a summarized form: It is difficult to grasp a large amount of

data or numerical figures. Averages summaries such data into a single figure which makes it

easier to understand and remember.

2. To facilitate comparison: Averages are very helpful for making comparative studies as

they reduce the mass of statistical data to a single figure or estimate.

3. To facilitate further statistical analysis: Various tools of statistical analysis like standard

deviation, correlation etc. are based on averages.

4. To trace precise relationship: Averages are helpful and even essential when it comes to

establishing relationships between different groups of data or variable.

ESSENTIALS OF A GOOD AVERAGE AND MEASURE OF CENTRAL TENDENCY

1. It should be rigidly defined: An average should be clear and there should be only one form

of interpretation. It should have a definite and fixed value irrespective of method of

calculations or formulae used.

2. It should be based on all observations: Average should be calculated by taking into

consideration each and every item of the series. If it is not based on all observations, it will

not be representative of the whole group.

1
 3. It should not be affected much by extreme values: The value of an average should not be

affected much by extreme values. One or two very small or very large values should not

unduly affect the value of the average significantly.

4. It should be least affected by fluctuations of sampling: An average should possess sampling

stability i.e. If we take two or more samples from a given population and compute averages

for each, then the values thus obtained from different samples should not differ much from

each other.

TYPES OF MEASURES CENTRAL TENDENCY

I. Mean

II. Median

III. Mode

MEAN: There are three (3) kinds of mean, they are:

I. Arithmetic Mean

II. Harmonic Mean

III. Geometric Mean Arithmetic

ARITHEMETIC MEAN

To find arithmetic mean add all the values all terms and then divide sum by the number of

terms, quotient is the arithmetic mean.

Sample mean: If X1, X2 …Xn are data values then arithmetic mean is given by

Frequency Distribution: Let X1, X2 …Xn are class marks and the corresponding frequencies are

F1, F2 …Fn, then arithmetic mean is given by

𝑁 = ∑ 𝑓𝑖

∑𝑛1 𝑓𝑖 𝑥𝑖
𝑋̅ =
𝑁

2
 PROPERTIES OF ARITHEMETICS MEAN

1. Arithmetic mean is NOT independent of change of origin If each observation of a series

is increased (or decreased) by a constant, then the mean of these observations is also increased

(or decreased) by that constant.

2. Arithmetic mean is NOT independent of change of scale If each observation of a series

is multiplied (or divided) by a constant, then the mean of these observations is also multiplied

(or divided) by that constant.

Merits of Arithmetic Mean

1. It is based on all observations i.e. it takes into consideration all the values in a given series. It

is considered to be more representative of the distribution.

2. Its value is always definite and it is rigidly defined.

3. It is capable of further algebraic treatment. It is widely used in the computation of various

statistical measures such as standard deviation, correlation etc.

Demerit of Arithmetic Mean

1. It is affected by extreme values: Since arithmetic mean is calculated using all the items of a

series, it can be unduly affected by extreme values i.e. very small or very large items.

2. It may give absurd results: For example, if a teacher says that average number of students in a

class is 28.75, it sounds illogical.

3. It cannot be obtained graphically like median or mode.

Geometric Mean is useful to average relative changes, averaging ratios and percentages. It is

theoretically the best average for construction of index number. But it should not be used for

measuring absolute changes.

Merits of Geometric Mean

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

2. It is not much affected by sampling fluctuations.

3
 Demerits of Geometric Mean

1. It is not easy to understand & not easy to calculate

2. It is not well defined.

Harmonic Mean: is another important mean is the harmonic mean which is used for averaging

the rates.

Merits of Harmonic Mean

1. It is rigidly defined.

2. It is easy to understand & easy to calculate.

Demerits of Harmonic Mean

1. It is not easy to understand & not easy to calculate.

2. It cannot be calculated if any observations are missing

MEDIAN

The point or the value which divides the data in to two equal parts, or when the data is arranged

in numerical order.

The data must be ranked (sorted in ascending order) first. The median is the number in the

middle. Depending on the data size we define median as:

It is the middle value when data size N is odd. It is the mean of the middle two values, when

data size N is even.

Steps for Calculating Median

Step1: First arrange the data in ascending order.

Step2: Use the given formula to calculate the median.

where N = Total number of observations.

4
 PROPERTIES OF MEDIAN

1) The sum of absolute deviations of items from the median (ignoring the signs) is the minimum.

i.e Σ|X-Median| is minimum.

2) Median is a positional average so is not affected by change in extreme values.

Merits of Median

➢ Its value is always definite and it is rigidly defined.

➢ It is not affected by extreme values.

➢ It can be obtained graphically using ogives.

➢ It is appropriate for qualitative data.

Demerits of Median

➢ It is not based on all observations.

➢ It is not capable of further algebraic treatment.

➢ It is affected by fluctuations of sampling.

➢ It requires arrangement of data in ascending or descending order of magnitude.

MODE

Mode is defined as the value occurring most frequently in a given series and around which

other items of the set cluster most densely. The word mode has been derived from the French

word ‘la Mode’ which signifies the most fashionable values of a distribution, because it is

repeated the highest number of times in the series.

𝒇𝟏 −𝒇𝟐
𝑴𝑶𝑫𝑬 = 𝑳 + (𝟐𝒇 ) 𝒄 … For Grouped Data
𝟏 −𝒇𝟎 −𝒇𝟐

5
 Merits of Mode

➢ It is not affected by values of extreme items.

➢ It can be obtained graphically using histogram.

➢ It can be used to describe quantitative as well as qualitative data.

➢ It can be calculated even in case of open-ended distributions without finding class limits.

Demerits of Mode

➢ It is not rigidly defined.

➢ It is not based on all observations.

➢ It is not capable of further algebraic treatment.

6
 LITERATURE REVIEWS

The scholastic development of average most often begins in the primary grades with the

concept of mode, followed by midrange and median. McGrath & McClain (2002), their

research work indicates most students view the arithmetic mean as a procedure and often do

not understand it as a fair-share distribution of the data or as the centre-of-balance of the data

set. Mokros & Russell (1995), Studies indicate that when early primary grade students are first

introduced to data sets they have difficulties seeing the data as a whole and focus on the aspects

of the individual data points, also, Gonzales and Ottenbacker (2001), their studies indicate the

idea of recognizing trends or representativeness of data occurs for most students around the

third grade. This intuitive sense of average is most often expressed as “most” or

“middle,” which are ideas related to the formal averaging concepts of mode and median,

respectively.

Golba (2000), Statisticians rely heavily on measurements of central tendency as they examine

data and produce visualizations that help others to understand complex number systems. For

example, a statistician who works in pure mathematics produces algorithms to predict results

of a trial based on the central tendencies that past data sets exhibit.

7
 METHODOLOGY

Arithmetic Mean of ungrouped data

It is defined as the sum of the values of all observations divided by the number of observations.

In general, if there are N observations as X1, X2, …………Xn are data values then arithmetic

mean is given by

And it is written in a simpler form

EXAMPLE 1: The Marks obtained in 10 class tests are 25, 20, 20, 9, 16, 10, 21, 12, 8, 13.

(Source: F.Y.B. Sc Statistical note, paper 1unit III)

SOLUTION

Arithmetic mean for grouped data:: Let X1, X2, ………………Xn are class marks and the

corresponding frequencies are f1, f2,……………fn, then arithmetic mean is given by

EXAMPLE: The following data represents income distribution of 100 families, Calculate

mean income of 100 families.

Income in ‟00 30-40 40-50 50-60 60-70 70-80 80-90 90-100

Rs.

No. of families 8 12 25 22 16 11 6

(Source: F.Y.B. Sc Statistical note, paper 1unit III)

8
 SOLUTION

Class interval Class mark(xi) No of family (fi) Fixi

30-40 35 8 280

40-50 45 12 540

50-60 55 25 1375

60-70 65 22 1430

70-80 75 16 1200

80-90 85 11 935

90-100 95 6 570

⅀fi=100 ⅀fixi=6330

N =100

Mean =

Harmonic Mean

HM= N

Where N is the number of items or observations in the series 1, 2 ... n.

9
EXAMPLE: If a man travels 200km each on three days at speeds of 60,50,40km/hr respectively, his

average speed is given by the HM of the three speed rates as.(Source: Introduction to statistical methods

1,page 69-70 by Gabrie1 O.A, Janet O.O, James O.A)

SOLUTION
HM = N

= 3

= 3

10 +12 +15

600

=48.65Km/h

GEOMETRIC MEAN

GM=

If 1, 2 ... 𝑋𝑛 are the observations and n is the number of items /observations.

EXAMPLE

The geometric mean of 4,8,16.(Source: Introduction to statistical methods 1,page 66 by Gabrie1 O.A,

Janet O.O, James O.A)

SOLUTION

GM=

=8

10
 MEDIAN FOR UNGROUPED DATA

The median of ungrouped data is found easily if the items are first arranged in order of

magnitude and reading the value of middle observation.

th

EXAMPLE: Determine the median from the data in the table below:

Size(X) 5 6 7 8 9 10 11

No of pairs(ƒ) 30 50 300 950 750 250 49

(Source: Introduction to statistical methods1, page 73 by Gabrie1 O.A, Janet O.O, James O.A)

SOLUTION

Size(X) No of pairs(ƒ) Cumulative Total

5 30 30

6 50 80

7 300 380

8 950 1330

9 750 2080

10 250 2330

11 49 2379

⅀2379

Median=(

=1190th item

=8

11
Since the items are already arranged in ascending order(size-wise), the size of 1190th item is

easily determined by constructing the cumulative frequency.

Thus, the median size of shoes sold is 8, the size of the 1190th item.

MEDIAN OF GROUPED DATA

The determination of median of continuous grouped data is a little bit more involved. The

median is given as

𝑁
− 𝐶𝐹
𝑀𝐸𝐷𝐼𝐴𝑁 = 𝐿 + ( 2 )𝑐
𝑓

Where L=lower class boundary of the median class

N=total number of observation or items or cases

CF= cumulative frequency of the class before (above) the median class

c= class of the median class size

Ƒ= frequency of the median class

In the cases of continuous grouped data, it is ideal to locate the median class using and not

i.e. the median is the item in this case. This is the frequencies lose their individuality

and the effort now is to find a point on a curve where half the frequencies are above and half

below.

EXAMPLE: Find the median from the data in the table below.

Class 6-10 11-15 16-20 21-25 26-30 31-35 36-40 41-45

intervals

Frequency(ƒ) 225 240 117 52 10 6 3 2

(Source: Introduction to statistical methods1, page 74-75-76 by Gabrie1 O.A, Janet O.O, James O.A)

12
S0LUTION

Class intervals Frequency(ƒ) Class boundaries Cumulative

frequency

6-10 225 5.5-10.5 225

11-15 240 10.5-15.5 465

16-20 117 15.5-20.5 582

21-25 52 20.5-25.5 634

26-30 10 25.5-30.5 644

31-35 6 30.5-35.5 650

36-40 3 35.5-40.5 653

41-45 2 40.5-45.5 655

⅀=655

N=655 F=240 L=10.5 CF=225 Median class =11-15

Median=

=327.5th item

That is, the median class is the class in which the 327.5th item lies which is class ‘’11-15’’. This

is because the cumulative frequency of 465 covers items 226-465 between which 327’5th item

lies. Then,

L=10.5 N=665 CF=225 c=5 (15.5-10.5=5) ƒ=240

𝑁
−𝐶𝐹
𝑀𝐸𝐷𝐼𝐴𝑁 = 𝐿 + ( 2 )𝑐
𝑓

655
− 225
𝑀𝐸𝐷𝐼𝐴𝑁 = 10.5 + ( 2 )×5
240

13
 327.5 − 225
= 10.5 + ( )×5
240

102.5
= 10.5 + ( )×5
240

= 10.5 + 2.14

= 12.64

MODE OF GROUPED DATA

The mode is the most frequent data value. Mode is the value of the variable which is

predominant in the given data series. Thus in case of discrete frequency distribution, mode is

the value corresponding to maximum frequency. Sometimes there may be no single mode if no

one value appears more than any other. There may also be two modes (bimodal), three modes

(trimodal), or more than three modes (multi-modal).

𝒇𝟏 −𝒇𝟐
𝑴𝑶𝑫𝑬 = 𝑳 + (𝟐𝒇 ) 𝒄 … For Grouped Data
𝟏 −𝒇𝟎 −𝒇𝟐

Where L= lower class boundaries of the modal class

Ƒ0= frequency of the above (before) the modal class

Ƒ1=frequency of the modal class

Ƒ2=frequency of the class below (after) the modal class

c= class size of the modal class

EXAMPLE: Determine the mode of the data in the table.

Class 15-18 19-22 23-30 27-30 31-34 35-38

interval

frequency 6 18 19 12 5 4

(Source: Introduction to statistical methods1, page 79-80-81 by Gabrie1 O.A, Janet O.O, James O.A)

14
SOLUTION

Class interval Frequency Class boundary

15-18 6 14.5-18.5

19-22 18 18.5-22.5

23-26 19 22.5-26.5

27-30 12 26.5-30.5

31-34 5 30.5-34.5

35-38 4 34.5-38.5

In the given data 23-26 is the modal, since it has the highest frequency,

L=22.5, ƒ0=18, ƒ1=19, ƒ2= 12, c=4(i.e. 26.5-22.5)

𝒇𝟏 −𝒇𝟐
𝑴𝑶𝑫𝑬 = 𝑳 + (𝟐𝒇 ) 𝒄 … For Grouped Data
𝟏 −𝒇𝟎 −𝒇𝟐

𝟏𝟗−𝟏𝟖
𝑴𝑶𝑫𝑬 = 𝟐𝟐. 𝟓 + (𝟐(𝟏𝟗)−𝟏𝟖−𝟏𝟐) × 𝟒

𝟏
= 𝟐𝟐. 𝟓 + ( ) × 𝟒
𝟖

= 𝟐𝟐. 𝟓 + 𝟎. 𝟓

= 𝟐𝟑

15
 CONCLUSION

The mean has uses in statistics beyond the suggestion of central tendency. Future research

could relate how knowledge of a particular conceptualization of the mean, affects knowledge

of other concepts in statistics, such as variance and distributions. For symmetrically distributed

data, the mean, median and mode can be used almost interchangeably. Physically, mean can

be interpreted as the Centre of gravity of the distribution. Median divides the area of the

distribution into two equal parts and mode is the highest point of the distribution.

16