BUSINESS STATISTICS NOTES

Commerce and Professionals Institute

(CPI)
CPI Classes By:
1. CA.SAYED NEFAQUE (CA. SAN SIR)
2. CA. MUKESH SIR
Chartered Accountants
SPECIAL CLASSES FOR:
+2 COMMERCE, +3 COMMERCE, M. Com, MBA, CA, CS &
CMA.
Branch 1: Near SB Women’s college, Mission Road,
Cuttack
Branch 2: Jagannathpur, College Road, Bhadrak
Contact No.7978066272, 7735302028, 9439855332
Focus on Conceptual Clarity
Well Experienced faculty
Periodic testing for tracking improvement
Small size batch
Question set practice
VST and Motivation Class.
 UNIT: 1- INTRODUCTION
STATISTICS MEANING:
The term ‘Statistics’ is conveyed to two different things, in the plural use, statistics means some
systematic collection of numerical data about some particular topic.
In the singular use, it means the science of statistics. In the general practice, statistics is used to mean
the science of statistics and data or statistical data used for the numerical variables.
DEFINITION
According to A.I. Bowley, ‘‘Statistics are numerical statement of facts in any department of enquiry placed
in relation to each other’’.
CHARACTERISTICS OF STATISTICS
➢ Aggregate of facts:
Statistical enquiry is to get information from a mass of observation with regards to the group behavior
of individual items. For example, the aggregate of figures related to production, sale and profit over
different times is called statistics.
➢ Numerically expressed:
Numerical expression of the observed fact in terms of quantitative standards of particular scores could
be regarded as statistics.
➢ Estimated:
The numerical data pertaining by field of enquiry can be observed either by enumerating or by
estimation. Enumeration is used for sell field of enquiry while estimation is used for wide and large
field of enquiry.
➢ Standard of Accuracy:
In case of enumeration and estimation, it is essential to fix the desired standard of accuracy
beforehand.
➢ Predetermined purpose:
The purpose of enquiry is specifically stated, and then the data should be collected in a systematic
manner through some suitable plan, so as to make the figures free from bias and errors.
➢ Comparability:
The ultimate aim of statistical data is, for the purpose of the comparative or relative study. Therefore,
it is homogeneous to make valid comparison
OBJECTIVE OF STATISTICS
➢ To improve the unknown and to cast light upon the statistics out of facts and figures
➢ To enable comparison to be make between past and present
➢ To throw light on the reasons of changes, effects of changes and plans for future
➢ To help to drawing conclusion from facts effected by a multiplicity of causes
➢ To handle analyze and draw valid inferences.
IMPORTANCE OF STATISTICS
➢ In States:;
Statistics was regarded as the “Science of Kings”. It supplies the essential information to run the
government, Policies are adopted by the government with the help of statistics.
➢ In economics:
In economics, the problems are studied by the use of statistical methods economic loss is based on the
study of collected statistical data. The loss economics refer to statistics to prove their accuracy.
Statistics in economics as given birth to a new discipline called econometrics.
➢ In Business:
In the competitive business, the business people face some like shortage is overstocking, uneconomic
crisis etc., which can be solved through statistical analysis. To a greater extent statistics help the
businessman maximize their profit.
➢ In Education:
Statistics is widely used in education for research purpose. It is used to test the past knowledge and
evolved new knowledge.
➢ In Astronomy:
Astronauts study the eclipse and astronocal issues by applying statistics. They rely on estimation in
many cases and it was corrected with the help of statistics.
➢ In accounting:
In accounting correlation analysis between profit and sales is widely used. In auditing, Sampling
techniques are commonly followed.
➢ In Banking:
In this past developing technology, the banking sector needs a lot of information about the present
and future business development.
➢ In Investment Decision:
Statistics helps an investors in selecting securities, which are safe, yielding a good return an
appreciation in the market price
➢ In Insurance:
Statistics is extensively used in the field of Insurance. Actuarial statistics is must of the insurance
company through fix the premium relates which is based on the mortality tables.
FUNCTIONS OF STATISTICS
• It prevents facts in a definite numerical form
• It simplifies the complexity of the data
• It provides a technique of comparison
• It helps in formulation and testing hypothesis
• It helps in forecasting of future trends and tendencies
• It studies relationship
• It helps the government
LIMITATION OF STATISTICS
• Statistics cannot be applied to individual term
• Statistical study qualitative phenomena in indirect form
• Statistical law are not exact
• Statistical results are uncertain
• Statistics is not simple
• Statistical data may be incomparable
• Statistics is liable to be misused
COLLECTION OF DATA
Data Collection means the assembling for the purpose of a particular investigation of entirely new data,
presumably nor available in published sources.
DATA
Data refer to the facts, figures or information collected for a specific purpose.
Types of Data
• Primary data
• Secondary data
METHODS OF COLLECTION OF PRIMARY DATA
Experiment Method:
Here the researcher examines the truth contained in his hypotheses by conducting experiments, through
which the date are collected.
Survey Method:
Under this method, data can be collected by any one or more of the following ways:
➢ Observation method: This method refers to the collection of information by way of investigator’s own
observation without interviewing the respondents.
➢ Interview Method: In the interview method, a lot of questions relation to the proposed study is
prepared and the answer for these questionnaire obtained from the respondents.
➢ Mailed Questionnaire method: Under this method, the questionnaire is sent to the respondents with a
covering letter to fill up the questionnaire and send back within a specified time.
➢ Through Schedules: Under this method, enumerators are appointed and trained .Who will take the
questionnaire to the respondents and fill the answer to the questions, obtained from the respondents.
SECONDARY DATA
Secondary data are not new and original in nature which are obtained from published and or unpublished
sources.
Sources of Secondary Data
➢ Published Sources
➢ Un published Sources
SAMPLING
Population or universe is a complete set of all possible observation of the type which is to be investigated.
Types of Population
➢ Finite Population
➢ Infinite population
➢ Hypothetical population
➢ Existent population
SAMPLE
A sample is the part of the population or universe selected for the purpose of investigation
ESSENTIAL OF SAMPLING
➢ Economy
➢ Less time consuming
➢ Reliability
➢ Detailed study
OBJECTIVES OF SAMPLES
➢ To make an inference about an unknown parameter from a measurable sample statics
➢ To test the hypothesis relating to populations
➢ To avoid the vase study about the entire population
➢ To obtain quick result
METHODS OF SAMPLING
Probability or Random Sampling:
The method is based on the theory of probability. Under this method, every item in the universe has a
known chance of being chosen
Classification of Probability sampling
Unrestricted (Or) Simple Random Sampling
➢ Lottery Method:
Lottery method of sampling refers to the process of drawing a lot among the population or universe.
Under this method, the required number of samples is selected from the total population by blind fold
form the drum or urn.
➢ Random Number Method:
This method is an alternative to lottery method under which samples are drawn by using the table of
random numbers
➢ Restricted Random Sampling:
As the size of population or universe is not restricted under unrestricted method of sampling, it
consumes much expenses and time
These samples are usually obtained by using the following methods such as:
➢ Stratified random Sampling:
Under this method random sampling, the population is divided into some groups or classes based on
their homogeneity. Samples are drawn from each stratum at random It is a method used for
increasing the precisions of sampling.
➢ Systematical Sampling:
Under this method the universe or population is arranged on the basis of some systems like
alphabetical,. Numerical, geographical etc.
➢ Cluster and Area Sampling:
A cluster may refer to anything, a school, a company, an industry or a society. Cluster sampling refers
to the procedure of dividing the [population into groups called clusters and samples drawn firm theses
clusters.
➢ Multi stage sampling:
Multi stage sampling is a type of sample design in which some information is collected from the whole
sample and additional information is also collected from sub-sample of the full sample.
➢ Sequential sampling:
Under this sequential sampling method, the size of the sample units is nor determined in advance,
but fixed according to mathematical division rules based on the survey.
NON PROBABILITY OR NON RANDOM SAMPLING:
This method is not based on theirs of probability in which the researcher cannot assume that every
elements has an equal chance of being chosen.
➢ Convenience sampling:
The method is also called chunk method. A chunk refers to the fraction of the population to be
investigated. This chunk is not selected by probability but by judgment or convenience.
➢ Purposive or Judgment sampling:
It is that method of sampling in which the samples are drawn on the basis of personal judgment of a
person. Generally the researcher uses his judgment in the choice of the samples which he thinks most
suitable for his study. While choosing the samples only the average items are selected and extreme
items are omitted Selection of the samples is adjusted in accordance with the object of the survey.
This method is suitable only when small number of samples is required
➢ Quota sampling:
It is one of the commonly used methods of sampling in markets surveys and opinion polls. Though it
is a non-random sampling it combines the technique of probability sampling and purposive selection.
This method is convenient and economical.
CLASSIFICATION OF TABULATION
Classification is the process of arranging the data under various understandable homogeneous groups for
the purpose of convenient interpretation. The grouping of data is make on the basis of common
characteristics.
CHARACTERISTICS OF CLASSIFICATION
➢ All facts can be arranged into homogeneous groups
➢ Classification may be according to their resemblances and affinities
➢ Classification may be made on either actuality or nationality
➢ Going expression to the unity of attributes
➢ It should be flexible to accommodate adjustment
OBJECTIVES OF CLASSIFICATION
➢ To facilitate comparison
➢ To study the relationship
➢ To trace location of important facts at a glance
➢ To eliminate unnecessary details
➢ To effect statistical treatment of the collected data
➢ To facilitate easy interpretation
TYPES OF CLASSIFICATION GEOGRAPHICAL CLASSIFICATION
In this type the data are classified on the basis of geographical locational differences among various items
on the basis of states districts, cities, regions, and the like
➢ Chronological Classification:
Under this type data are classified in them basis of differences in time or period such as rainfall for 12
months.
➢ Qualitative Classification:
In this classification, data are classified on the basis of some attributes or qualitative phenomena such
as religion, sex, marital status, literacy, occupation and the like.
➢ Quantitative Classification:
Under this type data are classified according to some quantitative phenomena capable of quantitative
measurement such as age, experience, income, prices, production, sales and the like
➢ Frequency Distribution:
Frequency distribution is the process or method in simplify mass of data into grouped form of classes
and the member of items in such class is recorded
• Univaraite Frequency Distribution
• Bivariate Frequency Distribution
Univariate Frequency distribution:
It is one way frequency single variable distribution and further classification into
➢ Individual Observation
➢ Discrete Frequency Distribution
➢ Continuous Frequency Distribution
Bivariate Frequency Distribution:
Bivariate Frequency Distribution is a two way Frequency distribution, where two variables are measured
in the same set of items through cross distribution
TERMS USED IN THE FREQUENCY DISTRIBUTION
➢ Class Limits:
The class limits are the lowest and the highest values but can be included in the class
➢ Class Frequency:
The number of items included or counted in each of the classes is called class Frequency
➢ Mid-point:
Mid-point in their value lying half way between the lower and upper limits of a class interval
METHODS OF CONSTRUCTING CLASS INTERVALS
➢ Exclusive method (or) Overlapping Class Limits:
Under this method, the upper limit of one class would be the lower limit of the next class inclusive
method under this method the upper limit of each class is not repeated as the lower limit of the next
class.
➢ Open End Class Interval:
We wish to include a person whose age is 72. The inclusion necessitates three additional classes. The
frequency of each of the first two classes would be and the third class 1. Insisted of adding three new
intervals to account be for once case an alternative would be to add the case with the last class
interval marked ’50 and above.
 A class which does not give the upper and lower limits, but unsteady is defined as more than or less
than the specified limit, is called as open class or open ended interval.
CUMULATIVE FREQUENCY DISTRIBUTION
Cumulative Frequency Distribution is obtained by recessively adding the frequencies of the values of the
variable or classes. They are
➢ Less than cumulative Frequency
➢ More than cumulative frequency
Steps to construct a frequency distribution
Step -1: in the first column write the value
Step-2: In the next column marks a vertical bar to denote the number of repetition of a particular value. If,
it is repeated fifth time cross the four bars. It is called Tally mark.
Step-3: do the same for all values
Step -4: now count then total number of frequencies will be help of tally marks
TABULATION
Tribulation is a systematic arrangement of raw data in a compact form of historical Rows and vertical
column.
 UNIT: 2-MEASURES OF CENTRAL TENDENCY
AVERAGE – MEANING
Average is a single value that represents group of values.
DEFINITION
An Average is a value which a typical or representative of a net of data.
CHARACTERISTICS OF A GOOD AVERAGE
➢ It should be defined clear and unambiguous so that it leads to one and only one interpretation by
different persons
➢ It should be easy to understand and simple to compute and should not involve heavy arithmetical
calculations
➢ It should be based on all the items of the given set of data is compute the average.
➢ It should be suitable for further algebras mathematical treatment and capable of being used is
further statistical computations.
DIFFERENT TYPES OF AVERAGE:
There are various types of averages which can be grouped under the three broad classes:
➢ Mathematical averages
➢ Positional averages
Mathematical averages:
Under this class of average come the following:
➢ Arithmetic average, or mean
➢ Geometric mean
➢ Harmonic mean
ARITHMETIC AVERAGE, OR MEAN
An arithmetic average may be defined as the quotient obtained by dividing the total of the Values of a
variable by the total number of their observations, or items. There are four different methods of
computing the arithmetic average of a series: These are:
Direct Method:
In case of Individual series In case of Discrete Series In case of Continuous Series
∑𝑋 ∑𝐹𝑋 ∑𝐹𝑚
x̅ = x̅ = x̅ =
𝑁 𝑁 𝑁
Short-cut Method:
In case of Individual series In case of Discrete Series In case of Continuous Series
∑𝑑 ∑𝑓𝑑 ∑𝑓𝑑
x̅ = A + x̅ = A + x̅ = A +
𝑁 𝑁 𝑁
Step deviation method:
In case of Individual series In case of Discrete Series In case of Continuous Series
∑𝑑′ ∑𝐹𝑑′ ∑𝐹𝑑′
x̅ = A + ∗𝑐 x̅ = A + ∗𝑐 x̅ = A + ∗𝑐
𝑁 𝑁 𝑁
Shortest method:
In case of Individual series In case of Discrete Series In case of Continuous Series
x̅ = 𝑋 − 𝑖(𝐹1 − 1) x̅ = 𝑋 − 𝑖(𝐹1 − 1) x̅ = 𝑀 − 𝑖(𝐹1 − 1)
MERITS OF ANTIEMETIC MEAN
➢ Easy to calculate and understand
➢ It is a perfect average, affect by the value of every item in the series
➢ It is calculated value and not based on position in the series
➢ It is determined by a rigid formula. Hence, everyone who computes the average gets the same
answer
➢ I t is used in further calculation
➢ It gives a good base for comparison
DEMERITS OF ARITHMETIC MEAN
➢ The mean is unduly affected by the extreme items
➢ It is unreliable It may lead to a false conclusion
➢ It is not useful for the study of qualities
➢ It cannot be located by the graphic method
MEDIAN
The number is that value of the variable which divides the group into two equal parts, one part comprising
all values greater and the other, all values less than median.
MERITS OF MEDIAN
➢ It is easy to compute and understand
➢ It eliminates the effect of extreme item
➢ The value of median can be located graphically
DEMERITS OF MEDIAN
➢ The calculating media, it is necessary to arrange the data other averages do not need an
arrangement
➢ It is affected more by fluctuation of samplingthan the arithmetic mean.
➢ It is not based on all the items of the series
MODE
Mode is the modal value in the value of the variable which occurs more number of times or most
frequently is a distribution. Mode is the value which occurs with the greatest number of frequency in a
series
TYPES OF MODAL
➢ Uni-modal:
If there is only one mode in series is called uni-modal.
➢ Bi-Modal:
If there are two modes in the series, it is called bi-model.
GEOMETRIC MEAN
MERITS OF GEOMETRIC MEAN
➢ Every item in the distribution is included in the calculation
➢ It can be calculated with mathematical exactness, provided that all the qualities are greater than
zero and positive
➢ Large items have less effect on it than in the arithmetic average.
➢ It is amenable to further algebraic manipulation
DEMERITS OF GEOMETRIC MEAN
➢ It is very difficult to calculate
➢ It is impossible to use it when any item is zero or negative
➢ The value of the geometric mean may not correspond with any actual value in the distribution
HARMONIC MEAN
Harmonic Mean is the reciprocal of the arithmetic average of the reciprocal of values of various item in
the invariable
Merits of Harmonic Mean
➢ It utilizes all values of a variable
➢ It is very important to small values
➢ It is amenable to further algebraic manipulation
➢ It provides consistent results in problems relating to time and rates than similar averages
Demerits of Harmonic Mean
➢ It is not very easy to understand
➢ The method of calculation is difficult
➢ The presence of both positive and negative items in a series makes it impossible to compute its
value. The same difficulty is felt if one or more items are zero
➢ It is only a summary figure and may not be the actual item in the series.
 UNIT: 3 -MEASURES OF DISPERSION AND VARIABILITY
DISPERSION
Dispersion is the study of scatterness around an average.
DEFINITION
Dispersion is the measures of the variation of the items ---A.L.Bowly
Dispersion is a measure of extent to which the individual items vary ---L.R.Connor
IMPORTANCE OF MEASURING VARIATION OR DISPERSION
➢ Testing the Reliability of the Measures of Central Tendency
➢ Comparing two or more series on the basis of their variability
➢ Enabling to control the variability
➢ Facilitating as a Basis for further statistical Analysis
CHARACTERISTICS OF A MEASURE OF VARIATION
➢ It is easy to understand and simple to calculate
➢ It should be rigidly defined
➢ It should be based on all observations and it should not be affected by extreme observations
➢ It should be amenable to further algebraic treatment
➢ It should have sampling stability
METHODS OF MEASURING DISPERSION
➢ Range
➢ Inter Quartile range
➢ Quartile Deviation
➢ Mean Deviation
➢ Standard Deviation
➢ Lorenz Curve
RANGE
Range is the difference between the largest and the smallest value in the distribution. It is the simplest
and crudest measure of dispersion
USES OF RANGE
➢ It is used in industries for the statistical quality control of the m infected product
➢ It is used to study the variations such as stock, shares and other commodities
➢ It facilitates the use of other statistical measures
ADVANTAGES OF RANGE
➢ It is the simplest method of studying variation
➢ It is easy to understand and the easiest to compute
➢ It takes minimum time to calculate
➢ It is accurate
DISADVANTAGES OF RANGE
➢ Range is completely depended on the two extreme values
➢ It is subject to fluctuations of considerable magnitude from sample to sample
➢ It is not suitable for mathematical treatment
➢ It cannot be applied to open and classes
➢ Range cannot tell us anything about the character of the distribution
QUARTILE DEVIATION
Quartile deviation is an absolute measure of dispersion. It is calculated on the basis of the difference of
upper quartile and the lower Quartile divided by 2. In the series, four quartiles are there. By eliminating
the lowest (25%) items and the highest (25%) items of a series, we can obtain a measure of dispersion
and can find out half the distance between the first and the third quartiles.
𝑸𝟑−𝑸𝟏
Quartile Deviation (Q.D) = 𝟐
𝑸𝟑−𝑸𝟏
Co-efficient of Q.D = 𝑸𝟑+𝑸𝟏
MERITS OF QUARTILE DEVIATION
➢ It is simple to calculate and easy to understand
➢ Risk of extreme item variance is eliminated, as it depend upon the central 50 per cent items
➢ It can be applied to open and classes
DEMERITS OF QUARTILE DEVIATION
➢ Items below Q1 and above Q3 are ignored
➢ It is not capable of further mathematical treatment
➢ It is affected much by the fluctuations of sampling
➢ It is not calculated from a computed average, but from a positional average.
MEAN DEVIATION
Mean deviation is the average difference between the items in a distribution computed from the mean,
median or mode of that series counting all such deviation as positive. The mean deviation is also known
as the average deviation.
∑|𝑫|
Mean deviation =
𝑵
MERITS OF MEAN DEVIATION
➢ It is clear and easy to understand
➢ It is based on each and every item of the data It can be calculated from any measure of central
tendency and as such as flexible too.
DEMERITS OF MEAN DEVIATION
➢ It is not suitable for further mathematical processing
➢ It is rarely used in sociological studies
➢ It is mathematically unsound and illogical, because the signs are ignored in the calculation of mean
deviation
STANDARD DEVIATION
Standard deviation is the square root of the means of the stranded deviation from the Arithmetic mean.
So, it is also known as Root Mean Square Deviation an Average of Second order. Standard deviation is
denoted by the small Greek letter ‘σ’ the concept of standard deviation is introduced by Karl Pearson in
1893.
USES OF STANDARD DEVIATION
➢ It is used in statistics because it possesses must of the characteristics of an ideal measure of
dispersion.
➢ It is widely used in sampling theory and by biologists.
➢ It is applied in co-efficient of correlation and in the study of symmetrical frequency distribution
ADVANTAGES OF STANDARD DEVIATION
➢ It is rigidly defined determinate
➢ It is based on all the observations of a series
➢ It is less affected by fluctuations of sampling and hence stable
➢ It is amenable to algebraic treatment and is less affected by fluctuations of sampling most other
measures of dispersion
➢ The standard deviation is more appropriate mathematically than the mean deviation, since the
negative signs are removed by squaring the deviations rather than by ignoring
CO EFFICIENT OF VARIANCE
Standard deviation is an absolute measure of dispersion. The corresponding relative measure is known as
the co=-efficient of variation. It is used to compare the variability of two or more series.
Co –efficient of Standard deviation
𝝈
=
𝐱̄
𝝈
Co-efficient of Variance (C.V) =
𝐱̄
X100
GRAPHIC METHOD OF DISPERSION
Lorenz Curve
Lorenz Curve is a device used to show the measurement of economic inequalities as in the distribution of
income and wealth. It can also be used in business to study the disparities of distribution of profit, wages,
turnover, production and the like.
SKEWNESS
The term ‘Skewness’ refers to lack of symmetry, that is, when a distribution is to symmetrical it is called a
skewed distribution. It the curve us normal or the data distributed symmetrically or uniformly. Spread will
be the same on both sides of the cent repoint and the means median and mode will all have the same
value.
DEFINITION
‘Skewness or symmetry is the attribute of a frequency distribution that extends further on one side of the
class with the highest frequency on the other--- Simpson and Kafka
SKEWNESS OF A DISTRIBUTION
When a distribution is not symmetrical it is called a skewed Distribution.
The analysis of presence of skewness in a distribution implies two main tasks. They are
➢ Determination of the sign of skewness and testing of skewness and
➢ Determination of the extent of skewness
SYMMETRICAL DISTRIBUTION
In a symmetrical distribution, the values of mean, median and mode are coinciding. The spread of the
frequencies is the same on both sides of the Centre point of the curve.

SKEWED DISTRIBUTION

A distribution which is not symmetrical is called a skewed distribution it is called skewed distribution. It
may be either positively Skewed or negatively skewed Distribution
➢ Positively Skewed Distribution:
In a frequency distribution positively skewed distribution the curve has longer tail to the rights and its
value of the mean is highest and the made is least. The median lies in between the two. That is X‾ ˃ M
˃Z
➢ Negatively Skewed Distribution:
In a frequency distribution if the curve has long tail to the left then it is negatively skewed distribution
in which value of mode is higher and mean is the least. The median lies in between the two. That is X‾
˂M˂Z
VARIOUS MEASURES OF SKEWNESS
Skewness can be measured absolutely or relatively. Absolutely measures are called measures of
skewness and relative measures are called the co-efficient of skewness.
ABSOLUTE MEASURES OF SKEWNESS
➢ The Karl Peason’s Coefficient of Skewness
➢ The Bowley’s Co efficient of Skewness
➢ The Kelly’s Coefficient of Skewness
➢ Measure of Skewness based on moments
KARL PEARSON’S CO-EFFICIENT OF SKEWNESS
This method is based upon the difference between mean and mode and the difference is divided by
standard deviation to give a relative measures.
BOWLEY’S COEFFICIENT OF SKEWNESS
Bowelys measure is based on quartiles, in a symmetrical distribution first and third quartiles are
equidistant from the median
OBJECTIVES OF SKEWNESS
➢ To find out the direction and extent of asymmetry in a series.
➢ To compare two or more series with regards to skewness.
➢ To study the nature of variation of the items about the central value.
 BUSINESS STATISTICS NOTES
Commerce and Professionals Institute
(CPI)
CPI Classes By:
1. CA.SAYED NEFAQUE (CA. SAN SIR)
2. CA. MUKESH SIR
Chartered Accountants
SPECIAL CLASSES FOR:
+2 COMMERCE, +3 COMMERCE, M. Com, MBA, CA, CS &
CMA.
Branch 1: Near SB Women’s college, Mission Road,
Cuttack
Branch 2: Jagannathpur, College Road, Bhadrak
Contact No.7978066272, 7735302028, 9439855332
Focus on Conceptual Clarity
Well Experienced faculty
Periodic testing for tracking improvement
Small size batch
Question set practice
VST and Motivation Class.
 UNIT - IV CORRELATION
CORRELATION ANALYSIS MEANING
Correlation is the study of the natural relationship between two or more variables. Hence, it should be
noted that the detection and analysis of correlation between two statistical variables requires relationship
of some sort which associates the observation in pairs each of which is a value of the two variables
DEFINITION
The relationship that exists between two variables ---Smith
Correlation analysis deals with the association between two or more variables. ---Tuite
USES OF CORRELATION
➢ Correlation is very useful in physical and social sciences. Business and economics
➢ Correlation analysis is very useful in economics to study the relationship between price and demand
➢ It is also useful in business to estimates costs, value, price and other related variables
➢ Correlation is the basis of the concept of regression
➢ Correlation analysis help in calculation the sampling once.
TYPES OF CORRELATION
Positive correlation

Negative Correlation

Simple Correlation
TYPES OF
Multiple Correlations
CORRELATION
Non –Linear
Correlation
Linear Correlation

Partial Correlation

➢ Positive Correlation:
Correlation is said to be positive when the values of two variables move in the same direction, so
that an increase in the value of one variable is accompanied by an increase in the value of the other
variable or a decrease in the value of one variable is followed by a decrease in the value of the other
variable
➢ Negative Correlation:
Correlation is said to be negative when the values of two variables move in opposite direction, so
that an increase in the values of one variable is followed by a decrease in the value of the other and
vice-versa
➢ Simple Correlation:
When only two variables are stated, it is said to be simple correlation
➢ Multiple Correlations:
When more than two variables are stated simultaneously, the correlation is said to be multiple
➢ Partial Correlation:
Partial correlation coefficient provides a measure of relationship between a dependent variable and a
particular independent variable when all other variables involved are kept constant analysis to yield
and rainfall; it becomes a problem relating to simple correlation Linear Correlation
➢ Non Linear Correlation:
The correlation is nonlinear, if the amount of change in one variable does not bear a constant ratio to
the amount of change in the other related variable.
METHODS OF STUDYING CORRELATION GRAPHICAL METHOD
➢ Scatter diagram
➢ Simple graph method
REGRESSION ANALYSIS
The statistical method employed to estimate the unknown valued of one variable from the known value of
the related variables is called regression.
DEFINITION
Regression is the measure of the average relationship between two or more variables in terms of the
original units of the data…Blair
Regression analysis Meaning regression analysis is statistical device with which we estimator or predict
the unknown values of one variable from known value of another variable
REGRESSION ANALYSIS DEFINITION
One of the most frequently used techniques in economics and business research, top find a relation
between two or more variables that are related causally, is regression analysis. - Taro Famane
USES OF REGRESSION ANALYSIS
➢ It is useful to estimate the relationship between two variables
➢ It is useful for production of unknown value
➢ It is widely used in social sciences like economics, Natural and physical sciences
➢ It is useful to forecast the business situation
➢ It is useful to calculate correlation co-efficient and co-efficient of determinations
METHODS OF STUDYING REGRESSION
➢ Graphic method
➢ Algebraic method
Graphic method:
Under the method the dots are plotted on a graph paper representing pair of values of the given variables
having a linear relationship the independent variable is taken in the X axis and the dependent variable
taken on Y axis. The regression line of X on Y provides the most probable value of X given the most
probable value of Y when the exact value of X is known. Thus we get two regression lines.
Regression lines
➢ Regression of X on Y
➢ Regression of Y on X
Algebraic Method:
Regression equation is an algebraic method. It is an algebraic expression of the regression line.
Regression Equations
➢ Regression Equation of X on Y Xc = a+ by
➢ Regression Equation of Y on X Yc = a + bx
 UNIT: 5 - INDEX NUMBER
MEANING
As index number is a specialized average designed to measure the change in a group of related variable
over a period of time. It was first constructed in the year.
CONCEPT
In its simplest form on Index number is a Ratio of two numbers expressed as percent.
DEFINITION
Index number devices for measuring difference in the magnitude of a group of related variables---
Croxtonand Cowden
CHARACTERISTICS OF INDEX NUMBER
➢ They are specialized average
➢ They measure the net change in a group of related variables
➢ They measure the effect of changes over a period of time
➢ They help comparison of groups of variables directly
USES OF INDEX NUMBER
➢ Index number is most widely used statistical devises
➢ Index numbers are used to measure the relative changes
➢ They are widely used in the evaluation of business and economic conditions
➢ It is useful for better comparison
➢ It is a good guide for the progress of every country
➢ It is useful for better comparison
➢ It is useful to know trends and techniques
➢ For forecasting future activities
TYPES OF INDEX NUMBERS
➢ Price Index
➢ Quantity Index
➢ Value Index
METHODS OF INDEX NUMBER
➢ Un weighted Index Number
➢ Simple Aggregative method
➢ Simple average of price Relative method
CONSUMER PRICE INDEX NUMBER (OR) COST OF LIVING INDEX
Consumer price Index is designed to measure the change in the cost of living of workers because of
change in the retail price. A change in the price level affects the cost of living of the people. People con
some different types of commodities. So there is need to construct consumer’s price index. Consumer
price index can be used in different places for many purposes.
USES OF COST OF LIVING INDEX
➢ It is useful in fixing the wages
➢ It is useful to know the purchasing power of money
➢ By using the cost of living index the Government determines the price and other variables
➢ It is useful the analysis of price situations
LIMITATIONS OF INDEX NUMBERS
➢ If the chosen base year is not a normal one, the purpose is list
➢ Every index number has its own purpose. No index number can serve all purpose
➢ These are only appropriate indications of the relative level.
FORMULAE
𝑝1
➢ Fundamental formula, I= x 100
𝑞1
∑𝑝1
➢ Simple aggregative method, 𝑃01 = ∑𝑞0
x 100
𝑝
∑𝐼 ∑( 1𝑥100)
𝑝0
➢ Simple price relative method, 𝑃01 = 𝑁
or 𝑁

Weighted aggregative methods

∑𝑝1𝑞0
➢ Laspeyre’s Index No. 𝑃01(𝐿) = ∑𝑝0 𝑞0
x 100

∑𝑝1𝑞1
➢ Paasche’s Index No. 𝑃01(𝑃) = ∑𝑝0 𝑞1
x 100
 ∑𝑝1𝑞0 ∑𝑝1𝑞1
➢ Dorbish & Bowely’s Index No. 𝑃01 (D&B) = ½ (∑𝑝 + ∑𝑝 ) x 100
0 𝑞0 0 𝑞1

∑𝑝1𝑞0 ∑𝑝1𝑞1
➢ Fisher’s Ideal Index No. 𝑃01 (F) = √∑𝑝 𝑥 ∑𝑝 x 100
0 𝑞0 0 𝑞1

∑𝑝1 (𝑞0 +𝑞1 )

➢ Marshall Edgeworth’s Index No. 𝑃01(𝑀𝐸) = ∑𝑝0 (𝑞0 +𝑞1 )
x 100

∑𝑝1 √𝑞0𝑞1
➢ Walsch’s Index No. 𝑃01(𝑊) = x 100
∑𝑝0 √𝑞0 𝑞1

∑𝑝1 𝑞
➢ Kelley’s Index= 𝑃01(𝐾) = ∑𝑝0 𝑞
x 100

∑𝑝1 𝑊
➢ General method 𝑃01 = ∑𝑝0 𝑊
x 100

∑𝐼𝑉 ∑𝑃𝑊
➢ Weighted price relative method or family budget method 𝑃01 = ∑𝑉
or ∑𝑊

Quantity, or Volume Index

∑𝑞1 𝑝0
➢ Laspeyre’s Index = 𝑄01(𝐿) = ∑𝑞1 𝑝0
x 100

∑𝑞1 𝑝1
➢ Paasche’s Index 𝑄01(𝑃) = x 100
∑𝑞0 𝑝1

∑𝑞 𝑝 ∑𝑞1 𝑝1
➢ Fisher’s Ideal Index 𝑄01(𝐹) = √∑𝑞1 𝑝0 𝑥 ∑𝑞0 𝑝1
x 100
1 0

∑𝑝1𝑞1
➢ Value Index 𝑉01 = x 100
∑𝑞0 𝑝1

Cost of living Index

∑𝑝1𝑞0
➢ Aggregate Expenditure Method 𝑃01 = x 100
∑𝑝0 𝑞0

∑𝐼𝑉
➢ Family Budget Method 𝑃01 = ∑𝑉

➢ Test of Consistency
• Times reversal test: 𝑃01 x 𝑃10 = 1
∑𝑝1𝑞1
• Factor reversal test: 𝑃01 x 𝑄01 = ∑𝑝0 𝑞0
• Circular test: 𝑃01 x 𝑃12 x 𝑃20 = 1

ANALYSIS OF TIME SERIES

An arrangement of statistical data in accordance with time of occurrence or in chronological order is
called a time series.
DEFINITION
A time series is a set of observation arranged in chronological order. Morris Hamberg requirement of a
time series Data must be available for a long period of time. Data must consist of a homogeneous set of
values belonging to different time periods. The time gap between the variables or composite of variables
must be as For Passible equal.
USES OF TIME SERIES
➢ It helps in understanding the past behaviors and in establishing the future behavior
➢ It helps in planning and forecasting the future operation
➢ It facilitates comparison between data of one period with those of another period
➢ It helps in evaluating current accomplishment
➢ It is useful in forecasting the trade cycles
TIME SERIES MODELS
Mathematical Models and Multiplicative method
In classical analysis, it is assumed that some types of relationship exist among the four components of
time series
➢ Additive Model:
According to this model, the time series is expressed as Y = T + S + C + I
Y = the value of original time series T = Time Value
S = Seasonal variation C = Cyclical Variation
Irregular fluctuation
Multiplicative Model
According this model, the time series is expressed as
Y=YXSXCXI
TIME SERIES ANALYSIS
➢ Time series analysis is the analysis of identifying different components such as trend, seasonal,
cyclical and irregular in a given time series data.
➢ Components of time series
➢ Time series data contain variations of the following types:
• Secular Trend
• Seasonal Variation
• Cyclical Variations
• Irregular variation
➢ Secular Trend:
A secular trend or long-term trend refers to the movements of the series reflecting continuous
growth or decline over a long period of time. There are many types of trend. Some trends rise
upward and some fall downward
➢ Seasonal Variation:
Is that periodic investment in business activities within the year recurring periodically year after
year?
Generally, seasonal variation appear at weekly, monthly or quarterly intervals
➢ Cyclical Variation:
Up and down movements are different from seasonal fluctuations, in that they extend over longer
period of time – usually two or more years. Business time series is influenced by the wave-like
changes of prosperity and depression.
CAUSES
Changes of property and depression
Uses
➢ Useful to study the character of business fluctuation
➢ Useful to take timely decision in maintaining the business during different stages
➢ Helps in facing recession and utilizing the booms
UN-SECULAR VARIATION
Irregular variation refers to such variation in business activity which do not repeat in a definite pattern.
They are also called ‘erratic ‘accidental or random variations which are generally non-recurring and
unpredictable
CAUSES
War, food, revolution, strike, lockouts and the like
MEASUREMENT OF SECULAR OF SECULAR TREND
➢ Free hand Graphic Method
➢ In this method we must plot the original data on the graph. Draw a smooth curve carefully which will
show the direction of the trend. The time is taken on the horizontal axis I(X) and the value of the
variable on the vertical axis (Y)
MERITS
➢ It is the simplest and easiest method
➢ It can be applied to all types of trends
➢ It is useful to understand the character of time series
DEMERITS
➢ It is subject to personal bias
➢ Its results depend upon the judgments of the person who draw the time
➢ It does not help to measures trend
SEMI – AVERAGE METHOD
In this method the original data are divided into two equal parts and average are calculated for both the
parts. These averages are called semi average. Trend line is drawn with the help of the semi averages
MERITS
➢ It is simple and easier to understand
➢ Everyone will get the same trend like
➢ We can predict the future values based on the intermediate values
DEMERITS
➢ It is affected by the limitations of arithmetic mean
➢ It is not enough for forecasting the future trend
MOVING AVERAGE METHOD
In this method, the average value of a number of years or months or weeks is taken into account and
placed it at the Centre of the time span and it is the normal or trend value for the middle period.