Sei sulla pagina 1di 65

NEW HORIZON COLLEGE

MARATHALLI, BANGALORE
(Affiliated to Bangalore University)
A Recipient of Prestigious Rajyotsava State Award 2012 conferred by the Government of Karnataka

II SEM BBM STUDY MATERIAL

QUANTITATIVE METHODS FOR BUSINESS

(QMB II)

Prepared By

Nandita Matad

Ring Road, Bellandur Post, Near Marathalli, Bangalore - 560 103


Tel : +91-80-6629 7777 Fax : +91-80-2844 0770
E-mail : principalnhc.edu@gmail.com
Web : www.newhorizonindia.edu
1
TITLES PAGE NUMBER
S.NO
1. INTRODUCTION TO STATISTICS 4-15

2. MEASURES OF CENTRAL 16-24


TENDENCY

3. MEASURES OF DISPERSION 25-37

4. CORRELATION AND 38-45


REGRESSION ANALYSIS

5. INDEX NUMBERS 46-53

6. TIME SERIES 54-57

7. REFERENCE BOOK 57

8. PREVIOUS YEAR QUESTION 58-64


PAPER

2
3
1: INTRODUCTION TO STATISTICS

BACKGROUND AND BASIC CONCEPTS


INTRODUCTION:

Today our culture has become a statistical culture because every citizen finds statistics in
newspaper, magazines, advertisement in radios and televisions etc.

The figures relating to the various aspects of his life social political and economic
represent and support the absolute facts and situations. The reader analysis the figures and
arrives at certain conclusion.

EXAMPLE:

A prospective investor is interested in the profitability of the business enterprise and his
analysis the income statement and balance sheet of the enterprise for a number of years. Such
analysis helps him to decide whether to invest or not.

DEFINITION OF STATISTICS.

Statistics has been defined in two way;

(a)Singular way (or) sense.

(b)Plural sense.

In plural sense it means a collection of numerical facts.

In singular sense it is a complete body of principles and techniques used in collecting


and analyzing numerical data.

DEFENITION 2

By Prof Horace Secrist: Statistics may be defined as the aggregate of facts affected to a
marked extent by multiplicity of causes, numerically expressed enumerated or estimated
according to a reasonable standard of accuracy, collected in a systematic manner, for a
predetermined purpose and placed in relation to each other.

DEFENITION 3

According to Croxton and Cowden Statistics may be defined as a science of collection,


presentation, analysis and interpretation of numerical data.

COLLECTION:

It is the first step in statistical investigation. The collection part is the backbone of the enquiry.
If the of data is not in proper form in that case conclusion drawn can never be reliable.

4
The source of collection may be primary or secondary data.

Primary data: If the data are collected originally by the investigator for the given enquiry it
is termed as primary data.

Secondary data: if he makes use of the data which had been earlier collected by someone
else, it is termed as secondary data.

PRESENTATION: After collection and organizing the data should be presented. If the
data are presented systematically, the statistical analysis gets facilitated. As far as the
presentation of data is concerned either through diagrams or graphs. The classified data is to be
presented in such a way that it becomes easily understandable.

ANALYSIS :

Once the data is collected, presented the next step is that of analysis is to prepare data in such a
fashion so as to arrive at certain definite conclusion.

The method most commonly used are;

1. Measure of central tendency .

2. Measure of dispersion .

3. Correlation and Regression .

INTERPRETATION:

The last stage of statistical investigation is to drive the results and give comments on
the enquiry in question. Interpretation is to draw conclusion from the data collected and
analyzed. If the analyzed data is not properly interpretated the whole object of the enquiry may
be erroneous.

USES OF STATISTICS:

Every field of human activity makes use of statistics. Business houses, Government,
departments public sector undertaking, social reformers, economist etc, all use statistics.

The important uses of statistics to different sectors of the society are given below.

1.Statistics is the arithmetic of human welfare because the problems relating to unemployment,
food storage, poverty etc, cannot be analyzed without the use of statistics.
2. Statistics are great use to business man. A business man can estimate demand for his
product in different parts of the year correctly with the help of statistics.
2.It is useful to insurance companies because the insurance companies need exact information
of vital statistics to prepare mortality table and premium plans.
3.Statistics is very useful to bankers and banking industry in deciding the policies regarding
deposits advances etc.
5
4.Statistics analysis of railway working is very useful in determining the efficiency of services
their requirements and their expansion programmes.
5.Statistics is very useful to finance ministers who prepare annual budget and outlines the
physical policy on the basis of statistics collected in the various departments.
6.The educationist makes use of statistics for evaluating the performance of students and
teacher.
7.Statistics helps the administrator to know the social and economic ambitions of the society.
8.It is very much useful to the economists who prepares economic planes and frame economic
policies for the state.
9.It is useful to social reformer who has to carry on his activities based on statistics. The
incident of certain diseases, seriousness of beggar problem, child marriage etc, all need
statistics for their solution.

OBJECTS OF STATISTICS:

1.To throw light on the complex man data and make sense from them.
2.To take action on the data processed.
3.To draw conclusion on the analyzed data.
4.To estimate and forecast the trends in future from the past data.
5.To ascertain the reliability of statements.
6.To assist the research studies in gaining knowledge.
7.To prove unknown from the known data.
8.To examine change in the economic activities.

FUNCTIONS OF STATISTICS:

1.It assists in providing a better understanding and description of nature of data.


2.It helps the research workers in efficient and proper planning of any field of enquiry.
3.It guides in appropriate quantitative data.
4.It simplifies complex and un wieldy data and presents the same in an attractive form.
5.It studies quantitative observations to enlarge individual knowledge.
6.It guides the business in planning.
7.It discloses the facts hidden in the mass data.
8.It establishes relationship among the related data.

LIMITATION OF STATISTICS:

Science of statistics suffers from various limitations. If the limitations are not kept in mind the
conclusions reached will not be dependable. The following are the main limitations of statistics.

1.Statistics does not deal with individual:


Statistics does not deal with the aggregates rather than individuals. An individual item like
weight of a student in a class is 60kg is not called as statistics. In statistical method we deal
with aggregates and not with single figure. When we say that the average weight of a class is
60kgs this individual value refers to the aggregate of individuals.
6
2.Quantitative aspect ignored:
Statistical methods cannot study the nature of phenomenon which cannot be
expressed in quantitative form. The phenomenon which cannot be a part of the study of
statistics. These characteristics include health intelligence, beauty, honesty etc. there is no
doubt that the data which cannot be quantitatively expressed needs conversion of qualitative
data into quantitative data then we can easily apply the statistics techniques on this converted
data.

3.Statistics can be misused:


Statistics can be misused by ignorant (or) wrongly motivated persons. The data
used by untrained people can lead to misleading results.

4.Statistics laws are true only on an average:


Laws of physical science are perfect but statistical laws are not so perfect as the
laws of physics (or) chemistry. Statistical results are true only on the average.

5.Statistics is only a means:


Statistics is only one of the methods of studying a problems like culture, religion
etc, and statistics simplifies complicated data. Before using the data the background of the data
may be studied.

6.Statistics does not reveal entire story:


It provides solutions to the problems but does not study the problems themselves.
It is only a mean to an end but not at end itself.

DISTRUST OF STATISTICS:

The improper use of statistical tools by unscrupulous people with an improper statistical bend
of mind has led to the public distrust in statistics. By this we mean that public loses its belief,
faith and confidence in the science of statistics and starts condemning it. Such irresponsible,
inexperienced and dishonest persons who use statistical data and statistical techniques to fulfill
their selfish motives have discredited the science of statistics with some very interesting
comments, some of which are stated below:

1. An ounce of truth with produce tons of statistics.


2. Statistics can prove anything.
3. Figure do not lie, Liars figure.
4. Statistics is an unreliable science
Some of the reasons for the above remarks may be enumerated as follows.

7
a) Figures are innocent and believable and the facts base on them are psychologically more
convincing. By it is a pity that figures do not have the label of quality on their face.
b) Arguments are put forward to establish certain result which are not true by making use of
in-accurate figures or by using incomplete data. This destroying the truth.
c) Though accurate, the figures might be molded and manipulated by dishonest and
unscrupulous persons to conceal the truth and present a working and distorted picture of the
facts to the public for personal and selfish motives.
Hence if statistics and its tools are misused the fault does not lies
with the science of statistics rather, it is the people who misuse it, are to be blamed.

8
COLLECTION AND TABULATION OF DATA.

Collection of data is the process of searching, measuring, enumerating and systematically


recording of relevant, accurate facts and figures relating to a certain phenomenon.

Sources of Data

1) Primary source.
2) Secondary source.

Primary Source:
The data which are originally collected for the first time are called Primary
Data.
“Census” or “sample” technique is adopted in collecting the primary data. The collected raw
data is edited and scrutinized by detecting the errors and omitting the irrelevant and
inconsistent information.

The sources of collecting the primary data are:


i. Direct Personal observations:
Investigations themselves go to the field personally observe and
collect the information from the informants.

ii. Indirect Oral Interview:


Investigations used to appoint experienced enumerators to collect the
data. The enumerators are asked to interview the respondents and record the answer given by
them.

iii. Local Agencies:


Investigators used to appoint local agents or correspondents in different parts of the
area to collect the data.

iv. Questionnaires:
A questionnaire is a list of logically arranged questions relating to the field of
enquiry and providing space for the answer to be filled in by the respondents.

v. Schedules:

It is a printed list of simple questions. it is sent to the respondents through the


enumerators. The enumerators discuss personally with the respondents and record their
answers in the schedule.

Secondary Data or Source:

9
Secondary sources are sources of data which consists of readily
available compendia and already compiled information. They consist of published records,
reports and unpublished but already used records.

The Sources of Secondary data.


1) Published Sources:
It refers to the data sources which are available in printed format. Like
journals, newspapers, books, websites etc.

2) Unpublished Sources:
The data which are not available in printed form. There are various data
available which are unwritten in any format.

Eg: Folk songs, traditional songs, customs etc.


Secrets in business sectors, unwritten rules,
unofficial activities which cannot be published.

Techniques of Data Collection.


1) Census Technique.
2) Sample Technique.

Census Technique:
When each and every unit of population under study is considered and
collected for a statistical investigation.

Sample Technique:
The terminology “sampling” means the process of selecting a part of the
population under study with a view to obtaining information about the whole population.

Classification of Data.
Classification is the process of arranging the data into sequences and groups according to their
common characteristics them in to different but related parts.
-by- Horace Secrist.

Objectives of Classification of data.


1. To condense the mass of data.
2. To facilitate comparison.
3. To bring homogeneity to heterogeneous features of raw data.
4. To highlight the most significant features contained in the data at a grance.

10
Qualitative Classification: Data are classified according to attribute or characteristics or
qualities. Generally the qualitative phenomena are not measurable. However, they can be
studied with reference to their presence or absence like educated or uneducated, married and
unmarried, boys and girls so on.
Simple classification - It involves only 2 fold (two-fold).

Composite Classification- It involves more than 2 fold (manifold).

Arbitrary-> It refers to the attribute, which are not clearly defined and which no demarcation
can be made. Ex:- tall persons and short persons . we should give the correct height above
which the persons are considered tall and below which they are short.

Quantitative Classification.
Data are classified according to quantities that are measurable such as
age, weight, marks, price and so on.

11
Tabulation
A statistical table is the logical listing of related quantitative data is vertical columns and
horizontal rows of number with sufficient explanatory and qualifying words, phrases and
statements in the form of titles, heading and footnotes to make clear the full meaning of data
and their origin.
-by Tuttle.

Parts of a statistical Table. [Tabulation]


1. Table number
2. Title of Table.
3. Data.
4. Row designation.
5. column Heading.
6. Body of the Table.
7. Head note.
8. source of Data.
9. Foot note.

Types of Tabulation.
1.Simple Tabulation (one-way):-
When the data are tabulated to one characteristics.
Ex: - Table showing number of employees in Canara Bank according to age-group.

Age(in year) No. of Employees

Below 30 15
30-40 18
40-50 9
50 and 3
Above

12
2.Double Table:-
When data are tabulated to 2 characteristics at a time.
Ex:-
Table showing number of employees in Canara Bank according to age and sex

Age No. of Employees Total


Sex Male Female
(in year)
Below 30 9 6 15

30-40 10 8 18

40-50 2 7 9

50 and Above - 3 3

Total 21 24 45

3.Complex Table:- Table showing number of employees in Canara Bank according to age, sex
and marital status.

No. of Employees Grand


Marital Total
Status Male Female
Sex

Age group Mrd. Un. Mrd. Total


Mrd. Total Un.Mrd.

Below 30 3 6 9 2 4 6 15

30-40 2 8 10 4 4 8 18

40-50 1 1 2 7 - 7 9

50 and - - - 3 - 3 3

Above

Total 6 15 21 16 8 24 45

Ex:-
In a sample study about coffee habit in 2 town the following
information was received.

13
Town-A : Females were 40%, Total coffee drinkers were 45%
and Males non-coffee drinkers were 20%.
Town-B : Males were 55% Males non-coffee drinkers were
30% and females coffee drinkers were 15%.
Represent the above in tabular form.

Town A B

Gender Male Femal Total Male Femal Total


Habit e e

Coffee drinker 40 5 45 25 15 40

Non coffee 20 35 55 30 30 60

drinker

Total 60 40 100 55 45 100

DIAGRAMS

Diagrams are visual aids of presenting the data in pictures, geometric figures
and curves. They present huge mass of quantitative data in a condensed form
attractively.

OBJECTS:

1) TITLE: Every diagram and graph must be given a suitable title. The title
should communicate and details of data presented in that diagram.
2) SCALE: As a guiding principle, the scale should be selected consistent with
the size of the paper and nature of the data to be displayed, so that the diagram obtained
is either too small or too big.
3) WIDTH AND HEIGHT: A proper proportion between the width and height
of the diagram should be maintained to make it look attractive and understandable.
4) INDEX: An index explaining different types of shades colours used should be
given.
5) NEAT AND SIMPLE: To be effective, the diagrams should be prepared
neatly and they should be simple to understand.
USES:

1) They present huge mass of quantitative data in a condensed form attractively.


2) They leave everlasting impression on the minds of laymen who are not
interested in devoting much time to see the numerical data.
3) They save time which would otherwise be lost in studying the numerical data.
4) They make the entire data visible at a glance.

14
LIMITATIONS:

1) Diagrams and graphs provide only an approximate value.


2) They are much useful to a common man than an expert.
3) Diagrams and graphs are not available for mathematical treatment of data.
4) They can be easily maneuvered(manipulate).

DIAGRAMS GRAPHS
They can be drawn on only paper- They can only be drawn on graph
plane (or) graph. papers.
Lines, bars, rectangles, circles, cubes, Dots, dashes, dot-dashes and curves
pictures are used in diagrams. are used in graphs.
They furnish information They furnish information in detail.
approximately. They depict time series and
They depict categorical and frequently distribution.
geographical data. They are easy to draw.
They are not easy to draw.

15
2: MEASURES OF CENTRAL TENDENCY
REQUISTIES OF A GOOD AVERAGE:

A good and ideal averages should be easily understood, simple in calculation,


based on all the observations, rigidly defined and capable of further algebraic treatment. It
should have sampling stability. It should not be unduly affected by the extreme values.

ARITHMETIC MEAN

It is the quantity obtained by dividing the sum of the values of the items in a variable
by the number of items.

PROBLEM:

Compute the mean wages of a worker from the following

data .

Wages(in Rs): 48-56 56-64 64-72 72-80 80-88 88-96 96-104.

No of workers: 8 3 11 14 5 7 2

C.I Frequenc x Fx A=76 fd i=8


y
(f) Mid d=X-
point A

48-56 8 52 416 -24 -192 -3 -24

56-64 3 60 180 -16 -48 -2 -6

64-72 11 68 748 -8 -88 -1 -11

72-80 14 76 1064 0 0 0 0

80-88 5 84 420 8 40 1 5

88-96 7 92 644 16 112 2 14

96- 2 200 24 48 3 6
104 100
n=∑f=50 3672 -128 -16

16
1 .DIRECT METHOD:

2. SHORTCUT METHOD:

3. STEP DEVIATION METHOD:

MERITS:

1) It is simple to understand and easy to compute.


2) It takes into consideration every item in the series in computation.
3) Its concept is familiar to most people.
4) Every data set has one and only one mean.

DEMERITS:
1) IT is very much affected by extreme value
2) Not useful in case of open-end classes.
3) It is not always reliable.
4) It may give wrong impression, if proper weights are not given.

MEDIAN:
Median is the value which divides the given series into two equal parts.
INDIVIDUAL OBSERVATION:

25 36 45 68 75
𝒏+𝟏 𝒕𝒉
Median is the size of( ) item
𝟐

5+1
n=5 = 3 item , so
2

Median is 45

DISCRETE SERIES
Problem:
Calculate median from the following data.
Value: 10 20 30 40 50 60.
Frequency: 28 36 24 32 40 16
17
Values Frequency(f) Cumulative
frequency(c.f)
10 28 28
20 36 64
30 24 88
40 32 120
50 40 160
60 16 176
176
𝒏+𝟏 𝑡ℎ
Median is the size of( ) item
𝟐

176+1
n=176 = =88.5
2

cumulative frequency just > 88.5 is 120


The value of X against 120 is 40

Therefore , 𝑀𝑒 is 40

CONTINUOUS SERIES

Problem:
Calculate median from the following data.
Value: 10-20 20-30 30-40 40-50 50-60 60-70.
Frequency: 28 36 24 32 40 16

Values Frequency(f) Cumulative


frequency(c.f)
10-20 28 28
20-30 36 64
30-40 24 88
40-50 32 120
50-60 40 160
60-70 16 176
176
𝒏
Median is the size of( 𝟐)𝑡ℎ item
176
n=176 = =88
2

cumulative frequency just > 88 is 120


The value of X against 120 is 40-50
Therefore median class is 40-50 ,

Me= l + i/f(n/2 - m)

= 40+ 10/32(88-88)

𝑀𝑒 is 40

18
MERITS OF MEDIAN:

1) It is easy to calculate and simple to understand.


2) It indicates the value of middle item in the distribution.
3) It can be determined just by inspection of the arrayed data.
4) Extreme values do not affect the median as strongly as they do the mean.

DEMERITS OF MEDIAN:

1) It is necessary to arrange the data.


2) It is a positional average, therefore each and every observation is not considered.
3) It ignores the extreme value.
4) It is not capable of further algebraic treatment as it is not based on mathematical property.

MODE:

Mode is the value which occurs more frequently in a set of observation and around which
the other items of the set of observations clustered densely. It is denoted by „Z‟.

INDIVIDUAL OBSERVATION:

Following are the values of variables.

54 66 42 64 44 86 104 94 100 80 72 64 64 44 64 72 54 48 52 50.

The mode is 64, as it occurs the highest number of times in the series. So the mode is clearly
defined as it is a uni - modal case.

DISCRETE SERIES:

It is that value which is having the maximum frequency.

Following are the distributions.

A Frequency
SERIES
X F
1 2
2 8
3 11
4 18
5 9
6 7
Highest frequency is 18.

Therefore, the value of X against 18 is 4.

19
So, the Mode is 4.

CONTINUOUS SERIES

Problem:
Calculate mode.

X: 0-5 5-10 10-15 15-20 20-25 25-30 30-35.

f: 1 3 10 6 11 9 1

here , highest frequency is 11 i.e.,


𝑓1 = 11 and modal-class is 2o-25 so l=20, i=5

behind 𝑓1 is 𝑓0 i.e.,
𝑓0 = 6

next to 𝑓1 is 𝑓2 i.e.,
𝑓2 = 9
𝑓 1− 𝑓 2
Z= l+ 2𝑓 ×𝑖
1− 𝑓 2 −𝑓0

11−6
Z= 20+ 2 ×5
11 −6−9

Z=23.5

Calculate mode by using grouping table.

X: 0-5 5-10 10-15 15-20 20-25 25-30 30-35.

f: 1 3 10 6 10 9 1

X 𝑓1 𝑓2 𝑓3 𝑓4 𝑓5 𝑓6
0-5 1 4 13
5-10 3 13 19
10-15 10 16 26
15-20 6 16 25
20-25 10 19 20
25-30 9 10
30-35 1

20
ANALYSIS TABLE:

X0-5 5-10 10-15 15-20 20-25 25-30 30-35


𝑓1
- - 1 - 1 - -
𝑓2
- - - - 1 1 -
𝑓3
- - - 1 1 - -
𝑓4
- - - 1 1 1 -
𝑓5
- - - - 1 1 1
𝑓6
- - 1 1 1 - -
0 0 2 3 6 3 1
The highest value is 6, therefore modal-class is 2o-25.
𝑓 1− 𝑓 2
Z= l+ 2𝑓 ×𝑖
1− 𝑓 2 −𝑓0

10−6
Z= 20+ 2 ×5
10 −6−9

Z=24

Empirical relationship among the averages is given by;

Mode (Z) = 3 median(𝑴𝒆 ) – 2 mean

Problem

From the following data find out the missing frequency if the median is
50.

Class interval: 10-20 20-30 30-40 40-50 50-60 60-70

Frequency: 2 8 6 - 15 10

Sol:

C.I f cf

10-20 2 2

20-30 8 10

30-40 6 16

40-50 A 16+A

50-60 15 31+A

21
60-70 10 41+A

41+A

Me= 50

So median class is 50-60 ( 50 lies in CI 50-60)

CI is 50-60

l= 50, i=10, f=15, m=16+A , n= 41+A, Me=50

Me= l+i/f[n/2-m]

50= 50+10/15[ 𝟒𝟏+𝑨


𝟐
-(16+A)]

50-50=0.667[ 41+𝐴 −2(16+𝐴


2
)
]

0= 5[9-A]

A=9

Problem

Find out the missing frequency from the following data.

Class intervals: 10-20 20-30 30-40 40-50 50-60 60-70 70-80 total:229

Frequency: 12 30 - 65 - 25 18

Complete the distribution if its median is 46.

Sol:

CI f cf

10-20 12 12

20-30 30 42

30-40 A 42+A

22
40-50 65 107+A

50-60 B(79-A) 186

60-70 25 211

70-80 18 229

Total 229

 12+30+A+65+B+25+18=229
 A+B+150=229
 A+B=229-150
 A+B=79
 B=79-A

Me=46

Median class is 40-50

l= 40, i=10, f=65, m=42+A , n= 299, Me=46

Me= l+i/f[n/2+m]

Me= 40+10/65[299/2+(42+A)]

A=33.5

B=79-33.5

B=45.5
Problem

From the following data find out the missing frequency when its
arithmetic mean is 25.

Class interval: 0-10 10-20 20-30 30-40 40-50 total

Frequency: 5 - 15 - 5 45

Sol:

CI x f fx

23
0-10 5 5 15

10-20 15 A 15A

20-30 25 15 375

30-40 35 B(20-A) 700-35A

40-50 45 5 225

Total n=45 ∑𝒇𝒙 =1325-20A


∑𝒇𝒙
𝐱= 𝒏 Given 𝐱 = 𝟐𝟓

1325−20A
𝟐𝟓 = 𝟒𝟓

A=10 B=20-A=20-10

B=10

24
3: MEASURES OF DISPERSION

Measures of Dispersion are the averages of second order. They are based on averages of
deviations of the values obtained from central tendencies. The average of second order is an
average of difference of all items of the series from an average of those items.

Following are the distinctions between central tendencies and dispersion:

Central Tendencies Dispersions


1. Averages of first order. 1. Averages of second order.
2. Do not throw light on the formation 2. Throw light on the formation of
of series. series/distribution.
3. Do not give detailed features of 3. Give detailed characteristics of
observations. observations.
4. Do not establish relationship with the 4. Establish relationship with the
items. individual items.
5. Do not reveal entire picture of the 5. Reveal entire picture of the
distribution. distribution.

The objectives of computing averages of second order are:

i. To ascertain the consistency of performance.


ii. To decide the consistency of performance
iii. To reveal the degree of uniformity in the series.

Different types of measurement of dispersion:

1. Range
2. Quartile Deviation
3. Mean Deviations
4. Standard Deviation.

RANGE:

Range represents the difference between the values of the extremes, the largest value and
the smallest value.

25
R=L-S

R = Range

L = largest value

S = smallest value

Co-efficient of Range = 𝐿−𝑆


𝐿+𝑆

Merits of Range:

1. It is the simplest measure of dispersion


2. It is used in statistical quality control.
3. It is useful in studying the variations in prices of share and stocks.
4. It requires very less calculation.

Demerits of Range:

1. It is not a stable measure of dispersion because it is affected by extreme values.


2. It is not suitable for mathematical treatments.
3. It is very sensitive to fluctuations in the sampling size.

Problem:
Compute the range and co-efficient of range of the series and state which one is more
dispersed and which one is more uniform.

SERIES values of variable

1 13 14 15 16 17 (mean=15)
2 9 12 15 18 21 (mean=15)
“Central tendency is same but formation differs”.
SERIES 1
R=L–S
R = 17 - 13
R=4

Co-efficient of Range = 𝐿−𝑆


𝐿+𝑆

= 17 −13
17 +13

= 0.133

26
SERIES 2
R=L–S
R = 21 – 9
R = 12

Co-efficient of Range = 𝐿−𝑆


𝐿+𝑆

= 21 −9
21 +9

= 0.4

Conclusion :

SERIES 1 is more uniform and less dispersed.

SERIES 2 is more uniform and moderately dispersed.

QUARTILE DEVIATION

Quartile deviation is the measures of dispersion based on the upper quartile 𝑄3 and lower
quartile 𝑄1 .

Q.D = 𝑄 3−2 𝑄 1 . This is the absolute method of dispersion.

Co-efficient of Q.D = 𝑄𝑄 33 −+ 𝑄𝑄 11 . This is relative measure of dispersion.

Merits of Quartile Deviation:

1. It is very easy to calculate and simple to understand.


2. It is not affected by extreme values of variable as it is concerned with the central
half of the portion of the distribution.
3. It is not affected by open end class intervals.

Demerits of Quartile Deviation:

1. It ignores the portions below the lower quartile and upper quartile.
2. It is not capable of further mathematical treatment.
3. It is greatly affected by the fluctuations in the sampling

Problem:
Compute Q.D and its Co-efficient for the following data.

Value: 10 20 30 40 50 60.

Frequency: 28 36 24 32 40 16

27
Values Frequency(f) Cumulative
frequency(c.f)
10 28 28
20 36 64
30 24 88
40 32 120
50 40 160
60 16 176
176
𝒏+𝟏 𝒕𝒉
𝑸𝟏 𝒊s the size of( ) item.
𝟒

n=176 → 1764+1 =44.25.

cumulative frequency just > 44.25 is 64.

The value of X against 64 is 20.

So, 𝑄1 = 20
𝟑(𝒏+𝟏) 𝒕𝒉
𝑸𝟑 is the size of( ) item.
𝟒

3(176+1) 𝑡ℎ
n = 176. → ( ) item= 132.75.
4

cumulative frequency just > 132.75 is 160.

The value of X against 160 is 50.

So, 𝑄3 = 50.

Q.D = 𝑄 3−2 𝑄 1
50 −20
= 2

Q.D = 15.

Co-efficient of Q.D = 𝑄𝑄 33 −+ 𝑄𝑄 11 .

= 50 -20 /50+20 =0.428

MEAN DEVIATION

It is the average amount of difference of the items in a distribution from either the mean or
median or mode ignoring the signs of the deviation.

INDIVIDUAL OBSERVATION:
∑d
δ= 𝑛

𝛿 𝛿 𝛿
Coefficient of δ = 𝑀 or or
𝑒 z 𝑋

28
DISCRETE AND CONTINUOUS SERIES

δ = ∑𝑓𝑑
𝑛

𝛿 𝛿 𝛿
Coefficient of δ = 𝑀 or or
𝑒 z 𝑋

Question: From the following variable find the mean deviation and coefficient of mean
deviation from the mean:
X: 68 49 32 21 54 38 59 66 41
Solution: Arrange the data in an ascending order to have the short cut method applicable:

Computation of Mean Deviation


𝑥=∑x/n=428/9=47.56

X (x-𝑥)
21 26.56
32 15.56
38 9.56
41 6.56
49 1.44
54 6.44
59 11.44
66 18.44
69 20.44
∑x=428 ∑d=116.44
∑𝑑
𝛿=
𝑛

=116.44/9= 12.937

Coefficient of δ=δ/𝑥
=12.9378/47.56
=0.272
Question: Following are runs scored by the batsmen in different innings of cricket tests.
Runs: 20 40 60 80 100 120 140 160 180
No of batsmen 6 19 40 23 65 83 55 20 9
Compute mean deviation from mode and its coefficient

29
Solution: Computation of mean deviation:
X f (x-z)=d fd
20 6 100 600
40 19 80 1520
60 40 60 2400
80 23 40 920
100 65 20 1300
120 83 0 0
140 55 20 1100
160 20 40 800
180 9 60 540
n=320 ∑fd=9180

The highest frequency is 83


Z=120
δ=∑fd/n=9180/320=28.69
Coefficient of δ
=δ/z=28.69/120=0.239

Problem: Calculate mean deviation from mean from the following data.

X : 48-56 56-64 64-72 72-80 80-88 88-96 96-104.

f : 8 3 11 14 5 7 2

C.I Frequency X d = x -𝑋 fd fx

(f) Mid
point
48-56 8 52 21.44 171.52 416

56-64 3 60 13.44 40.32 180

64-72 11 68 5.44 59.84 748

72-80 14 76 2.56 35.84 1064

80-88 5 84 10.56 52.8 420

88-96 7 92 18.56 129.92 644

96-104 2 100 26.56 53.12 200

n=∑f=50 ∑fd = 3672


543.36

30
δ = ∑𝑓𝑑
𝑛

= 543.36/50 = 10.8672
𝛿
Coefficient of δ = 𝑋

= 10.8672/73.44
= 0.14797
problem:

Calculate mean deviation from median and also find its co-efficient.
Value: 10 20 30 40 50 60.
Frequency: 28 36 24 32 40 16

X f Cumulative d = X- fx fd
frequency(c.f) 𝑀𝑒

10 28 28 30 280 840
20 36 64 20 720 720
30 24 88 10 720 240
40 32 120 0 1280 0

50 40 160 10 2000 400


60 16 176 20 960 320
176 5960 ∑𝑓𝑑
=2520

𝑛+1 𝑡ℎ
𝑀𝑒 is the size of( ) item.
2
176+1
n=176 = =88.5
2

cumulative frequency just > 88.5 is 120

The value of X against 120 is 40

Therefore, 𝑀𝑒 is 40

δ = ∑𝑓𝑑
𝑛

31
= 2520/176

δ = 14.3181

𝛿
Coefficient of δ = .
𝑀𝑒

= 14.3181/40

= 0.35795

Problem:

Compute the mean deviation from mode.


X = 20 40 60 80 100 120 140 160 180
f = 6 19 40 23 65 83 55 20 9

X F d=X-Z Fd

20 6 100 600

40 19 80 1520

60 40 60 2400

80 23 40 920 Mode is the highest frequency, that is


83
100 65 20 1300 The value of X against 83 is 120

120 83 0 0 Mode is 120

δ = ∑𝑓𝑑
𝑛
140 55 20 1100
= 9180/320
160 20 40 800
δ = 28.687.
180 9 60 540 𝛿
Coefficient of δ = Z .
∑fd=9180 = 28.687/120
= 0.2390

32
Merits of Mean Deviation:
1. It is rigidly defined and easy to compute and understand.
2. It takes all items into consideration and gives weight to deviation according to
their size.
3. It is less affected by extreme values of variable.
4. It removes all the irregularities by obtaining deviations and provides a correct
measure.

Demerits of Mean Deviation:


1. It does not lend itself readily to algebraic treatment.
2. It ignores the negative deviation and treats them as positive which is not justified
mathematically.
3. It is not a satisfactory measure, when deviations are taken from the mode.
4. It is rarely used in social sciences.
5. It is not suitable when the class intervals are open end.
STANDARD DEVIATION AND CO-EFFICIENT OF VARIATION.

STANDARD DEVIATION (σ):


It is defined as the positive square root of the arithmetic mean of the squares of the
deviation of the given observation from their arithmetic mean.

CALCULATION OF STANDARD DEVIATION FROM SHORT CUT METHOD


1. Individual observation.

σ ∑d2 /𝑛 – (∑𝑑/𝑛)2 where d= X-A

2. Discrete and continuous series.

σ= ∑fd2 /𝑛– (∑𝑓𝑑/𝑛)2 . where d= X-A

C.V = (𝜎/𝑋 × 100 )

CALCULATION OF STANDARD DEVIATION FROM DIRECT METHOD


1. Individual observation
σ = ∑d2 /n ; where d= X- 𝑿

Coefficient of Variation σ/x *100


2. Discrete and continuous series.

33
σ = ∑fd2 /n where d= X- 𝑿

Coefficient of Variation σ/x *100


Problem:
Calculate S.D for the following deviation and also find co-efficient of variation.

Tests: 0 1 2 3 4

Marks: 17 9 6 5 3

X f Fx A=2 d2 fd fd2
d =X-A
0 17 0 -2 4
-34 68
1 9 9 -1 1
-9 9
2 6 12 0 0
0 0
3 5 15 1 1
1 5
4 3 12 2 4
6 12
40 ∑𝑓𝑑 =- ∑fd2 =94
32
σ= ∑fd2 /𝑛– (∑𝑓𝑑/𝑛)2

σ= 94/40– (−32/40)2

= 1.71

= 1.30

S.D = 𝒗𝒂𝒓𝒊𝒂𝒏𝒄𝒆.

Problem:
The numbers of employees, wages per employees for two factories are given below.

In which factory there is greater variance in the distribution of wages per employee and
which factory pays more wages.

Factory X Factory Y
No of employees 50 100
Average wages 60 42
per employee per
month
Variance wages 16 64
per employee
per month.

34
FACTORY X FACTORY Y
n = 50 n = 100
𝑋 =60 𝑋 =42
Variance = 16 Variance = 64
S.D= 𝒗𝒂𝒓𝒊𝒂𝒏𝒄𝒆. S.D = 𝒗𝒂𝒓𝒊𝒂𝒏𝒄𝒆.
= 𝟏𝟔 = 𝟔𝟒
= 4 = 8
To find total number of To find total number of
employees employees
∑𝑓𝑥= n ×𝑋 ∑𝑓𝑥= n ×𝑋
= 50×60 = 100×42
= 3000 = 4200
𝜎 𝜎
C.V = 𝑋 × 100 C.V = 𝑋 × 100
= (4/60 × 100 ) = 8/6(42 × 100 )
= 6.66 = 19.04

Conclusion:

Factory „y‟ pays more wages than Factory „X‟.

C.V of „X‟ is < C.V of „Y‟.

Therefore‟ variation of distribution of wages is more in Factory „Y‟.

Question: Find which of the Batsman is more consistent in scoring. Would you also
accept him as a better run getter? Why?

Batsman

A: 5 7 16 27 39 53 56 61 80 101 105

B: 0 4 16 21 41 43 57 78 83 90 95

35
Solution:

x-𝒙 𝒅𝟐 y y-𝒚 𝒅2
x Batsman A (d) Batsman B(d)

5 -45 2025 0 -48 2304


17 -43 1849 4 -44 1726
16 -34 1156 16 -32 1024
27 -23 529 21 -27 729
39 -11 121 41 -7 49
53 +3 9 43 -5 25
56 +6 36 57 9 81
61 11 121 78 30 900
80 30 900 83 35 1225
101 51 2601 90 42 1764
105 55 3025 98 47 2209
550 12372 528 12,246
𝑥=50 ∑d2 𝑦=48 ∑d𝑥 2

σd = ∑d2 /n =√12372/11 = 33.536752 σ b = ∑d2 /n =√12246/11 =33.365741

C.V = (𝜎/𝑋 × 100 ) C.V = (𝜎/𝑋 × 100 )

= 33.5368/50*100 =33.3657/48*100

= 67.0736% = 69.5119 %

i. Batsman „A „is more consistent.


ii. Of course yes „A‟ is a better run getter also as his average is more

Merits of Standard Deviation:

1. It is based on all the observations given.


2. It can be smoothly handled algebraically.
3. It is well defined and definite measure of dispersion.
4. It is great importance, when we are making comparison between variability of two
series.

Demerits of Standard Deviation:

1. It is difficult to calculate and understand.


2. It gives more weight to extreme values as the deviations are squared.
3. It is not useful in economic studies.

36
4. CORRELATION AND REGRESSION ANALYSIS

Correlation

“Correlation” means a possible connection or relationship or inter-dependence between the


values of two or more variables of the same phenomenon or individual series. It indicates the
strength of the relationship.

Regression

“Regression” means returning or stepping back to the average value. With the help of values
of one variable (independent) we can establish most likely values of other variable (dependent).
On the basis of two available correlated variables, we can forecast the future data or events or
values.

In statistics the term “Regression” means simply the “Average Relationship”. We can predict
or estimate the values of dependent variable from the given related values of independent
variable with the help of a Regression Technique.

Regression Analysis

“Regression Analysis” refers to the methods by which estimates are made about the values of
a dependent variable from the values of an independent variable. It is a technique of predicting
the unknown values on the basis of the “average relationship”.

Distinction Between Correlation and Regression

Correlation Regression

1. It precedes regression. 1. It succeeds correlation.

2. It tests the closeness between the 2. It studies the closeness between


two variables. the two variables and estimates
the values.

3. It measures the degree of 3. It measures the nature of


covariation. covariation.

37
4. It is merely a tool of ascertaining 4. It is also a tool of studying cause
the degree of relationship. and effect of relationship.

5. The relationship may be purely a 5. There is a perfect relationship


chance and it may not have and it has practical relevance.
practical relevance.

6. There is no question of 6. There is an indentification of


independent and dependent independent and dependent
variables. variables.

7. It is a two-way average of 7. It is a directional relationship


relationship. with cause and effect.

8. It establishes just a relationship. 8. It studies the functional


relationship with the two
equations of lines.

Types of Correlation
Correlation is classified, on the basis of its nature, into the following ways:

If the values of the two variables deviate in the same direction, correlation is said to be „positive‟
or „direct‟. It means, the increase in the values of one variable results, on an average, in a
corresponding increase in the values of other variable and vice versa.
If the values of the two variables deviate in the opposite direction, correlation is said to be
„negative‟ or „indirect‟. It means, the increase in the values of one variable results, on an average,
in a corresponding decrease in the values of other variable and vice versa.
When one variable is independent and the other variable is dependent on the former, it is the case
of a „partial correlation‟.
When only two variables are studied, it is called a „simple correlation‟. It means the study
involves only two variables, which are changing either in the same or opposite direction.

38
Probable Error
“Probable Error” is a difference resulting due to taking samples from the mass of population.

𝟏−𝒓𝟐
P.E. = Probable factor × Standard error = 0.6745
𝒏

Karl Pearsons Coefficient of Correlation

𝐝′ 𝐱 (𝐝′ 𝐲)
𝐝′ 𝐱𝐝′ 𝐲 −
𝐫= 𝐧
(𝐝′𝐱)𝟐 𝟐
𝐝′ 𝐱 𝟐 − 𝐝 ′ 𝐲 𝟐 − (𝐝′𝐲)
𝐧 𝐧
1. Following are the results of B.Com. Examination in a college. Compute coefficient of correlation
between age and success in the examination and interpret the result.
Age of Candidates: 20-21 21-22 22-23 23-24 24-25 25-26
Candidates Appeared: 120 100 70 40 10 5
Successful Candidates: 72 55 35 18 4 1
Solution: Let us obtain the Mid-value of age group and convert the successful candidates into
percentages.

Age M.V. (x-23.5) d‟x2 % of Passing (y-50)


(C.I) x d‟x d‟y d‟y2 d‟xd‟y

20-21 20.5 -3 9 60 +10 100 -300

21-22 21.5 -2 4 55 +5 25 -50

22-23 22.5 -1 1 50 0 0 0

23-24 23.5 0 0 45 -5 25 0

24-25 24.5 +1 1 40 -10 100 100

25-26 25.5 +2 4 20 -30 900 1800

d‟x=-3 d‟x2=19 d‟y=-30 d‟y2=1150


d‟xd‟y=1550

We are taking assumed means. So a short-cut formula is used.

39
𝐝′ 𝐱 (𝐝′ 𝐲)
𝐝′ 𝐱𝐝′ 𝐲 −
𝐫= 𝐧
(𝐝′𝐱) 𝟐 𝟐
𝐝′ 𝐱 𝟐 − 𝐝 ′ 𝐲 𝟐 − (𝐝′𝐲)
𝐧 𝐧

−𝟑 −𝟔
−𝟐𝟐 −
= 𝟔
−𝟑 𝟐 −𝟔 𝟐
𝟏𝟗 − 𝟒𝟔 −
𝟔 𝟔

−𝟐𝟓 −𝟐. 𝟓
= =
𝟒. 𝟏𝟖𝟑𝟑 × 𝟔. 𝟑𝟐𝟒𝟓 𝟐𝟔. 𝟒𝟓𝟕

r= -0.94492

1. Find the coefficient of correlation between the following two variables.


Comment on the results through the probable error.

X: 06 08 12 15 18 20 24 28 31

Y: 10 12 15 15 18 25 22 26 28

Sol:

X Y (x-18) dx dx2 (y-19) dy dy2 dxdy

06 10 -12 144 -9 81 +108

08 12 -10 100 -7 49 +70

12 15 -6 36 -4 16 +24

15 15 -3 09 -4 16 +12

18 18 0 00 -1 01 00

20 25 +2 04 +6 36 +12

24 22 +6 36 +3 09 +18

28 26 +10 100 +7 49 +70

31 28 +13 169 +9 81 +117

∑x=162 ∑y=171 ∑dx2=598 ∑dy2=338 ∑dxdy=431

40
𝐝𝐱𝐝𝐲
𝐫=
𝐝𝐱 𝟐 𝐝𝐲 𝟐

𝟒𝟑𝟏
𝐫=
𝟓𝟗𝟖 𝟑𝟑𝟖
𝟒𝟑𝟏
𝐫=
(𝟐𝟒. 𝟒𝟓) (𝟏𝟖. 𝟑𝟖)

𝟒𝟑𝟏
𝐫=
𝟒𝟒𝟗. 𝟑𝟗
R= 0.959

2. Calculate the rank correlation coefficient for the following data:


X: 60 34 40 50 45 41 22 43 42 66 64 46
Y: 75 32 35 40 45 33 12 30 36 72 41 57
Solution: Values are given Ranks are to be assigned

X y Rx Ry d d2

60 75 3 1 +2 4

34 32 11 10 +1 1

40 35 10 8 +2 4

50 40 4 6 -2 4

45 45 6 4 +2 4

41 33 9 9 0 0

22 12 12 12 0 0

43 30 7 11 -4 16

42 36 8 7 +1 1

66 72 1 2 -1 1

64 41 2 5 -3 9

46 57 5 3 +2 4

d=0 d2=48

41
6d 2
rs = 1-
n 3 −n

6×48
= 1-
12 3 −1

6×48
= 1-
123 −12

288
= 1-
1716

= 1 - 0.16783

rs = +0.83217

2. Find the correlation for following data.


X: 60 15 20 28 12 40 80 20
Y: 10 40 30 50 30 20 60 30

X Rx Y Ry d= Rx-Ry d2

60 2 10 8 -6 36
15 7 40 3 4 16
20 5.5 30 5 0.5 0.25
28 4 50 2 2 4
12 8 30 5 3 9
40 3 20 7 -4 16
80 1 60 1 0 0
20 5.5 30 5 0.5 0.25
d2 = 81.5

In ‘X’ series 5th and 6th ranks are tied(2 ranks equal m=2)
So 5+6/2 = 5.5
In ‘Y’ series 4th, 5th and 6th ranks are tied(3 ranks equal m=3)
So 4+5+6/2 = 5
1 1
𝟔[d 2 + m 3 −m + m 3 −m ]
rs = 𝟏 − 12 12
where m= no. of ranks equal
n 3 −n
1 1
𝟔[81.5+ 23 −2 + 33 −3 ]
rs = 𝟏 − 12
83 −8
12

42
1 1
𝟔[𝟖𝟏.𝟓+ 6 + 24 ]
rs = 𝟏 − 12 12
504

1
𝟔[81.5+ +2]
rs = 𝟏 − 2
504

𝟔[81.5+2.5]
rs = 𝟏 − 504
𝟓𝟎𝟒
rs = 𝟏 − 504
rs = 𝟎

3. The following data relate to the ages of husbands and wives:


Ages of Husbands: 25 28 30 32 35 36 38 39 42 55
Ages of Wives: 20 26 29 30 25 18 26 35 35 46
Obtain the two regression equations and determine likely age of husband for the age of wife
25 years.
Solution:
Husband‟s Wives (X-X) (Y-y ) x2 y2
xy
Ages(X) Age(Y) x y
25 20 -11 -9 121 81
99

28 26 -8 -3 64 9
24

30 29 -6 0 36 0
0

32 30 -4 +1 16 1
-4

35 25 -1 -4 1 16
+4

36 18 0 -11 0 121
0

38 26 2 -3 4 9
-6

39 35 3 +6 9 36
+18

42 35 6 +6 36 36
+36

55 46 19 +17 361 289


+323

x=360 y=290 x=0 y=0 x2=648 y2=598 xy=494

43
∑𝑥 360 ∑𝑦 290
𝑋= = = 36 𝑌= = = 29
𝑛 10 𝑛 10

y on x x on y

∑ 𝑥𝑦 ∑ 𝑥𝑦
𝑌−𝑌 =∑ 𝑋−𝑋 𝑋−𝑋 =∑ 𝑌−𝑌
𝑥2 𝑥2
494 494
(Y−29) = (X−36) (X−36) = (Y−29)
648 598
(Y−29) = 0.7624 (X−36) (Y−36) = 0.8261 (Y−29)
Y= 0.7624X−27.4464+29 X= 0.8261Y−23.9569+36
Y= 0.7624X +1.5536 X= 0.8261Y+12.0431

If a wife’s age is 25, =32.7 years = 32 years


X=0.8261(25)+12.0431 8 months 12 days
X=20.6525+12.0431
X=32.6956

4. You are given below the information about advertising and sales of a company:
Advertising expenses(x) Sales(y)
(Rs in lakhs) (Rs in lakhs)
Mean 10 90
Variance 9 144
Correlation Coefficient 0.8
a) Calculate the two regression lines.
b) Find the likely sales when advertising expenses are Rs 15 and Rs 20.
c) What should be the advertising expenses when the company wants to attain a sales target of Rs 140 lakhs
and Rs 190 lakhs.

Solution:
a) Calculation of Two Regression Lines
𝜎𝑥 = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 9 = 3, 𝜎𝑦 = 𝑣𝑎𝑟𝑖𝑎𝑛𝑐𝑒 = 144 = 12
Y on x x on y
y=bx x=by
𝑌 − 𝑌 = 𝑏𝑦𝑥 𝑋 − 𝑋 𝑋 − 𝑋 = 𝑏𝑥𝑦 𝑌 − 𝑌
𝜎𝑦 𝜎𝑥
𝑌 − 90 = 𝑟 𝑋 − 10 𝑋 − 10 = 𝑟 𝑌 − 90
𝜎𝑥 𝜎𝑦
12 3
𝑌 − 90 = 0.8 𝑋 − 10 𝑋 − 10 = 0.8 𝑌 − 90
3 12

44
Y – 90 = 3.2 (X − 10) X – 10 = 0.2 (Y − 90)
Y −90 = 3.2X −32 X −10 = 0.2Y −18
Y=3.2X −32+90 X=0.2Y −18+10

Y=3.2X+58 X=0.2Y−8

b) If Advertising expenses are, If expected sales are,


Rs 15 lakhs, sales would be Rs 140, Advt.exp. would be
Y=3.2(15)+58=48+58 x=0.2(140)-8=28-8
Sales=Rs 106 lakhs Advt.exp.=Rs 20 lakhs
Rs 20 lakhs, sales would be, Rs 190, Advt.exp would be
y=3.2(20)+58 x=0.2(190)-8
y=64+58 x=38-8
Sales= Rs 122 lakhs Advt.exp. Rs 30 lakhs.

45
5: INDEX NUMBER
According to A.M Tuttle „Index number‟ is a single ratio which measures the
combine change of several variables between two different times, places, (or) situations.
It can also be defined as a quantity which by reference to a base period shows variations or
changes in the magnitude over a period of time.
Purpose:
i. To measure and compare changes in a variable or set of variables with
some base year.
ii. To measure purchasing power of money which help in finding out real
wages of people
iii. To provide guidelines to policymaking in business field.
Importance:
Index numbers are economic barometers as they indicate the pulses of economy and
tendencies in price fluctuations .They also measure the pressure of economic activities of the
country.
Base year:
Base year is a year with which index number are to be compared (or) to which they have to
be refered. It should be a period which is having normal (or) stable economic activities.
Current year
It refers to the year for which comparison is done.
METHODS OF CONSTRUCTING INDEX NUMBER.

INDEX NUMBER

UNWEIGHTED WEIGHTED
(PRICE AND
(PRICE) QUALITY)

SIMPLE AVERAGE SIMPLE AVERAGE


AGGREGATIVE OF PRICE AGGREGATIVE OF PRICE
METHOD RELATIVE METHOD RELATIVE
METHOD METHOD

NOTATIONS:
𝑃0 = Base year prices.

46
𝑃1 = Current year prices.

𝑞0 = Base year quantity.

𝑞1 = current year quantity.

𝑃01 = Price index number for current year with reference to the base year.

𝑞01 = Quantity index number for the current year with reference to the base year.

𝑉01 = Value index number for the current year with reference to the base year.

SIMPLE AGGREGATIVE METHOD:

𝑃01 = ∑𝑝 1
∑𝑝 0
×100

Where;

∑𝑝1 = Total of current year prices.


∑𝑝0 = Total of base year prices.
𝑃01 = Price index number.
Problem:
Calculate price index number by Simple aggregative method.

Items A B C D E
Price in 6 10 2 12 5
2001(𝑝0 )
Price in 8 15 4 8 5
2003(𝑝1 )
Solution:

Items 𝑝0 (2001) 𝑝1 (2003)


A 6 8
B 10 15
C 2 4
D 12 8
E 5 5
∑𝑝0 = 35 ∑𝑝1 = 40
∑𝑝
𝑃01 = ∑𝑝1 ×100
0

40
= 35 ×100

= 114.28.

47
Conclusion:

This means during the year 2003 the prices have rise up by 14.28% on an average
compared to the prices in the year 2001.

Average of price relative:


∑𝐼
𝑃01 = 𝑛 .

Where;
𝑝
I = 𝑝1 ×100
0

I= Price relative.
n = number of commodities.
Problem:
Calculate index number by average of price relatives method.

Items A B C D E
Price in 6 10 2 12 5
2001(𝑝0 )
Price in 8 15 4 8 5
2003(𝑝1 )
Solution:

Items 𝑝0 (2001) 𝑝1 (2003) 𝑝


I = 𝑝1 ×100
0

A 6 8 133.3
B 10 15 150
C 2 4 200
D 12 8 66.67
E 5 5 100
∑𝐼= 650

𝑃01 = ∑𝐼
𝑛
n=5

= 650/5= 130

48
WEIGHTED INDEX NUMBER:
1. Laspeyre‟s method:
In this method the base year quantity are taken as weights.
∑𝑝 𝑞
𝑃01 = ∑𝑝1 𝑞0 × 100
0 0

2 Paasche‟s method:

In this method current years quantities are taken as weights.

𝑃01 =∑𝑝 1 𝑞 1 × 100


∑𝑝 𝑞0 1

3 Marshall- Edge worth :


In this method the arithmetic mean of the quantities of base year and current year
quantities are taken as weights.

𝑃01 =∑𝑝 1 𝑞 0 +∑𝑝 1 𝑞 1


∑𝑝 0 𝑞 0 +∑𝑝 0 𝑞 1
× 100

4 Fisher‟s method:

𝑃01 = 𝐿𝑎𝑠𝑝𝑒𝑦𝑟𝑒′𝑠 × 𝑃𝑎𝑎𝑠𝑐ℎ𝑒′𝑠

∑𝑝 1 𝑞 0 ∑𝑝 1 𝑞 1
𝑃01 = ∑𝑝 0 𝑞 0
× ×100
∑𝑝 0 𝑞 1

Time reversal test:


The formula should work both ways, base year to current year and current year to base
year, resulting into the same ratio.

∑𝑝1 𝑞0 ∑𝑝1 𝑞1
𝑃01 = ∑𝑝0 𝑞0
× ∑𝑝0 𝑞1

∑𝑝0 𝑞1 ∑𝑝0 𝑞0
𝑃01 = ∑𝑝1 𝑞1
× ∑𝑝1 𝑞0

𝑃01 × 𝑃01 = 1.

49
Factor reversal test:

The formula should true value ratio, if the price index number multiplied by quantity index
number.

∑𝑝1 𝑞0 ∑𝑝 𝑞
𝑃01 = ∑𝑝0 𝑞0
× ∑𝑝1𝑞1
0 1

∑𝑞 1 𝑝 0 ∑𝑞 1 𝑝 1
𝑄01 = ∑𝑞 0 𝑝 0
×
∑𝑞 0 𝑝 1

∑𝑝 1 𝑞 1
𝑉01 =
∑𝑝 0 𝑞 0

𝑃01 × 𝑄01 = 𝑉01


Problem:
Construct the Laspeyre‟s, Paasche‟s, Marshall- Edge worth and Index number for the
following data and prove that it satisfies both TRT and FRT.

Commodities Base Base year Current Current


year Quantity year year
price price Quantity
A 10 80 12 90
B 14 90 16 80
C 15 100 3 110
D 18 80 17 100

Solution:

Comm 𝑝0 𝑞0 𝑝1 𝑞1 𝑝1 𝑞0 𝑝0 𝑞0 𝑝1 𝑞1 𝑝0 𝑞1
odities
A 10 80 12 90 960 800 1080 900
B 14 90 16 80 1440 1260 1280 1120
C 15 100 3 110 1300 1500 1500 1650
D 18 80 17 100 1360 1440 1440 1800
5060 5000 5490 5470

50
1.Fisher‟s method:
∑𝑝1 𝑞0 ∑𝑝 𝑞
𝑃01 = ∑𝑝0 𝑞0
× ∑𝑝1𝑞1×100
0 1

5060 5490
𝑃01 = × 5470 × 100
5000

= 100.78
2.Laspeyre‟s method:
∑𝑝 𝑞
𝑃01 = ∑𝑝 1 𝑞 0 × 100
0 0
5060
= ×100
5000

= 101.2
3. Paasche‟s method

𝑃01 = ∑𝑝 1 𝑞 1 × 100
∑𝑝 𝑞
0 1
5490
×100
5470

= 100.36
4. Marshall- Edge worth :

𝑃01 =∑𝑝 1 𝑞 0 +∑𝑝 1 𝑞 1 × 100


∑𝑝 0 𝑞 0 +∑𝑝 0 𝑞 1

=5060 +5490
5000 +5470
× 100
=1.0076
5.Time reversal test:
𝑃01 × 𝑃01 = 1.
∑𝑝 1 𝑞 0 ∑𝑝 𝑞 ∑𝑝 0 𝑞 1 ∑𝑝 𝑞
∑𝑝 0 𝑞 0
× ∑𝑝1 𝑞 1 × ∑𝑝 1 𝑞 1
× ∑𝑝0 𝑞 0
0 1 1 0

5060 5490 5470 5000


5000
× 5470 × 5490
× 5060

5060
5000
× 5490
5470
× 5470
5490
× 5000
5060
= 1

51
6.Factor reversal test:

𝑃01 × 𝑄01 = 𝑉01

∑𝑝 1 𝑞 0
∑𝑝 0 𝑞 0
× ∑𝑝 1𝑞1
∑𝑝 0 𝑞 1
× ∑𝑞 1 𝑝 0
∑𝑞 0 𝑝 0
× ∑𝑞 1𝑝 1
∑𝑞 0 𝑝 1

5060 5490 5470 5490


5000
× 5470 × 5000
× 5060

5060 5490 5470 5490


5000
× 5470 × 5000 × 5060

∑𝑝 1 𝑞 1
= 5490/5000 = = 𝑉01
∑𝑝 0 𝑞 0

Consumer Price Index Number:


It is designed to study the effect of changes in price on the working class families or
consumers.

Methods of computation:

∑𝑝 1 𝑞 0
Aggregate Expenditure Method….𝑃01 = × 100
∑𝑝 0 𝑞 0
∑IW
Family Budget Method………….. 𝑃01 = ∑W
× 100

Uses of Consumer Price Index Number:


 They are useful in wage negotiations and settlements.
 They are helpful to the government in forming wage policy, income policy, price
policy, rent control etc.
 They are used for measuring the purchasing power of money and real wages or
income.
 Used in analyzing the markets for particular type of goods and services.

Question: A textile worker earns Rs. 350 per month . The cost of living indeex
for that particular month is known as 136. Using the following data finid the
amounts spend by him on house rent and clothing.

Group Food Clothing Rent Fuel Miscellanous


Expenditure 140 ? ? 56 63
Group Index 180 150 100 110 80

52
Solution: Assume the amounts spend on clothing and house rent as A & B
respectively. The total wages spent will also be assumed as his earnings. Thus we can
have following equations:
140+A+B+56+63=350
A+B=91…………………………………………… (i)
Computation of cost of living Index

Group Expenditure(W) I IW
Food 140 180 25,200
Clothing A 150 (150A)
House rent B 100 (100B)
Fuel 56 110 6160
Miscellaneous 63 80 5040
∑W=350 ∑IW=36400+150A+100B

∑𝐈𝐖
C.L.I= ∑𝐖
× 100

136=36400+150A+100B/350
150A+100B=11,200………………………….. (ii)
Solving (i) & (ii) we get the value of A & B AS

A=42 & B=49 ; so the worker has spent Rs 42 on clothing and Rs 49 on House rent

53
6. TIME SERIES
Time series is a series of numerical data which have been recorded at different
intervals of time. It is a record of changes in variables over a period of time.

COMPONENTS OF TIME SERIES:

1) SECULAR TREND/ LONG TERM MOVEMENT:


The values of variables tend to increase or decrease over a period of 8-10
years. Though there are upward and downward changes in the trend, we find
in general only one trend over a period of time.
2) SEASONAL VARIATION:
The values of variables change in a regular, periodic, and rhythmic order
according to season covering a period of time not exceeding 12 months.
Ex: Weather conditions, climatic changes, rainfalls and sunlight.
3) CYCLIC VARIATION:
The values of variables change in a rhythmic pattern over a period of time
from 2 to 6 years extending even up to8 years. There are oscillatory
movements in the economic activities, which are complex, less regular and
less uniform. They are the outcomes of the business cycles.
Boom period, Recession, Depression and recovery and again Boom period.
4) RANDOM FLUCTUATIONS:
The values of variables change suddenly or unexpectedly. The influencing
factors are unpredictable. They are generally mixed up with the seasonal and
cyclic fluctuations.
Ex: Earthquakes, floods, storms.

The two methods of measuring trend values.


1) Moving average method.
2) Least square method.

MOVING AVERAGE METHOD


1) Using the 3 yearly moving average determine the trend value and plot the
graph for the actual and trend values.
Year: 1995 1996 1997 1998 1999 2000 2001 2002
Production: 21 22 23 24 25 26 27 26
Year production 3 year 3 year year
moving moving
total average
1995 21 - - -
1996 22 66 66/3=22 1996
1997 23 69 69/3=23 1997
1998 24 72 72/3=26 1998
1999 25 75 75/3=25 1999
2000 26 78 78/3=26 2000
2001 27 79 79/3=26.33 2001
2002 26 - - -

54
2. Using the 4 yearly moving average determine the trend value and plot the graph for the
actual and trend values.

Year: 1994 1995 1996 1997 1998 1999 2000

Production: 75 62 76 78 94 84 96

Year Production 4 year Centered Year


4 year moving moving
total average

1994 75

62

1995 76
291 291/4=72.75
78
1996 75.125 96
94
310 310/4=77.5
1997 84 80.25 97

96 332 332/4=83
1998 85.5 98
352 352/4=88
1999

2000

55
2) Using 5 yearly moving average determine the trend values and plot the graph.

Year: 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996

Sales: 12 14 18 24 22 20 16 25 26 34

31

Year Sales 5 year 5 year Year


moving moving
total average
1986 12 - - -
1987 14 - - -
1988 18 90 90/5=18 1988
1989 24 98 98/5=19.6 1989
1990 22 100 100/5=20 1990
1991 20 107 107/5=21.4 1991
1992 16 109 109/5=21.8 1992
1993 25 121 121/5=24.2 1993
1994 26 132 132/5=26.4 1994
1995 34 - - -
1996 31 - - -

Least square method:

a =∑y/n

b = ∑xy/∑𝒙𝟐

𝒀𝒄=𝒂+𝒃𝒙

1) Calculate the trend value by applying least square method.

Year: 1996 1997 1998 1999 2000 2001 2002

Sales: 20 23 22 25 26 29 30

Year Sales x 𝑥2 xy 𝑌𝑐=𝑎+𝑏𝑥

1996 20 -3 9 -60 20.08


1997 23 -2 4 -46 21.72
1998 22 -1 1 -22 23.36
1999 25 0 0 0 25
2000 26 1 1 26 26.64
2001 29 2 4 58 28.28
2002 30 3 9 90 29.92

56
a =∑y/n b = ∑xy/∑𝒙𝟐 𝒀𝒄=𝒂+𝒃𝒙

= 175/7 = 46/28 = = 25+1.64(7)


1.642
=25 =36.48

Reference Book:
 Quantitative Analysis for Business Decision by C.M Chikkodi & B.G Satyaprasad

57
PREVIOUS YEAR QUESTION PAPERS:-

58
59
60
61
62
63
64