Quantitative Reasoning

Ms. Zunaira Khurrum

Statistics Department

(Only the main points are covered on the slides. Please ensure the
use of reference books also)
Presentation of data
• The first step of statistical inquiry is the collection of data from any of the two sources
(primary and secondary).
• The next step is to organize or sort the data, arrange it in the form of table or frequency
distribution. It may be organized by classification, tabulation or graphical representation.

bar graph
No. of
brothers
x f 25

0 20 20

f
1 5 14
12
2 12
3 14 5

4 25 0 1 2 3 4
No. of Brothers
Classification of data regarding the structure involved
The data may be classified on any of the following basis:

1 2 3 4
• Classified on • Classified on • The data • Data classified
Qualitative

Quantitative
Geographical

Chronological
the basis of the basis of arranged by on the basis of
some quality some their time of discrete or
or attribute. geographical occurrence. continuous .
• Gender region or Also called Presented in
• Education location. time series the form of
level • Population of data. series of
major cities • Monthly shoe observations
• Religion
• Elevation data store sale or a frequency
• Eye color distribution
• River locations • Population of
• Marital status Pakistan from • 45,47,50,52,55
in Punjab
1990-2000 • Height of
• Latitudinal city
locations • Player students
performance • No. of cars in a
over time showroom
Classification of data
• Process of arranging observations into homogeneous (similar characteristics) groups or
categories.
• Example: sorting of letters in a post office. They are classified according to cities and
further according to sectors/streets.
One-way

Based on
Qualitative Two-way
variable

Manifold
Classification
Arrayed data

Based on Discrete
Quantitative frequency
variable distribution
Grouped
frequency
distribution
Classification according to Qualitative Variable

1 2 3
• When data are • When data are • When data are

Two-way
One-way

Manifold
sorted by one classified by two classified by
characteristic. characteristics more than two
• Car at a time. characteristics
Transmission • Based on at a time.
(Manual, religion(Muslim, • Based on
Automatic). This Non-Muslim) & religion(Muslim/
attribute has education Non-Muslim),
two levels also (Literate & education
known as Illiterate) (Literate /
dichotomy. Illiterate)
• Three levels & gender
known as (male/female)
trichotomy.
Classification according to Quantitative Variable

Arrayed data or series of individual observations

Discrete frequency distribution

Grouped frequency distribution

Tabulation
A table is a systematic arrangement of data into rows and columns and this process of
arranging data is called tabulation. Constructing of a table consists of the following parts:
1) Title
2) Column caption or boxhead
3) Row caption or stub
4) Body arrangement of table
5) Source note
6) Spacing and ruling
7) Prefatory notes
8) Foot notes
Types of Tabulation

Tabulation

One-way/Single Two-way/Double Manifold

(Data presented (Data presented (Data presented
relating to one relating to two relating to more than
characteristic) characteristics) two characteristics)
A series of individual observation
• A collection of data recorded as it is received from the field is known as
ungrouped data. Data not arranged systematically is called raw data. Example:
student marks; 52,47,55,65,60,45,50
• The arrangement of raw numerical data in ascending or descending order is
called arranged or arrayed data. Example: The students’ marks are arranged in
ascending order.
• 45,47,50,52,55,60,65 is arrayed data.
Frequency Distribution
• A compact tabular arrangement of data into different classes with corresponding class
frequency is a frequency distribution or a frequency table..
• The total number of times an event occurs is called frequency. Σf denotes the sum of
frequency and equals n (number of observations in the data set).
• The number of observations in a particular class is called class frequency and is denoted
by f.
• The frequency distribution can be constructed for discrete, categorical and continuous
data.
Ingredients of a frequency distribution
• Class limits: The smallest and largest value that can fall in a given class. For example,
in interval 120-130, 120 is the lower limit and 130 is the upper limit. When the data are
classified by inclusive method, they are called class limits i.e. the upper limit is included in
the interval)
• Class Boundaries: True class limits that are needed when working with continuous data.
When the data are classified by exclusive method, they are called class boundaries i.e. the
upper limit is excluded from the interval. Next class will absorb the observation.
• Class intervals: The difference between two successive lower-class limits or two
successive upper-class limits.
• Class marks: The midpoint between the upper and lower class boundary/limits is called
class mark or midpoint denoted by “X”.
• Tally marks: Data may be entered as vertical dashed lines in various classes. Five
dashes make one unit.
 Ingredients of a frequency distribution
Midpoint

Lower
limit

Upper
limit

Lower Upper
class class
boundry boundary
Discrete frequency distribution
• If the number of observations is written once with the number of times it occurs in a
tabular form, it is known as discrete frequency distribution.
Categorical frequency distribution
Constructing a group frequency distribution
1. Determine the Range i.e. maximum value of data –min value of data.
2. Determine the no. of classes (k) by the following rule:
k=√n
3. Estimate the approximate width of the interval, h
𝑅𝑎𝑛𝑔𝑒 𝑅
h= =
𝑁𝑜.𝑜𝑓 𝑐𝑙𝑎𝑠𝑠𝑒𝑠 𝑘
4. Make class boundaries
5. Determine class marks
6. Tally marks
7. Make the frequency column
8. Sum the frequencies which should come out to be the same as no. of
observations in the data.
Any Questions