Statistics: Summarization, Presentation & Analysis

Statistics:

‘ When we think of statistics, in practice we think of a set of data that has been collected.’
’ Statistics is the science of data.
Statistics is the art of learning from data. (Ross, 2010)
Statistics is the study of data.
Statistics is the use of data to help the decision maker reach better decisions.
Statistics is the study of the collection, organization, presentation, analysis, and interpretation, of numerical data.
Initially it was regarded as the ‘science of statecraft’.

Statistics has now been considered as indispensable part of our everyday life.

Statistics: It may be defined as the branch of science, which deals with the collection, organization, presentation,
analysis and interpretation of numerical data in any field of enquiry to assist in making more effective decisions.

Dr. A. L. Bowley defined “ Statistics are numerical statement of facts in any department of enquiry placed in relation
to each other”
According to Croxton and Cowden, : Statistics may be defined as the science of collection, presentation, analysis, and
interpretation, of numerical data”.

Agricultural statistics: A branch of Statistics where statistical methods and techniques are used to analysis the data
collected from various fields of agriculture.
Business statistics, biostatistics, psychometry, education statistics etc. are branch of statistics.

Origin and development of Statistics: The word ‘Statistics’ seems to hsve been derived from the Ltin word ‘status’
or the Italian word ‘statista’ or the German word ‘statistik’, French word ‘statistique’ each of which means a ‘political
state’. Thus it was regarded as the ‘science of statecraft’
Major Area of Statistics:
1. Descriptive Statistics
2. Inferential statistics

Descriptive statistics:
It involves methods of organizing, picturing and summarizing information from data.

Inferential Statistics:
Inferential statistics involves methods of using information from a sample to draw conclusions about the population
characteristics.

Characteristics of Statistics:
a. Statistics deals with the aggregates of facts rather than with individual alone.
b. Statistics, generally are not the outcome of a single cause, but are affected by multiple causes.
c. Statistics are numerically expressed.
d. Statistical data is collected in a systematic manner.
e. Statistics are collected for a predetermined purpose.
f. Statistics are enumerated or estimated according to reasonable standard of accuracy.
g. Statistics are comparable and homogenous.
Functions of Statistics:
 Page 2 of 15

1. It condenses and summarizes voluminous data into a few presentable, understandable and precise figures. In other
words, it simplifies mass of figures.
2. It facilitates classification and comparison of data.
3. It helps in determining relationship between two or more phenomenon: correlation.
4. It helps in predicting future trends.
5. It helps in formulating and testing suitable hypothesis.
6. It helps the central management and the government in formulating suitable policies.

Limitations of Statistics:
1. Statistics deals with aggregates of items and not with isolated/individual item/ or measurement.
2. Statistics deals only with quantitative characteristics.
3. Statistical laws hold good only for the averages.
4. It plays only an auxiliary role in summarizing a fact.
5. Statistics can be misused.
Statistics are liable to be misused and misinterpreted. As it is well known “there are three kinds of lies- lies,
damned lies and statistics”.

Importance:

* Statistics of wealth and manpower are important for development and planning.
* Statistics are invaluable in business and commerce;
* Statistics helps the planner to estimate the revenue income and expenditure of the country;
* Agriculture statistics may play a key role in agriculture development.
* In industry, statistics is widely used to provide quality control;
* Statistics is usually used in education, life science, social science and psychology

Scope and Importance of Statistics in various fields:

The uses of statistics are unlimited. It is much harder to name a field in which statistics is not used. Today, statistical
tools are used in every spheres of life such as trade, industry and commerce, economic, biology, agricultural,
biological sciences, forestry, environment, astronomy, medical sciences, physics, chemistry, education, sociology,
public administration, psychology, meteorology, etc. for handling, analyzing and drawing valid inference from them.
Statistics can be compared like salt of the curry.

Statistical terms and concept:

Population: In statistical term, the totality or collection of all elements under study or enquiry is known as population.
The ‘population’ in statistics includes all members of a defined group that we are studying or collecting information.
Example: If we want to investigate on some characteristics of trees of CU campus then all the trees of CU campus
will be population.

Finite population: All workers in an industry.

Infinite population: Number of fishes in a river, number of insects in a large agricultural fields etc.

Sample: A representative part of a population that is considered for study and analysis is called sample.
Example: Some employees of a firm

Population Sample
1. The totality of all elements under study or enquiry is A representative part of the population is called
called population sample.
A population includes each element from the set of A sample consists only of observations drawn from
observations that can be made the population. It is a subset of population
Population may be finite or infinite Sample must be finite
Collecting data from every element of a population is Collecting data is relatively easy.
not easy.
All students of statistics Few students drawn from students of statistics.
 Page 3 of 15

Parameter: Any numerical measure or value that describes an unknown characteristic of a population is called
parameter.
µ, σ2, etc. are the parameters.
Statistic: Any numerical value that describes a characteristic of a sample is called a statistic.

𝑥, s2, etc. are statistic.

Data:
A set of observations obtained from a particular enquiry is called data or a data set. Single observation is known as
datum.

Experimental unit: Each (individual) object/item of a population is called an experimental unit.

Example: A cow of a firm, a tree in a forest.
Survey: It is a device of obtaining the desired data.

Why do we use sample?

Sampling: The process of selecting sample from the target population is called sampling.
Sampling Frame: It refers to the listing of all units in the population under study.
Sampling units: Items included in a population are called sampling units.
Simple random sample: A sample is called simple random sample if every elements of the population has an equal
chance of being included in the sample.

Variable: A measurable characteristic or phenomenon, which varies from unit to unit under consideration, is called
a variable. Example: Weight, height, gender.

Variable

Qualitative Quantitative

Discrete Continuous

Quantitative (also known as numerical variable): A variable is called quantitative when it measures a numerical
quantity or amount on each experimental unit. Example: length and diameter of trees.

Qualitative: A qualitative variable is one for which numerical measurement is not possible but can be categorized
under same qualitative characteristics. It is also known as categorical variable or attribute.

For example: Gender of patients of a clinic, teaching performance of a professor, opinion of the economists regarding
the economic conditions in the country, etc.

Sources and types of data: a. Primary source and b. Secondary source.

Scales of measurement:

Measurement: It is a process of assigning numbers to some characteristics or variables or events according to

scientific rules. According to Stevens (1968), there are four levels or scales of measurement. They are:
1. Nominal scale 2. Ordinal scale 3. Interval scale 4. Ratio scale
 Page 4 of 15

Organization of Data

Introduction: The data which has been collected are in raw or disorganized form. It is very important that the numerical
findings of any study be presented clearly and concisely and in a manner that enables one to quickly obtain a feel for
the essential characteristics of data which is difficult to explore from the collected raw data. Hence organization or
Summarization of data is required for presentation and analysis of data.

Classification: Classification is the process of arranging data into different groups or classes according to their
common characteristics.

Objectives/Purposes:
(i) To condense the mass of data (ii) to bring out clearly point of similarity and dissimilarity.(iii) To prepare the data
for tabulation (iv) To facilitate comparison. (v) To pinpoint the most significant features of the data at a glance.

Types/Basis of classification:
(a) Geographical --- Area wise, Cities, district, divisions, rural, urban
(b) Chronological --- On the basis of time
(c) Qualitative --- According to some attributes (quality) population: urban and Rural
(d) Quantitative --- in terms of magnitudes:

Tabulation: Tabulation is a logical and systematic organization/ arrangement of statistical data in rows and columns.

Frequency: The number of times that a given value occurs into each group or class is termed as class frequency or
simply frequency.

Frequency Distribution: Arrangement of observational data in different groups according to frequencies of the
observations is called frequency distribution. In other words Frequency Distribution is nothing but the organization
of raw data in the form of table using classes and frequencies.

Problem: Birth weight in pounds of 100 newborns (Exercise-1)

7.4 2.0 3.7 9.4 4.4 4.8 7.6 9.9 8.3 6.5 7.3 4.1 5.2 8.1 3.4 10.0 7.1 4.1 7.2 9.4

8.2 3.1 10.9 7.1 5.2 6.9 7.3 7.3 8.2 5.7 7.0 8.0 5.7 4.0 7.2 9.4 8.2 4.4 5.2 8.9

6.7 4.3 11.7 8.1 6.4 6.0 5.1 8.2 8.9 7.3 7.8 7.4 6.8 6.7 5.3 11.2 7.0 7.5 7.5 7.6

7.1 7.7 8.8 8.0 7.1 6.8 7.4 10.0 7.2 8.8 8.8 7.2 10.1 9.3 8.3 6.7 4.1 5.1 7.4 7.4

7.3 9.8 8.2 7.7 7.6 9.8 6.0 9.7 5.1 6.0 7.1 9.3 9.1 7.6 7.5 9.3 8.5 7.3 9.4 9.4

1. Find the range: The largest value is 11.7 and the smallest value is 2.0.
Thus range= largest value - smallest value= 11.7-2.0=9.7

2. Number of classes: Find the number of classes to be made. Here n =100. So the number of classes
should be K=1+3.322 Log N  K=1+3.322 Log 100= 7.644  8.

3. Class Interval: The length (size) of classes should be around = Range = 9 .7  =1.3.
No. of Classes 8

4. Now make the classes with the interval 2.0 -3.3, 3.3 -4.6, … , 11.1 -12.7 in the following way.

Table-1: Frequency distribution table of birth weight of 100 newborn:

Class interval Tally Marks Frequency Cumulative Cumulative Frequency Relative Frequency
(C.I) ( fi ) Frequency (greater than) RF = 8
fi
(less than)  fi
i =1

2.0 --3.3 // 2 2 100

 Page 5 of 15

3.3 -- 4.6 //// //// 9 11 98

4.6 -- 5.9 //// //// 10 21 89
5.9 -- 7.2 //// //// //// //// 19 40 79
7.2 -- 8.5 //// //// //// //// //// 36 76 60
//// //// /
8.5 -- 9.8 //// //// //// 15 91 24
9.8 -- 11.1 //// // 7 98 9
11.1 -- 12.4 // 2 100 2
Total 100

Bi-variate Frequency distribution for Quantitative variable (also known correlation table):
Problem: The following data represent the temperature (in 0c) and humidity (in %) in different days of the year:
Temp 33.0 33.5 32.6 32.4 32.8 32.2 33.4 33.4 32.2 33.7 33.8
Humidity 82 81 85 84 81 78 81 82 84 80 78
Temp 25.2 27.9 30.2 31.9 33.8 31.3 31.2 32.9 33.8 321.5 29.0
Humidity 81 76 71 81 82 83 89 89 84 82 82
Temp 21.3 27.6 30.7 34.0 34.9 35.7 32.8 32.8 32.6 29.8 26.7
Humidity 84 75 69 74 74 76 82 90 89 88 86
Temp 22.5 27.3 28.8 30.9 32.2 32.7 30.5 30.8 31.6 32.4 30.7
Humidity 78 71 72 81 82 86 90 90 86 85 80

Construct a bivariate frequency table to show the temperature and humidity (left to participators).

Graphical representation: Statistical data may be presented through some visual aids, refers to Graphs
and Diagrams.

Advantages of diagrammatic representation of data:

i. Diagrams give a bird eye view of entire data.

ii. Easy to understand even by a layman or common man.
iii. They facilitate comparison of data. Diagrams help one in making quick and accurate comparison of
data.
iv. They are attractive to the eye/ audience and thus very popular in exhibitions.. So diagrams create greater
interest than figures can.
v. They have long lasting impression;

Various diagrammatic and graphic representations that are commonly used:

a. Bar Diagram
b. Pie Diagram
c. Histogram
d. Frequency Polygon
e. Ogive Curve
f. Scatter diagram

Bar diagram: Simple bar diagram is the most popular diagrammatical representation of qualitative data

Example: Population (in million ) of a certain country in last five census

 Page 6 of 15

Year Male population Female population Total population

Census 1 31.25 28.75 60
Census 2 38.66 36.34 75
Census 3 52.93 47.07 100
Census 4 60.87 59.13 120
Census 5 66.55 63.45 130

Represent the data by bar diagram, horizontal bar diagram, component bar diagram and multiple bar diagram.

Bar Diagram

140
120
Population

100
80 Series1
60 120 130
100
40 75
60
20
0
1 2 3 4 5

Census Year

Horizontal Bar diagram

Census Year

3 Series1

1
0 50 100 150

Total Population

Component Bar Diagram

Male and Female population

140
120
100 Series2
80
60
40 Series1
20
0
1 2 3 4 5

Census Year
 Page 7 of 15

Multiple Bar Diagram

150

Male, Female and

Total Population
100 Series1
Series2
50 Series3

0
1 2 3 4 5
Census Year

Pie diagram: This type of diagram enables us to show the partitioning of a total into its component parts.

Problem: Relative frequencies, percent frequencies and angles of different sectors.

Relative Angles of
Sector Expenditure
Expenditure different sectors
Agriculture 80 0.30 108.00
Industry 70 0.26 93.60
Education 40 0.15 54.00
Transport 25 0..09 32.40
Other 55 0.20 72.00
Total 270 1.00 360
Pie chart of the expenditure of different sectors is exhibited in figure 4.4.2..

Fig.: Pie chart of expenditure of different sectors.

Histogram: The most common form of graphical presentation of a frequency distribution is the histogram. A
histogram is a bar diagram which is suitable for frequency distribution with continuous classes.

Table-1: Frequency distribution table of birth weight of 100 newborn babies (exclusive method):

Class Frequency Cumulative

( fi )
interval Frequency
(C.I) (less than)
2.0 --3.3 2 2
3.3 -- 4.6 9 11
4.6 -- 5.9 10 21
5.9 -- 7.2 19 40
7.2 -- 8.5 36 76
8.5 -- 9.8 15 91
 Page 8 of 15

9.8 -- 11.1 7 98
11.1 -- 12.4 2 100
Total 100

Histogram for the data of birth wight

of 100 new born baby
40

35

30

25
Frequency

20

15

10

2.0 3.3 4.6 5.9 7.2 8.5 9.8 11.1 12.4

Class boundary

Frequency polygon:

b) Ogive curve: The cumulative frequency curve or ogive is the graphic representation of a cumulative frequency
distribution. Ogives are of two types. I) Less than ogive and ii) greater than ogive

i) Less than ogive: In this case less than cumulative frequencies are plotted against the lower boundaries of their
respective class intervals.

ii) Greater than ogive: In this case greater than cumulative frequencies are plotted against upper boundaries of their
respective class intervals.
 Page 9 of 15

Ogive Curve (Less than method )

120

100
Cumulative frequency

80

60

40

20

0
12.0 3.3
2 3
4.6 4
5.9 5
7.2 6
8.5 7
9.8 8 12.49
11.1

Upper limit of the class boundary

Stem and leaf plot:

Stem-leaf display is another form of presentation of the data distribution. The idea is based on an analogy to plants.
Stem-and-leaf plot: Stem-and-leaf plot is a simple device to construct a histogram-like picture of frequency
distribution
Construction: First we arrange the data in ascending order to simplify the construction of stem and leaf method. Use
left/ first/ leading digits (tens) as stem and the last / trailing digit (units) as the leaf. All the values in the stem are listed
in order in a column and a vertical line is drawn beside them and then all the corresponding leaf values are recorded
for each stem in a row to the right of the vertical line.
3.3 2.9 3.2 3.5 4.1 4.5 3.7 3.5 4.0 4.7
4.2 3.5 5.1 2.8 2.9 3.7 4.3 3.2 3.7 4.8
4.5 3.9 4.5 3.1 5.2 2.9 3.7 2.9 3.9 2.6
4.2 3.4 3.8 2.9 3.7 3.9 3.5 2.5 2.4 4.9
3.6 3.7 2.9 3.8 4.1 3.5 2.9 3.3 4.7 3.4
Figure: The stem-and-leaf display for the height of 50 trees.
Stem Leaf
2 4 5 6 8 9 9 9 9 9 9 9
3 1 2 2 3 3 4 4 5 5 5 5 5 5 7 7 7 7 7 7 8 8 9 9 9
4 0 1 1 2 2 3 5 5 5 7 7 8 9
5 1 2
 Page 10 of 15

MASURES OF CENTRAL TENDENCY

Central Tendency: The individual observations of a distribution or a data set are found to have a general tendency to
cluster around a certain point, somewhere at the center of the distribution. This tendency of the observations of a
distribution to concentrate around the center of the distribution is called central tendency and its numerical measures
are known as the measures of central tendency.

Objective of averaging:
There are two main objectives of the study of averages:
1. To get one single value that describes the characteristics of the entire data.
2. To facilitate comparison: a. compare result of two colleges--- which one is better?
b. result of same college for 2 years--- whether improving the result

Different measures of central tendency:

1. Arithmetic Mean (A.M) 2. Geometric Mean (G.M) 3. Harmonic Mean (H.M) 4. Median and 5. Mode

Measures For ungrouped data For grouped data

Arithmetic Mean (A.M.)
fx
x + x2 + ... + xn
A.M , x = 1
x= =
n
i i
where f i =n
n
n
 xi
i =1
=
n

GM=Antilog  
Geometric mean (GM) 1
 f i log xi 
GM= ( x1  x2  ........xn ) , n

 n 
  log x1 
or GM= Antilog  
 n 

Harmonic mean (HM) n n ; n

HM = = H=
1 1 1 1
+ + ......... x f
x1 x2 xn i  xi
i

Median Median is the middle most value when the n

observations are arranged in order of − Fm
Me = LM + 2 C ,
magnitude. fm
* If n is odd, n + 1 th observation in the where, Lm = Lower limit of the median class;
2
series will be the median.
fm = Frequency of the median class
*If n is even, median will be the arithmetic
th
Fm= CF of the pre-median class
n C = Width of the median class.
mean of   and ( n + 1) th observations in
2 2
the series.

Mode The mode is that value which occurs most 1

frequently (max. frequency) in the series of Mo = L + C
the observations. 1 +  2
L = Lower limit of the modal class
1 = The difference between the frequency of
the modal class and pre-modal class
 2 = The difference between the frequency
of the modal class and post modal class
C = width of the modal class
 Page 11 of 15

Problem: Suppose that we have a family of seven members whose age in years are 12, 7, 21, 34, 17, 21
and 2. Compute AM, GM, HM, Median and Mode.
7

x
i =1
i
x1 + x 2 + x 3 + x 4 + x 5 + x 6 + x 7 12 + 7 + 21 + 34 + 17 + 21 + 2
Solution: AM = = = = 16.29
7 7 7

7 7 7
Here HM = = = = 7.69

1 1 1 1 1 1 1 1 0.91
+ + + + + +
xi 12 7 21 34 17 21 2
Median: Arrange data first, then most middle value is median. 2, 7, 12, 17, 21, 21, 34

*** Calculation of all measures of Central tendency: For Grouped data:

Class Freque xi fi x i f i x i2 Log xi fi log xi x i − 6.55 fi u i

ui =
interval ncy fi 1.30
(C.I) ( fi ) xi
2.0 --3.3 2 2.65 5.30 20.28 0.42 0.84 0.75 -3 -6
3.3 -- 4.6 9 3.95 35.55 81.00 0.60 5.40 2.28 -2 -18
4.6 -- 5.9 10 5.25 52.50 127.16 0.72 7.20 1.90 -1 -10
5.9 -- 7.2 19 6.55 124.45 173.28 0.82 15.58 2.90 0 0
7.2 -- 8.5 36 7.85 282.60 105.84 0.89 32.04 4.59 1 36
8.5 -- 9.8 15 9.15 137.25 105.80 0.96 14.40 1.64 2 30
9.8 -- 11.1 7 10.45 73.15 100.00 1.02 7.14 0.67 3 21
11.1 -- 12.7 2 11.75 23.5 1.07 2.14 0.17 4 8
Total 100
f x i i f log x  xf
i i i
i
f u i i

=734.30 =84.74 =61

=14.90

Arithmetic mean (By direct method)

Arithmetic mean, x =
f x i i
=
734.60
= 7.34
n 100
Arithmetic mean (By indirect method)

 x =  a + h u  n = n + n  x = a + hu
xi − a x a h u i i
Let u i =  x i = a + hu i  i i
h

AM by Indirect method, x = a + hu = a + h
 f u = 6.55 + 1.30 x 61 = 6.55 + .79 = 7.34 which is equal to the direct
i i
n 100
method

Geometric mean:

We know Log GM=

 f log x
i i
; therefore GM=Antilog
 f log x
i i

n n
 84.74 
Here GM = Antilog   = Antilog0.85 = 7.08
 100 
 Page 12 of 15

n 100
Harmonic mean, HM= = = 6.71

fi 14.90
xi

Median:
n
− Fm
Median, Me = L + 2 C,
M
fm
where, Lm = Lower limit of the median class; N = Total Frequency
fm = Frequency of the median class Fm= Cumulative frequency of the pre-median class
C = Width of the median class.
n
− Fm
50 − 40
Here Me = LM + 2  C = 7.2 +  1.30 = 7.56
fm 36
Similarly
3n 3 x 100
− Fm − 40
75 − 40
3rd Quartile: Q3 = L + 4  C = 7.2 + 4 x 1.30 = 7.2 + x1.3 = 8.46
fm 36 36
Interpretation: 75 per cent of the new born babies weigh 8.46 lb or less.
7n 7 x 100
− Fm − 40
10 70 − 40
7 Decile D7 = L +
th
 C = 7.2 + 10 x 1.30 = 7.2 + x 1.3 = 8.28
fm 36 36
80n 80 x 100
− Fm − 76
4
80th percentile, P80 = L + 100  C = 8.5 + 100 x 1.30 = 8.5 + x 1.3 = 8.85
fm 15 15

1 1
(36 − 19)
Mode: Mo = L + C =L+  C= 7.2 + x1.30
1 +  2 1 +  2 (36 − 19) + (36 − 15)
17 17
= 7 .2 + x 1.3 = 7.2 + x 1.3 =7.78
17 + 21 38
L = Lower limit of the modal class (the class which corresponds to the maximum frequency )
1 = The difference between the frequency of the modal class and pre-modal class
 2 = The difference between the frequency of the modal class and post modal class
C = width of the modal class

Median (using GRAPHICAL LOCATION ) of Median, 3rd Quartile, 7th Decile and 80th Percentile:
 Page 13 of 15

Ogive Curve (Less than method )

120

100
Cumulative frequency

80

60

40

20

0
12.0 3.3
2 3
4.6 4
5.9 5
7.2 6
8.5 7
9.8 8 12.49
11.1
Median = 7.6
P80 =8.90
D7 = 8.20 Q3= 8.45
Upper limit of the class boundary

d) Mode:

e) Location of Mode Graphically:

Histogram for the data of birth wight

of 100 new born baby
40

35

30

25
Frequency

20

15

10

0
2.0 3.3 4.6 5.9 7.2 8.5 9.8 11.1 12.4
Mode = 7.8
Class boundary
 Page 14 of 15

Comparison among the measures of central tendency:

Criteria AM GM HM Me Mo
Definition Rigidly defined Rigidly defined Rigidly defined Rigidly Not Rigidly
defined defined
Data restriction No restriction Values must be Values must be No restriction No
nonzero & positive nonzero restriction
Computation Easy Slightly difficult Slightly difficult Easy Easy
Based upon all Yes Yes Yes No No
observation
Effect of Less affected Not affected Less affected Not affected Not affected
extreme values
Sampling Little Little Little Much Much
fluctuation
Graphical Not possible Not possible Not possible Possible Possible
Location
Further Possible Possible Not possible Not possible Not possible
algebraic
treatment

Merits and demerits of measures of Central tendency:

Measures Merits Demerits
AM It is rigidly defined. Affected much by extreme observations.
It is easy to calculate. Can’t be used for qualitative data.
It is based upon all observations of the data set. Can’t be found out graphically.
It is easy to understand. Can’t be calculated if open-ended class exists.
It is less affected by fluctuations of sampling. Not suitable for skewed distribution.
It is suitable for further algebraic treatment
GM Has a definite formula to calculate Not easy to understand and calculate for a
non-mathematics [person.
Based upon all observations Can’t be computed for negative or zero values
in the series
Suitable for further algebraic treatment Can’t be calculated if open-ended class exists
Not affected much by fluctuations of sampling Can’t be found out graphically.
Most suitable for measuring rate of change
HM Rigidly defined Can’t be computed where there is any zero
values in the series.
Based on all observations Sampling fluctuation neither easy to calculate nor easy to
is less understand
sampling fluctuation is less It is very complex for further algebraic
treatment
Not affected much by extreme values. Can’t be calculated if the extreme classes of
the frequency distribution are open.
Median can be calculated for distribution with opened Not based on all observations;
classes
Easy to understand and easy to calculate; Can’t be used for further algebraic treatment;
Best for highly skewed distribution; Affected by sampling fluctuation.
Not affected by extreme values in the series.
Can be obtained graphically;
Only average to be used to deal with qualitative
variable
Mode easy to understand and easy to calculate Ill-defined. Not always to find a clearly
defined mode.
Can be located graphically Don’t include all the data set;
 Page 15 of 15

Easy to calculate and easy to understand As compared with mean, affected to a great extent
by sampling fluctuation
Not affected by extreme values Not capable of further mathematical
calculation
Include open-ended class interval -

Prof. Md. Emdadul Haque

Department of Statistics, CU

--- x --