SALWANI TUTORIALS

STATISTICS NOTES
CH – 1 COLLECTION OF DATA
Origin and Growth of Statistics:
 From the time of Mauryan empire (321-296 BC) the contribution of India in Statistics
has been quite significant.
 During the time of Mughal empire, Akbar (1596-97) mentioned statistical system in
‘Ain-I-Akbari’ written by Abul Fazal.
 The German word ‘Statistik’ was first used by Gottfried Achen Wall in 1749 for
analysis of data of the state.
 By 18th century, the term ‘statistics’ was used for systematic collection of data by
states.
 Statistics was formally introduced in Encyclopedia Britanica in 1797.
 In 17th and 18th century Laplace (1749- 1827) and Gauss (1772-1855) presented the
initial principles on probability.
 In the late 19th and early 20th century Karl Pearson founded Mathematical Statistics.
Galton and Karl Pearson used mathematical statistics in Science, Industry and Politics.
 During 1910 and 1920, Gosset and Fisher developed modern statistical science and
applied in the fields such as genetics, biometry, psychology, education, agriculture,
etc.
 During 1930, role of E. Pearson and J. Neyman had been significant in the
development of statistics. After that advanced methods of statistics were developed
day-by-day.
Growth of Statistics in India:
 Contribution of Prof. P. C. Mahalanobis has been significant in growth of statistics in
India. He has founded Indian Statistical Institute – ISI in 1931 at Kolkata. He started
for the first time post graduate course in Statistics at Kolkata University in 1941.
 In 1950, Mahalanobis established National Sample Survey – NSS and started data
collection. (NSS has been named as National Sample Survey Organisation – NSSO at
present.)
 Indian Agriculture Statistics Research Institute – IASRI has contributed a lot in the
development of statistics in India.
 SALWANI TUTORIALS
 Among the various definitions of statistics, the definition given by Croxton and
Cowden is ‘Statistics is the science which deals with the collection, analysis and
interpretation of numerical data.’
 Now a days, statistics is not only useful for quantitative data but also for qualitative
data.
 Statistics is considered as a part of scientific methods. An important branch of
statistics is Operations Research-OR, which was used in the military projects during
the second world war. The use of OR in industries and for the government cannot be
ignored.
Quantitative Data and Qualitative Data:
 Population: In statistics, a group of all the units under study is called a population. For
example, in population census a group of all citizens of the country is population.
 Population Size: The total number of units in the population is called the size of
population. It is denoted by symbol ’N’.
 Finite Population: If the total number of units contained in the population N is
countable such a population is called finite population.
 Sample: A set of units selected from the population on the basis of some definite
criterion is called sample. For example, a group of 90 students selected at random
from the 900 students of a school is sample.
 Sample Size: The number of units in the sample is termed as the sample size. It is
denoted by symbol ‘n’. For example, if 30 workers are selected by some statistical
method from 300 workers of a factory, then sample size n = 30.
 Variable Characteristics: A characteristic that varies for each unit of population or
sample is called variable characteristic. It can be either numerical or non-numerical. If
the variable characteristic is non-numerical or qualitative it is called qualitative
variable or attribute. If the variable characteristic is numerical, it is called numerical
variable.
 Data: A set of all the observations obtained by an inspection of a variable
characteristic defined on units of a population or the sample selected from it, is called
data.
 Qualitative Data: A set of observations on the attribute is called qualitative data. For
example, data on sex of the workers of a factory, level of education, economic
condition of parents of students of a school, etc. are qualitative data.
Primary Data and Secondary Data:
 SALWANI TUTORIALS
 Primary Data: The data originally collected by any authorised agency or investigator
for the first time is called primary data. For example, the data collected by NSSO of
population census of India every ten years are primary data.
 Secondary Data: When an authorised agency or investigator uses the data collected by
any other agency or investigator, then such data becomes secondary data for the users.
For example, if the planning commission make use of the data collected in population
census for economic planning of the country, than for planning commission that data
becomes secondary data.
Methods of collecting Primary Data:
 Method of Direct Inquiry: An investigator himself collects the data by visiting
personally to the field.
 Method of Indirect Inquiry: Instead of an investigator, data is obtained with the help of
the third party.
Method of Questionnaire:
A questionnaire is prepared by making a list of questions relevant to the object of the study
keeping the space between the questions for the answers. The method of collecting data
using such type of questionnaire is called method of questionnaire.
There are two ways of collecting data by questionnaires:
1. By post and
2. By enumerators.
Secondary Data:
Sources of Secondary Data:
 Government Publications,
 Semi-government Publications,
 International Publications,
 Reports of Research Organisations,
 Reports of Local self Government Institutions and Autonomous Educational
Institutions,
 Publications of Business and Commerce Organisations,
 Newspapers and Periodicals and
 Unpublished Sources.
 SALWANI TUTORIALS
Precautions for using Secondary Data:
Before using secondary data, the following precautions should be taken:
 Data collector and source of data,
 The purpose of collecting data
 The time period of data collected,
 Scope of data, region of data and definitions of different terms
 Whether data is estimated and
 The method of collecting data.
 SALWANI TUTORIALS
CH – 2 PRESENTATION OF DATA
Meaning and need of Classification:
1. Numerical Variable:
A numeric characteristic that varies from unit to unit of a population or sample is called
numeric variable. For example, age of a person, price of an item, profit of a firm, number of
children per family, etc. are numeric variables.
2. Qualitative Variable or Attribute:
A qualitative characteristic that varies from unit to unit of a population or sample cannot be
measured numerically but can be described is called qualitative variable or attribute. For
example, profession of a person, efficiency of a worker, etc. are attributes.
3. Types of Numerical Variable:
 Discrete Variable: If a variable can assume definite or countable values within the
specified range, then it is called discrete variable. For example, number of flowers per
plant, number of accident on a road, etc. are discrete variables.
 Continuous Variable: If a variable can assume any value within the specified range,
then it is called continuous variable. For example, age of a person (in years), weight of
a student (in kg), salary of an employee (in ₹), temperature of a day (in Celsius), etc.
are continuous variable.
4. Discrete Data and Continuous Data:
The data on discrete variable is discrete data, while the data on continuous variable is
continuous data.
5. Raw Data:
Data obtained by population inquiry or sample inquiry are called original data or ungrouped
data or raw data. For example, marks of 100 students in the subject statistics.
6. Classification:
A process of arranging ungrouped or raw data in systematic and short form is called
classification.
7. Classified Data:
The data obtained by classification are called classified data or grouped data.
8. Need of Classification:
 To represent large data into simple, short and attractive manner,
 to compare the various characteristics of the data and
 to analyse the data by saving time, money and labour.
 SALWANI TUTORIALS
Types of Classification:
1. Quantitative Classification:
 Classification of data on numeric variable, discrete and continuous is called
quantitative classification. It is also known as numerical classification or frequency
distribution.
 Frequency Distribution: If discrete or continuous data are classified according to the
value of the variable, then it is called frequency distribution.
Types of Frequency Distribution:
1. Discrete Frequency Distribution: When discrete data are classified according to the values
of a variable showing how frequent each value occurs, then it is called discrete frequency
distribution. Thus, a table showing various possible values of discrete variable with their
respective frequencies is called discrete frequency distribution. For example, the table
showing the number of families as per the number of children is discrete frequency
distribution.
2. Continuous Frequency Distribution: When the variable of raw data is continuous or range
of the data is large, then dividing the range of data into fix number of groups or classes, data
are classified in the manner, how many values of the variable occur in each class. Thus, a
table showing various classes with their respective frequencies is called continuous
frequency distribution. For example, the table showing the number of companies according
to various classes of the profit (in ₹) earned during a year.
Frequency:
A numeric value showing the repetition of value of variable is called the frequency (f) of that
value. Similarly, the number of observations corresponding to each class is the frequency of
that class.
Range:
The difference between the highest value and the lowest value of the data is called range.
Class or Class Interval:
The interval obtained by two fixed values of the variable is called a class. For example, 10-
14, 15-19, 20-24 etc.
Lower Limit:
The lowest value of a class is called the lower limit of that class. For example, the lower
limit of the class 10- 14 is 10.
Upper Limit:
The highest value of a class is called the upper limit of that class. For example, the upper
limit of class 10-14 is 14.
 SALWANI TUTORIALS
Exclusive Class:
If the upper limit of a class is not included in that class but is included in the next class, such
a class is called exclusive class. In exclusive class, the upper limit of any class is the lower
limit of the next class, e.g., the classes 10-20, 20-30, 30-40. … are exclusive classes. Here,
the upper limit 20 of class 10-20 is not included in class 10-20, but it is included in the class
20 – 30. The frequency distribution having exclusive classes is called exclusive type
frequency distribution. It is carried out for the continuous raw data.
Inclusive Class:
If the upper limit of a class is included in the class itself, such a class is called inclusive
class. In inclusive class, the upper limit of any class and the lower limit of the next class are
not equal, e.g., the classes 10-19, 20-29, 30-39, … are inclusive classes. Here, the upper limit
19 of class 10-19 is included in the class itself. The frequency distribution having inclusive
classes is called inclusive type frequency distribution. It is carried out for the discrete raw
data having large value of range.
Conversion of Inclusive Type Continuous Frequency Distribution into Exclusive Type
Continuous Frequency Distribution:
For such conversion class limits are expressed as class boundary points.
Class Boundary Points:
 Lower Boundary Point: It is an average of lower limit of a class and the upper limit of
previous class. For example, for classes 10-14, 15-19, 20-24, …, etc. lower boundary
point of class 15 – 19 is 15+142 = 14.5.
 Upper Boundary Point: It is an average of the upper limit of a class and the lower limit
of succeeding class. For example, for classes 10- 14, 15- 19. 20-24, …, etc. upper
boundary point of class 15-19 is 19+202 = 19.5.
[Note; For exclusive classes class limits are the class boundary points. For example, for
classes 10-20, 20 – 30, 30 – 40 etc. lower limit and lower boundary point of the class 20 – 30
are 20 and upper limit and upper boundary point of the class 20-30 are 30.)
Mid Value:
The value obtained by dividing the sum of the values of the lower limit and the upper limit
of a class is called the middle value or mid value of the class, e.g., the mid value of the class
10-14 = 10+142 = 12.
Class Length:
The difference between the values of the upper and lower boundary points of any class is
called the class length of that class, e.g., the class length of class 15 – 19 = 19.5 – 14,5 = 5.
Cumulative Frequency:
The sum of the frequencies of values less than or equal to some specified value of the
 SALWANI TUTORIALS
variable is called the cumulative frequency of that specified value of a discrete distribution.
Similarly, the sum of frequencies of the classes preceding to the specified class and the
frequency of the specified class is called the cumulative frequency of that specified class of a
continuous frequency distribution.
 Less than’ Cumulative Frequency:
In continuous frequency distribution, the ‘less than’ cumulative frequency of a given
class is the sum of frequencies of all classes which include all observations less than or
equal to the upper boundary point of that class. Such cumulative frequencies are in
ascending order.
 More than’ Cumulative Frequency:
In continuous frequency distribution, the ‘more than’ cumulative frequency of a given
class is the sum of frequencies of all classes which include all observations more than
or equal to the lower boundary point of that class. Such cumulative frequencies are in
descending order.
Cumulative Frequency Distribution:
A table showing the cumulative frequency according to the value or a class of values is
called cumulative frequency distribution.
 Discrete Cumulative Frequency Distribution: The cumulative frequency distribution
obtained by considering the value of a discrete variable is called discrete cumulative
frequency distribution.
 Continuous Cumulative Frequency Distribution: The cumulative fre¬quency
distribution obtained by considering the boundary points is called continuous
cumulative frequency distribution.
Types of Cumulative Frequency Distribution:
 ‘Less than’ Type Cumulative Frequency Distribution: The distribution obtained by
each value of the variable and its corresponding cumulative frequency of a discrete
frequency distribution is called a discrete cumulative frequency distribution of ‘less
than’ type. Similarly, the distribution obtained by the upper boundary point of each
class and its corresponding cumulative frequency is called a continuous cumulative
frequency distribution of ‘less than’ type.
 ‘More than’ Type Cumulative Frequency Distribution: The distribution obtained by
each value of the variable and its corresponding ‘more than’ cumulative frequency of a
discrete frequency distribution is called a discrete cumulative frequency distribution of
‘more than’ type. Similarly, the distribution representing the lower boundary points
and their corresponding cumulative frequencies is called ‘more than’ type continuous
cumulative frequency distribution.
 SALWANI TUTORIALS
2. Qualitative Classification:
Classification of data according to the attributes of the information by arranging them in
rows and columns is called qualitative classification. It is known as Tabulation.
Types of Qualitative Classification:
 Simple Classification: A classification on the basis of a single attribute is called simple
classification or tabulation. For example, classification of the data of employees of a
company on the basis of their status in the company.
 Manifold Classification: A classification of row data carried out by considering more
than one attribute under study is called manifold, classification or tabulation. For
example, classification of data of employees of a company on the basis of their sex
and status of working in the company.
Tabulation:
Tabulation is a process of arranging in systematic manner the qualitative data into rows and
columns on the basis of the attributes. In the tabulation title of the table, sources of the data
and explanation of data are given.
Uses of Tabulation:
 Represents the extensive data in simple, organised and precise manner,
 required information can be obtained easily
 various characteristics to be compared are placed side by side. Hence comparison
becomes easy
 row and/or column totals are found, hence errors can be rectified easily.
 unnecessary information is removed, hence the time, money and labour required for
the study of data is saved and
 the analysis of the data becomes simple and convenient.
Rules of Tabulation:
 Appropriate title should be given
 there should be clear and simple captions to the rows and column
 size of the table should be proportionate to the space available
 the interrelated information should be placed adjacent to each other,
 large numbers should be represented in hundred, thousands, lakhs or crores,
 separate lines should be drawn to distinguish the main characteristics of the data
 SALWANI TUTORIALS
 provision for indicating the totals of primary and subsidiary characteristics should be
there in a table
 large volume of data should be represented in different- tables instead of a single table
 source of the data must be mentioned at the end of the table and
 before preparing the final table, a rough table should be prepared.
Diagram:
Diagram is a tool to represent huge and complex data into simple and attractive manner in
order to understand the data easily.
Importance and Limitations of Diagram:
Importance:
 Represents the data in attractive, simple and concise form
 the data expressed by diagrams are remembered for longer time
 saves time in representing the data
 the comparative study of the data becomes very simple
 easily understood by the illiterates, less educated or even by children
 in business and industries useful for effective advertisement and
 easy to understand irrespective of language barriers.
Limitations:
 Lac of accuracy in drawing diagrams leads to wrong interpretation
 Illusionary effect of diagrams misleads the public opinion and
 there is a loss of accuracy of the data.
Types of Diagram:
1. One Dimensional Diagram: A diagram drawn by considering only one characteristic of the
data is called one dimensional diagram.
 Bar Diagram: It is drawn considering only one characteristic such as different places,
things or time.
 Multiple or Adjacent Bar Diagram: It is drawn, if the data about different places,
things or times on more than one mutually related characteristics are given.
 Simple Divided Bar Diagram: It is drawn if the data about different places, things or
times consists of several mutually related sub-data.
 SALWANI TUTORIALS
 Percentage Divided Bar Diagram: It is drawn when mutually related sub-data are to be
compared effectively.
2. Two Dimensional Diagrams: When the volume of the data is large, then considering length
and breadth, two-dimensional diagrams are drawn.
 Circle Diagram: It is drawn when the volume of data regarding two or more places,
things or times is large.
 Pie Diagram: It is drawn, when the data related to different places, things or times
consist of several mutually related sub-data on different components are numerically
large.’
3. Pictogram: A diagram in which the data are represented by appropriate pictures is called
pictorial diagram or pictogram. It has no barrier of language.
Important Formulae:
 SALWANI TUTORIALS
CH – 3 MEASURES OF CENTRAL TENDENCY
Meaning of Measure of Central Tendency:
Central Tendency:
In classified data the values of the variable are concentrated around a certain central value.
This characteristic of data is called central tendency.
Measure of Central Tendency:
The central value around which the values of the variable are concentrated is called as
measure of central tendency.
Average:
A measure, representative for the whole set of data and representing an essence of the main
characteristics of the data is called average. Its’ measure being in the centre of the data, is
known as measure of central tendency.
Measures of Central Tendency:
 Arithmetic Mean or Mean
 Geometric Mean
 Median, Quartiles, Deciles, Percentiles
 Mode
Characteristics of an ideal of Average:
 Its definition should be clear and precise.
 It should be easy to understand and calculate.
 It should be based on all the observations of the data.
 Suitable for further algebraic operations
 A stable measure
 Less affected by too large or too small observations
 Useful for data analysis
 Real measure k Arithmetic Mean or Mean:
Mean:
The value obtained by dividing the sum of all observations of the given data by the total
number of observations is called mean of the data. It is denoted as x̄ .
x̄ = Σxn Where, Σx = Sum of observations
n = Number of observations
 SALWANI TUTORIALS
Combined Mean:
If the number of observations and their means are given for two or more groups, the mean
obtained by combining all the groups is called combined mean. It is denoted as x c.
Weighted Mean:
The mean calculated by the observations of the given data with the consideration of their
relative weights is called weighted mean. It is denoted as x̄ w.
Geometric Mean:
If ‘n’ observations of given data are positive and non-zero, say x1, x2, x3, …, xn then nth root
of the product of n observations is called the geometric mean of the data and it is denoted by
G.
G = x1⋅x2⋅x3……xn−−−−−−−−−−−−−−−√n
[Note: If x̄ = Arithmetic mean of n positive observations and G = Geometric mean of n
positive numbers, then inequality x̄ ≥ G is satisfied.]
Measures of Positional Average:
Median:
The value of the observation located exactly in the middle in the sequence of observations
arranged in ascending or descending order of their magnitudes is called the median of the
data. It is denoted by the symbol M.
M = Value of (n+1)2th observation
Here, n = number of observations
Quartiles:
The quartiles are the values of observations which divide the sequence of observations of
data arranged in ascending or descending order of their magnitudes into four equal parts.
There are three quartiles and they are denoted by symbols Q1 Q2 and Q3.
Qj = Value of j(n+1)4th observation
Here, j = 1, 2, 3
Its clear that, Q2 = Second quartile = Median; Q1 ≤ Q2 ≤ Q3
Deciles:
The deciles are the values of observations that divide the observations of the data arranged in
ascending or descending order of their magnitudes into ten equal parts. There are nine
deciles and they are denoted by symbols D1, D2, D3, …, D9.
Dj = Value of j(n+1)4th observation
Here, j = 1, 2, 3, …, 9 It is clear that, D5 = Q2 = M
D1 ≤ D2 ≤ D3 ≤ … ≤ D8 ≤ D9
Percentiles:
The percentiles are the values of the observations which divide the observations of the data
arranged in ascending or descending order of their magnitudes into 100 equal parts. There
 SALWANI TUTORIALS
are 99 percentiles. They are denoted by symbols P1, P2, P3, …, P99.
Pj = Value of j(n+1)4 th observation
Here, j = 1, 2, 3, …, 99
It is clear that, P25 = Q1; P50 = D5 = Q2 = M;
P75 = Q3’ P10 = D1 P20 = D2
Thus, P10 × j = Dj, J = 1, 2, …, 9
Pi ≤ P2 ≤ P3 ≤ … ≤ P98 ≤ P99
Mode:
Mode: The value of the observation which is repeated maximum number of times in the
given data is called the mode of the data. It is denoted by M0.
Relation among the measures of Average:
For the frequency distribution in which the observations of the data are not evenly
distributed around average Karl Pearson established the following relation:

⇒ M0 = 3M – 2x
3 (Median – Mode) = 2 (Mean – Mode)

Where, M0 = Mode; M – Median; x = Mean

Some Algebric results for measures of Central Tendency:
 If the values of all observations of the data are equal, then the values of all measures
of central tendency are equal.
For example, if the marks of statistics of 5 students of std. 11 are 70, 70, 70, 70, 70,
then x = M = M0 – G = xw = 70.
 For the data evenly distributed from average, Mean = Median = Mode.
 The values of Mean, Median and Mode are changed by the change of origin and scale.
For example, if multiplying the variable x by non-zero b and adding a to it, then new
variable we get y = bx + a. Therefore, ȳ = bx̄ + a; Median of y =b (M) + a; Mode of y
= b(M0) + a.

Comparative study of Mean, Median and Mode:

 The very popular measure of average is mean which is useful for study in advanced
statistical method.
 For qualitative data median is useful. When the values of the variable are not evenly
distributed, it is useful for studying social problems, business activities and agriculture
.related problems.
 In business and commerce mode is more useful.
 SALWANI TUTORIALS
The selection of average is based on
 Nature of the data,
 Nature of variable involved,
 The purpose of study,
 The type of classification used and
 The need of statistical analysis.
Important Formulae:
1. Mean:
Ungrouped Data:
Direct method (By definition)
x̄ = Σxn
Where, x = Observation
Σx = Sum of observations
n = Total number of observations
Short Cut Method:
x̄ = A + Σdn
Where, A = Assumed mean
d = Deviation from Assumed mean
Σd = Sum of deviations
n = Total number of observations
Grouped data:
Discrete Frequency distribution:
Direct method:
Discrete x̄ = Σfxn
Where, x = Observation
f = Frequency of observation
n = Total frequency = Σf
Short cut method:
Discrete x̄ = A + Σfdn
Where, A = Assumed mean
d = (x – A)
f = Frequency of observation
n = Total frequency = Σf
Continuous Frequency distribution:
Direct Method:
 SALWANI TUTORIALS
x̄ = Σfxn
Where, x = Mid value of class
f = Frequency of class
n = Total frequency = Σf
Short Cut Method:
x̄ = A + Σfdn × c
Where, d = x−Ac
x = Mid value of class
A = Assumed mid value
c = Class length
n = Total frequency = Σf
2. Combined Mean
x̄ = n1x¯1+n2x¯2+n3x¯3+…+nkx¯kn1+n2+n3+…+nk
Where, x̄ 1, x̄ 2, …, x̄ k are means of k groups respectively
n1, n2, …………nk are number of observations of k groups respectively
xc = Combined mean of k groups

3. Weighted Mean
x̄ w = x1w1+x2w2+x3w3+…+xkwkw1+w2+w3+…+wk=ΣxwΣw
Where, x̄ w = Weighted mean; Σm = Total weight
x1, x2, …, xk are k observations respectively;
x = Observation
w1, w2, …….. wk are weights of k observations respectively;
w = Weight of observations
Some algebraic results about Mean:
1. The sum of the deviations of the observations of the data from their mean is always zero,
i.e., Σ (x – x̄ ) = 0.
For example:
x: 5, 7, 9, 11, 13 x̄ = Σxn=455 = 9
2 (x – x̄ ) = (5 – 9) + (7 – 9) + (9 – 9) + (11 – 9) + (13 – 9) = (-4) + (-2) + 0 + 2 + 4 = – 6 + 6
=0
2. If each observation of the data is multiplied by a non-zero constant ‘b’ and a non-zero
constant ‘a’ is added to it, the mean of new observations becomes bx + a.
For example:
In the above example x̄ = 9. If each observation is multiplied by 3 and 2 is added to it, then
mean of new observations = 3(9)4 – 2 = 29.
 SALWANI TUTORIALS
In the same way, if a constant ‘a’ is added to each observation and the result is divided by a
non-zero constant ‘c\ then the mean of new observations becomes = x¯+ac
For example:
In the above example x = 9. If 3 is added to each observation and then the result is divided
by 4, then the mean of new observations = 9+34=124 = 3.
3. x̄ = Σxn So out of three values x̄ , Σx and n, if the values of any two are given, the value of
third can be obtained.
For example:
In the above example x = 9 and if n = 5 is given, then Σx = n.x = 5 x 9 = 45
In the same way, x = 9 and Σx = 45 is given, then n = Σxx¯=459 = 5
4. Geometric Mean
Ungrouped data:
G = x1⋅x2⋅x3⋯xn−−−−−−−−−−−−−√n
Note: The relation between mean x and Geometric mean G is x̄ ≥ G.
5. Median
Ungrouped data:
M – Value of (n+12)th observation
Where, n = Number of observations
Discrete frequency distribution:
Grouped data:
M = Value of (n+12)th observation
where, n = Total frequency = Σf
Continuous frequency distribution:
Class for median = Class in which n2th observation lies
M = L + n2−cff × c
Where, L = Lower boundary point of median class n = Total frequency = Σf
cf = Cumulative frequency of class preceding the median class
f = Frequency of median class
c = Class length of median class
6. Quartiles
Ungrouped data:
Qj = Value of j(n+14) th observation; Where j = 1, 2, 3 and n = Total number of observations
Grouped data:
Discrete frequency distribution:
Q1 = Value of (n+14)th observation
 SALWANI TUTORIALS
Q2 = Value of 2(n+14)th = (n+12)th observation
Q3 = Value of 3(n+14)th observation Where, n = Total frequency = Σf
Continuous frequency distribution:
First Quartile:
Q1 class = Class in which j(n4)th observation lies
Q1 = L + n4−cff × c
Third Quartile:
Q3 class = Class in which 3(n4)th observation lies
Q3 = L + 3(n4)−cff × c
Note:
Get, either the class for Q1 or Q3 or the values of Q1 or Q3 by referring to the order of
observation in the column of cumulative frequency cf.

7. Deciles
Ungrouped data:
Dj = Value of j(n+110)th observation;
Where j = 1, 2, 3, …, 9 and n = Total number of observations
Grouped data:
Discrete frequency distribution:
Dj = Value of j(n+110)th observation; Where j = 1, 2, 3, …, 9 and n = Total frequency = Σf
Continuous frequency distribution:
Class for Dj = Class in which j(n10)th observation lies
Dj = L + j(n10)−cff × c Where j = 1, 2, 3 9
Note: Get the values of Dj or class for Dj by referring to the order of observations in the
column of cumulative frequency cf.
8. Percentile
Ungrouped data:
Pj = Value of j(n+1100)th observation: Where, j = 1.2, 3, …,99 and n = Total number of
observations
Grouped data:
Discrete frequency distribution:
= Value of j (n+1100)th observation: Where, j = 1. 2, 3 99 and n = Total frequency =Σf
Continuous frequency distribution:
Class interval for Pj = Class in which j(n+1100)th observation lies
Pj = L + j(n100)−cff × c; Where, j= 1. 2, 3, ………….. 99
 SALWANI TUTORIALS
Note: Get the values of P or class for P by referring to the order of observations In the
column of cumulative frequency cf.
9. Mode
Ungrouped data:
M0 = The observation which is repeated for maximum number of times
Grouped data:
Discrete frequency distribution: M0 = Value of the observation with maximum frequency
Continuous frequency distribution:
Modal class = A class with maximum frequency
M0 = L + fm−f12fm−f1−f2 × c
Where, L = Lower boundary point of the model class;
f1 = Frequency of the class preceding the model class;
Jm = Frequency of the model class;
f2 = Frequency of the class succeeding the model class; c = length of the model class
Emperical Formula:
(For bimodal frequency distribution or frequency distribution of unequal class length)
M0 = 3M – 2x̄ ; Where x̄ = Mean, M = Median, M0 = Mode
Graphical Method for Mode:
 It is used only for uni-modal frequency distribution.
 It is used for the continuous frequency distribution with equal class length and unequal
class length.
 To find mode by graph Histogram is used.
 To draw histogram, convert inclusive type continuous frequency distribution into
exclusive type of continuous frequency distribution by class boundary points.
 If the frequency distribution is of unequal class length, find the proportionate
frequency of each class by using the following formula: frequency of a class
Proportionate frequency = frequency of a class class length of a class × smallest class
length