Statistics for Managers

An Introduction
 Nature created variation

Need for
statistics Uncertainty about future

Most of the decisions in

life or business are based
on expectation that
combines variability and
uncertainty.
 Statistics
• Means pieces of numerical
information.
• Statistics as a discipline is the body
of knowledge which is used for
collecting, organising, presenting,
analysing and interpreting
numerical data or data that may be
converted into numerical form.
 Business Statistics
• Science of good decision making under
uncertainty
• For good decision making management
requires information
• Statistics allows organizing and
meaningfully interpreting the collected
information
• Set of tools and techniques to convert
data into meaningful information.
 Three types of
Business Statistics
• Descriptive Statistics - designed to
describe data
• Include graphic methods and
numeric measures
• Graphic methods comprise of bar
charts, line graphs and pie charts
• Numeric measures include
measures of central tendency,
dispersion, skewness and kurtosis
 Descriptive
statistics

Sorting a large amount of

collected data in ways which
Gender Frequency Percent
enable its main features to be
seen immediately Male 224 89.6
Female 26 10.4
Mean , Median , Standard
Total 250 100.0
deviation
 Three types of
Business Statistics
• Inferential Statistics – facilitate
estimating the characteristics of a
population or making decisions
concerning a population on the basis
of a sample.
• Include estimation and hypothesis
testing
• the small amount of data that has
been collected (called the sample)
may be analyzed to infer general
conclusions about the total amount
of similar data that exist uncollected
in the world (called the population).
• Inferential statistics
Using sample to infer general conclusions about population
E.g.. Opinion poll

Population

Sample
 Parameters and Statistics
• Characteristics of a population is termed
parameters
• Characteristics of a sample are termed
statistics
 Three types of
Business Statistics
• Predictive statistics- understand
the relationship between pair of
variables and try to predict one
variable on the basis of other.
• Eg: advertisement expenses and
sales
• Also includes reliable forecasts of
variables like Time series analysis.
• Depends on :
• Research facilities available
• Extent of accuracy required
in analysis
• Time span of the study
• Amount of money required
Sources of data
 Understanding Data
• Data refers to facts and figures
• Data set refers to all the data collected for a
particular study
• Elements entities on which data are collected
• Variable piece of information about every
element
• Observation measurements collected in
respect of an element
Data Set
 Types of Statistical Data
• Data sets can be classified on different bases
including :

(i) Kind of measurement: qualitative or quantitative

data
(ii) Number of variables: univariate, bivariate or
multivariate
(iii) Time series and cross sectional data
Organizing Data
 Classification of data
• Arranging data in groups/classes on the basis
of certain properties.
• Helps in
- Condensing raw data
-Reveal salient features
-Facilitates comparison
 Basis of classification
• Geographical
• Chronological
• Qualitative
• Quantitative
 Organizing data using data array
• At the initial level, the most convenient way to
arrange data in a systematic form is to put
them in the order of magnitude.
 Frequency distribution
• At the next level of organizing and
summarizing data is to reduce them into a
convenient number of groupings, called
classes.
• The observations falling in different classes
are identified , counted and their number
indicated against each class – frequency
distribution
• Classes must be non-overlapping
• Number of observations in each class is
referred to as frequency denoted as f.
• Width of the classes is known as class interval
• Class boundaries are known as class limits.
• 2 limits:Upper Limit and Lower Limit
 Divided into two types:

• Univariate Frequency Distribution

- Individual observation
- Discrete Frequency Distribution
- Continuous Frequency Distribution
• Bivariate Frequency distribution
 Individual observation
• Series where items are listed individually after
observation.
Roll no Marks
1 40
2 33
3 27
4 38
5 41
6 55
 Discrete Frequency Distribution
• The term discrete implies distinct or separate.
• refers to the type of quantitative data that relies on
counts.
• Outcomes are measured in fixed numbers.
• contains only finite values, whose subdivision is not
possible.
Eg : Number of students in each elective
Electives Frequency
Marketing 15
Finance 16
Operations 8
Human Resource 15
IB 6
60
 Continuous Frequency Distribution
• an unbroken set of observations; that can be
measured on a scale.
• any numeric value, within a finite or infinite
range of possible value.
Eg : Shows the marks secured by a student in
Finance
Class Frequency
0-20 15
20-40 16
40-60 8
60-80 15
80-100 6
60
1.Discrete data is the type of data that has clear spaces between values.
Continuous data is data that falls in a continuous sequence.

2.Discrete data is graphically represented by bar graph whereas a

histogram is used to represent continuous data graphically.

Discrete: Number of students in the school, the number of cars in

the parking lot, the number of computers in a computer lab, the
number of animals in a zoo, etc.
Continuous: Age, height or weight of a person, time taken to
complete a task, temperature, time, money, etc.
 Constructing a frequency distribution
• Tally method is used to construct frequency
distribution
• Decide the number of class intervals
Number of class = √Number of observation

• Determine the width of class interval

Width of the class interval = Range/ number of classes
Range = max-min

• Determine the class limits

- two limits upper limit (U) & lower limits(L)
- midpoint or class mark =(L+U)/2
 Two methods of classifying data into class

Exclusive Method Inclusive Method

Class Frequency Class Frequency

0-20 6 0-19 6
20-40 6 20-39 6
40-60 8 40-59 8
60-80 4 60-79 4
80-100 4 80-99 4

• Convert Inclusive method to exclusive method

• Deduct correction factor from lower limits and add it to upper limits
 Illustration 1
• From the following data about the number of
defective units produced by 32 workers in the
last week, prepare a frequency distribution by
taking a suitable group size:
14 3 8 6 8 6 8 11 9 13 6 4 7 8 3 6

4 5 12 7 9 12 10 11 5 7 8 9 6 3 5 7
 Solution
Class Interval Tally Marks Frequency
3-5 IIII 5
5-7 IIII III 8
7-9 IIII IIII 9
9-11 IIII 4
11-13 IIII 4
13-15 II 2
 Illustration 2
• From the following data about the number of
children in a house, prepare a frequency
distribution

1 2 1 3 3 1 2 1 1 2
2 1 3 1 1 2 1 2 1 3
0 2 3 0 1 0 2 1 3 2
• The take –home salary of 30 unskilled workers
from a company for a particular month was
3482 3392 3499 3412 3440 3444
3446 3540 3394 3365 3412 3458
3482 3394 3450 3444 3440 3494
3460 3425 3500 3390 3414 3365
3390 3460 3422 3500 3470 3428

• Construct a frequency distribution having a

suitable number of classes.
 Bivariate Frequency Distribution

• Frequency distribution that involve two variables is

known as bivariate frequency table

• For example: income & expenditure, demand & supply

etc

• Conditional frequency – Frequency distribution of variable x

for a given value of y
• Marginal frequency - The frequency of values of variables x
and y together with their frequency totals are called as
marginal frequencies
 Bivariate Frequency Distribution
• Construct a bivariate frequency table. Also prepare marginal
frequency table and conditional frequency distribution
Income No. of Income No. of Income No. of Income No. of Income No. of
Families Families Families Families Families

5500 12 2250 25 6800 13 2020 29 6890 11

6230 14 3100 26 3000 25 2550 27 5230 12

3100 18 6400 20 4250 16 4920 18 3170 18

4200 16 5120 18 5550 15 5870 21 3840 17

6000 15 6900 12 3250 23 6430 19 4000 19

 Solution

Income Number of families Marginal

frequency
10-15 15-20 20-25 25-30

Conditional frequency
2000-3000 3 3
3000-4000 3 1 2 6
4000-5000 4 4
5000-6000 2 2 1 5
6000-7000 4 2 1 7
Marginal 6 11 3 5 25
frequency
 Types of frequency distribution
• Cumulative frequency distribution
- Less than type(corresponds to the upper limit)
- More than type(corresponds to lower limit)
• Relative frequency distribution
-class frequency/total number of observations
• Percentage frequency distribution
-(class frequency/total number of observations)* 100
Less than & More than cumulative
Classes Frequency Relative Frequency Percentage
Frequency
0-5 5
5-10 22
10-15 13
15-20 8
20-25 2

Classes Frequency Classes Frequency

Less than 5 5 More than 0 50
Less than 10 27(5+22) More than 5 45(50-5)
Less than 15 40(27+13) More than 10 23(45-22)
Less than 20 48(40+8) More than 15 10(23-13)
Less than 25 50(48+2) More than 20 2(10-8)
Tabulation of data
 Tabulation
• Summarizing and presenting the data in a
systematic form in rows and columns
• Simplify the complex data
• Depicts trend
• Facilitates comparison and other statistical
analysis.
 Parts of Tabulation
1. Table number
2. Title
3. Head note in brackets if any
4. Caption: column head
5. Stubs: Row head
6. Body of the table
7. Foot note
8. Source note
Diagrammatic and Graphical
representation
 Diagram
• Visual form for presentation of statistical data.
• Bar diagrams, circles, maps, pictorials,
cartograms or statistical maps
Simple Bar Diagram
Sub-divided bar diagram
Multiple Bar Diagrams
 Pie chart
• Circular diagram used to represent data
• Represent relative frequencies or percentages
• To draw a pie chart we first convert the given
values or percentages into degrees that would
total up to 360.
 Problem

Draw a pie chart for the following data

Company name Net Sales

GSK Consumer Ltd 900

Colgate Palmolive 1500

HUL 8000

Nestle India Ltd 4000

 Percentage Angle
GSK Consumer
Ltd 900 6.25% 22.5

Colgate
Palmolive 1500 10.42% 37.5

HUL 8000 55.56% 200

Nestle India Ltd 4000 27.78% 100

14400 360
Pictograms
Cartograms
 Graphic presentation
• Information contained in a frequency
distribution can be shown graphically
• Principle charts of frequency distribution with
class intervals are histogram, frequency
polygon and ogive.
 Classification of graphs
• Mainly two heads:
1. Graphs of frequency distribution
• Histogram
• Frequency polygon
• Frequency Curve
• Ogive or cumulative frequency curve
2. Graphs of Time series
• Line graph
 Histogram
• Histogram is a snap shot of the continuous
frequency distribution .
• x-axis represents classes and y-axis represent
frequency.
Example

Class Frequency 8
0-20 4
Frequency
6

20-40 6
40-60 8
4

60-80 6
2

80-100 4
0 -20 20-40 40-60 60-80 80-100

Classes
 Frequency polygon
• Line chart to represent frequency distribution
with continuous data
• Formed with a number of distinct lines
• Use midpoints of various classes
• Frequency curve may be drawn corresponding
to frequency polygon by free hand
 Histogram and Frequency polygon
8
6
Frequency

4
2

0 -20 20-40 40-60 60-80 80-100

Classes
 Frequency Curve
• Smooth free hand curve drawn through the
vertices of a frequency polygon
• Objective of this curve is to eliminate the
erratic ups and downs
 Ogive
• Ogive curve is the graphical representation of
the cumulative frequency distribution using
numbers or percentages

• Less than values on x axis and cumulative

frequency in numbers or percentages are on y
axis

• A curve is drawn connecting the cumulative

frequencies that corresponds to the upper
boundaries of the class
 Class Frequency Cumulative frequency in numbers
0-20 6 6
20-40 6 12
40-60 8 20
60-80 4 24
80-100 4 28
Cumulative frequency

Less than Values

Graphs of Time series
 Problems
1. Create the frequency Distribution table, histogram, frequency
polygon ,ogive and relative frequency for the following data

6 18 54 67 93 41 66

54 12 23 26 33 52 67

33 8 17 35 83 7 75

35 49 57 56 99 55 81
 Solution:
1. Calculate Range = max-min i.e.. 99-6= 93

2. Number of class = √Number of observation

= √28 = 5.29 So 5 classes can be
taken

3. Width of the class interval = Range/ number of

classes
= 93/5 = 18.3
So width can be fixed as 20 approximately
 Solution:
Frequency table
Class Frequency

0-20 6

20-40 6

40-60 8

60-80 4

80-100 4
 Relative frequency distribution

Cumulative
frequency in Relative
Class Frequency numbers frequency
0-20 6
6 0.214
20-40 6
12 0.214
40-60 8
20 0.285
60-80 4
24 0.142
80-100 4
28 0.142
 Solution:
Histogram and Frequency polygon
8
6
Frequency

4
2

0 -20 20-40 40-60 60-80 80-100

Classes
 Class Frequency Cumulative frequency in numbers
0-20 6 6
20-40 6 12
40-60 8 20
60-80 4 24
80-100 4 28
Cumulative frequency

Less than Values

 Problem
2. Construct a histogram and frequency polygon
from the data.
Marks: 5-9 10-14 15-19 20-24 25-29 30-34

Students 4 17 25 32 13 6

Class Frequency
4.5-9.5 4
9.5-14.5 17
Solution 14.5-19.5 25
19.5-24.5 32
24.5-29.5 13
29.5-34.5 6
0 4.5 9.5 14.5 19.5 24.5 29.5 34.5