f

1)
53
o

73
11
97
,9
m
co
n

l.
ai
gm
3@
19
o

iya
az
a (s
sh
i
3
19
ya
t
t ss
ha
zi
a
a
to
s
ng
lo
be
s
D
F
PD
is
Th

Organi
 1)
53
73
11
97
,9
m
l. co
ai
gm
3@
19
iya
az
sh
(s
3
19
ya
zi
ha
ss
to
s
ng
lo
be
F
PD
is
Th
 Ch:4 Organisation of Data
Classification of Raw Data

The process of arranging raw data into meaningful groups or classes to facilitate
comparisons and analysis is known as classification. This arrangement enables the
organization of data based on their distinct characteristics.

Th
is
For instance, classification can involve grouping data into categories such as rich,

PD
F
be
poor, black, white, and so forth, thereby enhancing the interpretability and

lo
ng
s
utility of the raw data.

to
ss
ha
zi
ya
Objectives of Classification

19
3
(s
sh
az
i
1. Simplification of Data

ya
19
3@
2. Classification aims to condense and simplify raw data, making it more

gm
ai
l.
manageable and easier to comprehend.

co
m
,9
3. Enhancing Utility

97
11
73
4. The primary goal of classification is to extract utility from data,

53
1)
transforming it into a form that is more useful and meaningful for analysis
and decision-making.
5. Facilitating Comparisons
6. Classification enables data to be organized in a manner that allows for
meaningful comparisons between different groups or categories, aiding in the
identification of patterns and trends.
7. Achieving Scientific Arrangement
8. Classification seeks to achieve a systematic and scientific arrangement of
data, ensuring that it is organized logically and coherently for accurate
interpretation and analysis.
Basis of Classification
1. Geographical/Spatial Basis: Classification based on locational differences, such
as Agra, Delhi, etc.
2. Chronological Basis: Classification based on time, such as years (1991, 1992,
1993, etc.).
3. Qualitative Classification
Simple Classification: Involves categorizing items based on one
characteristic. For example, classifying fruits based on color (e.g., red apples,
green apples).
 Manifold Classification: Considers multiple characteristics for classification.
For instance, classifying cars based on make, model, and color, or classifying
students based on intelligence level, occupation, and religion. This type of
classification allows for more detailed and nuanced categorization based on
several attributes simultaneously.
4. Quantitative/Numerical Classification: Classification based on numerical
values, where classes are formed based on the range of values in the data,

Th
is
PD
considering the lowest and highest values.

F
be
lo
ng
For example, if we measure the height of XI commerce students, the heights of

s
to
ss
students would be considered as a variable. In a quantitative classification, we

ha
zi
ya
could classify the heights into different ranges (e.g., < 150 cm, 150-160 cm, 160-

19
3
(s
sh
170 cm, etc.) based on numerical values. This would allow us to categorize the

az
i
ya
heights of students quantitatively rather than qualitatively.

19
3@
gm
ai
l.
co
m
,9
97
11
73
53
1)
a. Discrete b. Contineous

a. In complete numbers classification, values are discrete and typically represent

counts or ranks. For example, consider the ranks of students, which are
represented by integers such as 1, 2, 3, 4, and so on. These values cannot be
fractional or continuous; they must be whole numbers.
b. In continuous classification, values form a range or continuum, often
increasing in fractions or decimals. For instance, consider the measurement of
temperature, where values can range from fractions of a degree Celsius or
Fahrenheit. This type of classification allows for precision in representing data
that falls within a continuous spectrum.
 Raw Data into
Statistical Series

1. Individual series 2. frequency series

Th
is
PD
F
be
lo
ng
s
to
ss
ha
Frequency

zi
ya
a. Discrete series b.

19
distribution

3
(s
sh
az
i
ya
(frequency array) (contineous)

19
1. Individual Series

3@
gm
ai
l.
co
Classification without class or frequency repetition arranges items by serial

m
,9
97
number, ascending order, or descending order.

11
73
53
1)
E.g
Marks

20
30
40
45
85

2. Frequency series

1. Frequency: The number of times an item occurs or repeats in a dataset. For

example, if 5 marks are obtained by 8 students, then the frequency of 5 is 8.
2. Class Frequency: The number of times an item repeats itself within a
specified range of values, known as a class interval. For instance, if we have
class intervals like 10-15, 15-20, 20-30, etc., class frequency would represent
the count of items falling within each interval.
3. Tally Bars method involves marking a vertical line for each individual item
and then, for every fifth item, a cross bar is marked across the four vertical
lines. This method is commonly used for counting and tallying data.
 Th
is
PD
F
be
a. Discrete series / frequency Array

lo
ng
s
to
ss
ha
A discrete series or frequency array presents data in a precise manner along with

zi
ya
19
their corresponding frequencies. For example:

3
(s
sh
Data: 8, 9, 10, 12, 15

az
i
ya
19
Frequency: 6, 5, 6, 3, 2

3@
gm
This indicates that the data values 8, 9, 10, 12, and 15 occur with frequencies of 6,

ai
l.
co
m
5, 6, 3, and 2 respectively.

,9
97
11
73
53
1)

b. Frequency distribution
Frequency distribution involves organizing data into class intervals or ranges.
The magnitude of a class interval is calculated as the difference between the
upper limit and the lower limit, which can be expressed as:
Magnitude = Upper Limit - Lower Limit
For example, if the upper limit is 10 and the lower limit is 5:
Magnitude = 10 - 5 = 5

The mid-value or midpoint of a class interval is calculated as the average of the

Th
is
upper and lower limits, which can be expressed as:

PD
F
be
Mid-value = (Upper Limit + Lower Limit) / 2

lo
ng
s
This gives the middle point of the interval.

to
ss
ha
zi
Continous Series

ya
19
3
(s
sh
az
i
ya
19
3@
gm
ai
Mid Value Open End Cumulative

l.
co
Inclusive Series Exclusive Series

m
Seeies

,9
Series Series

97
11
73
53
Marks No.of S Marks No.of S (a) Less than

1)
Series.
5-9 24 5-10 24 Lower Class + Upper class
32 (b) More than
10-14 32 10-15
2 Series.
15-19 17 15-20 17
20-24 5 20-25 5

1. In inclusive frequency distribution, the upper limit of a class interval is

included within that interval. For instance, in the interval 10 - 20, both 10
and 20 belong to this interval.

10 - 19 → 19 also belong to this class

2. Exclusive upper limit frequency distribution refers to a type of frequency

distribution where the upper limit of a class interval is not included in that
class interval.
 E.g

Th
is
In exclusive upper limit frequency distribution, the upper limit of a class interval

PD
F
be
is not included within that interval. For example, in the interval 10 - 20, the value

lo
ng
s
20 does not belong to this interval; instead, it belongs to the next interval, such

to
ss
ha
as 20 - 30, and so on.

zi
ya
19
3
(s
Conversion from to Inclusive to Exclusive

sh
az
i
ya
19
3@
a. To convert from inclusive to exclusive class intervals, follow these steps:

gm
ai
l.
co
Calculate the difference between the lower limit of the current class and the

m
,9
97
upper limit of the previous class.

11
73
53
1)
For example, if the upper limit of the current class is 20 and the lower limit
of the previous class is 19:
Difference = Upper limit of current class - Lower limit of previous class
= 20 - 19
=1
This difference represents the width of the exclusive interval.

b. Divide the difference by [2] and then

The result will be substracted from lower interval of every class and
same to will be called to upper interval of every class.
3.Mid value series
they have only mid values of the class intervals

E.g

Th
is
PD
F
be
lo
ng
Conversion into normal.

s
to
ss
Step 1. Find mutual difference b/w Mid values

ha
zi
ya
Here difference is 15 - 5 = (10) (i)

19
3
(s
2. Divide the difference by (2) ie. (i/2)

sh
az
i
ya
3. Lower limit = l1 m - 1 / 2 (i)

19
3@
gm
upper limit = l2 = m + 1 / 2 x i

ai
l.
co
m
,9
4. .Open-end series

97
11
73
the lower limit of the first class & upper limit of the last class are missing

53
1)
instead of less
then and more than is written.

to solve it is assumed to have equal class intervals

hence, 0 - 10 & 30 - 40

5. Cumulative frequency
Frequency is continuously added corresponding to each class
interval

on the basis. of upper limit lower limit

with , less than ___ more than__
less than ___ more then___
 Important Questions with Answers
Q1. Heights (in inches) of 35 students of a class in given below. Classify the
following data in a discrete frequency series

Th
is
PD
F
be
lo
ng
Ans: In the form of frequency distribution, the given data can be arranged as

s
to
ss
follows.

ha
zi
ya
19
3
(s
sh
az
i
ya
19
3@
gm
ai
l.
co
m
,9
97
11
73
53
1)
Q2. Convert the following 'more than' cumulative frequency distribution into a
'less than' cumulative frequency distribution

Ans: The 'more than' cumulative frequency distribution can be presented in the
form of a 'simple frequency distribution' as follows.

From the above distribution, we can make the 'less than' cumulative frequency
distribution as follows.
 Th
is
PD
Q3. Prepare a frequency distribution from the following data:

F
be
lo
ng
s
to
ss
ha
zi
ya
19
Ans:

3
(s
sh
az
i
ya
19
3@
gm
ai
l.
co
m
,9
97
11
73
53
1)

NOTE : Worksheet (Important questions of all typology with

answers) is provided as a seperate PDF on website
padhleakshay.com