THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA.

PRANAV POPAT

Statistics Theory Weightage till Jan 2025

Chapter → Chp13 Chp14 Chp17 Chp18 Total
Exam↓
May 18 2 4 6 8 20
Nov 18 6 1 2 3 12
Jun 19 5 3 1 5 14
Nov 19 1 7 2 5 15
Nov 20 8 5 3 6 22
Jan 21 10 5 2 4 21
Jul 21 6 1 1 0 8
Dec 21 3 5 2 4 14
Jun 22 9 3 4 6 22
Dec 22 4 3 1 3 11
Jun 23 2 0 0 2 4
Dec 23 5 0 2 2 9
Jun 24 7 3 2 4 16
Sep 24 8 4 3 3 18
Jan 25 4 3 0 2 9

Click the Poster to Watch Session

THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Theory Concept Marathon

THEORY CONCEPTS

Statistical Description of Data – Basics of Statistics

• Plural Sense: Any data – quantitative or qualitative used for statistical

analysis.
Definition of
• Singular Sense: Scientific method of collecting, analyzing, and
Statistics
presenting data to draw statistical inferences. It is also called as
Science of Averages or Science of Counting
Language Actual Word Memorize by
Latin Status Latus
Origin of
Italian Statista Pasta
Word
German Statistic Breadstick
French Statistique Barbeque
Koutilya’s • Record of Birth and Deaths
Arthashastra • Chandragupta’s reign
• 4th Century B.C
Abu Fezal’s Ain-i- • Record on Agriculture
Publication
Akbari • Akbar Reign
• 16th Century A.D.
First Census • Egypt 300 BC to 2000 BC
• By Pharaoh
• Economics: Demand Analysis, Future Projection etc.
• Business Management: Decision making using quantitative
Application of
techniques not intuition
Statistics
• Industry and Commerce: Profit maximization using business data –
sales, purchase, market etc. by consulting experts
• It deals with aggregate data and not individual data
• Quantitative data can only be used, however for qualitative – it needs
to be converted into quantitative
Limitation of
• Projections are based on conditions/ assumptions and any change in
Statistics
that will change the projection. Example: Future projections of sales
• Sampling based conclusions are used, improper sampling leads to
improper results. Random Sampling is must.
• Quantitative Information shown as number
Data • Primary: first time collected by agency/ investigator
• Secondary: collected data used by different person/ agency
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

• Measurable Data – Value can vary

• When a variable assumes a finite or count
Discrete ably infinite isolated values.
Variable • Example: no. of petals in a flower, no. of
Variable road accident in locality
• When a variable assumes any value from
Continuous the given interval (can also be in decimals,
Variable fractions).
• Example: height, weight, sale, money
• Qualitative Characteristics. Example: gender of a baby, the
Attribute
nationality of a person, the colour of a flower etc.
Method Details
Personal • Where data is collected directly from
Interview respondents.
• Highly Accurate – Low Coverage
• Example: Natural Calamity, Door to Door
Collection of Survey
Primary Data
Indirect • When reaching respondent is difficult, data is
– Interview
Interview collected by contacting associated persons.
Method
• Highly Accurate – Low Coverage
• Example: Rail accident
Telephone • Data is collected over phone
Interview • Quick and non-expensive method
• Low Accuracy – High Coverage
Collection of • In this method well drafted and soundly sequenced questionnaire,
Primary Data • covering all the important aspects of the data requirement is sent to
– Mailed respondent for filling.
Questionnaire • Here coverage is wide but amount of non-responses will be
Method maximum
• In this method data is collected by direct observation or using
Collection of
instrument.
Primary Data
• For example: data on height and weight for a group of students.
– Observation
Method • Although more accurate but it is time consuming, low coverage and
laborious method.
Collection of
Primary Data
• Mix of Interview and Mailed Questionnaire
–
• Enumerator means a Person who directly interacts with respondent
Questionnaire
and fills the questionnaire.
Filled and
• It is generally used in case of Surveys and Census.
sent by
Enumerators
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

International World Health Organization (WHO), International

Sources Monetary Fund (IMF), International Labor
Organization (ILO), World Bank
Government In India – Central Statistics Office (CSO), Indian
Sources of
Sources Agricultural Statistics by the Ministry of Food and
Secondary
Agri, National Sample Survey Office- NSSO,
Data
Regulators – RBI, SEBI, RERA, IRDA
Private or Indian Statistical Institute (ISI), Indian Council of
Quasi-govt. Agriculture, NCERT
sources
• checking accuracy and consistency of data
• There is no rule for it, one must apply his intelligence, patience and
Scrutiny of
experience while scrutinizing the given information.
Data
• Internal Consistency: When two or more series of related data are
given, we should check consistency among them.
Classification or Organisation: putting data in a neat, precise, and
condensed form, making it comparable, suitable for analysis, more
understandable.
Chronological/ • Data arranged based on Time
Temporal/ Time • Example: Revenues YoY i.e year on year
Presentation Series Data
of Data – Geographical or • Arrangement based on regions
Classification Spatial Series Data • Example: Country wise Revenue of a
/ Organization
global company
of Data
Qualitative or • Based on some attribute
Ordinal Data • Nationality Wise Medal Winners in
Olympics
Quantitative or • Based on some variable
Cardinal Data • Example: Frequency Distribution of a Data
Mode of • This method comprises presenting data with the help of a paragraph
Presentation or several paragraphs.
of Data – • This is not a suitable mode of presentation as it is dull, monotonous
Textual and non-comparable.
• When data is shown in the form of Table.
Mode of • Useful in easy comparison
Presentation • Complicated data can be presented
of Data – • Table is must to create a diagram
Tabular Form • No analysis possible without table
• Components of Table
Description Name of Component of Table
Entire Upper Part Box Head
Upper Part describing Caption
Components
columns and sub-columns
of Table
Left part of the table Stub
describing rows
Main Data of Table Body
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Source of Data at the bottom Footnote

of Table
Mode of
• Can be used by educated and uneducated section of society
Presentation
• Hidden trend can be traced
of Data –
• If priority is accuracy, then tabulation is better
Diagrams
• Time Series is generally in x axis
• For wide fluctuation – log chart or ratio chart is used
Line Diagram
• Two or more series of same unit – Multiple Line Chart
• Two or more series of different unit – Multiple Axis Chart
• Bar means rectangle of same width and of varying length drawn
horizontally or vertically
• For comparable series – multiple or grouped bar diagrams can be
used
• For data divided into multiple components – subdivided or
component bar diagrams
Bar Diagram
• For relative comparison to whole, percentage bar diagrams or divided
bar diagrams
• Vertical Bar Diagram: Useful for Data varying over Time and
Quantitative Data
• Horizontal Bar Diagram: Useful for Data varying over Space and
Qualitative Data
• Used for circular presentation of relative data (% of whole)
• Summation of values of all components/segments are equated to
360 Degree (total angle of circle)
Pie Chart
• Segment angle =
(segment value x 360°)
(total value)

Statistical Description of Data – Frequency Distribution

• Frequency means number of times a particular observation is

repeated.
• Frequency Distribution is table which contains observation or
class intervals in one column and corresponding frequency in the
other.
Frequency and
• Definition: A frequency distribution may be defined as a
Distribution
- tabular representation of statistical data, usually in an
ascending order,
- relating to a measurable characteristic
- according to individual value or a group of values of the
characteristic under study.
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Ungrouped/ • When there are limited number of distinct

Simple observations, frequency can be assigned to each
Frequency one of them.
Distribution • This distribution is simple
Types of Grouped • When there are large no. of observations, grouping
Frequency Frequency is done among them (generally in ascending
Distribution Distribution order).
• Each group is called as class interval and
frequency is assigned to group and not individual
values,
• this is called Grouped Frequency Distribution
• For a class interval CL is the minimum and maximum value the
class interval may contain
• Minimum Value – Lower Class Limit
• Maximum Value – Upper Class Limit
Class Limit
Class Interval Frequency LCL UCL
10-19 10 10 19
20-29 5 20 29
30-39 8 30 39
Mutually Exclusive / • Here UCL an interval and LCL of next
Overlapping interval are same
Classification • This is usually applicable for
continuous variable.
Class LC UC • An observation which is equivalent to
L L common class limit is excluded from
10-20 10 20 the class interval where it is UCL and
Classification 20-30 20 30 taken in the class where it is LCL.
of Grouped of
30-40 30 40
Frequency
Mutually Inclusive / • There is no common class limits
Distribution
Non-Overlapping between two intervals.
Classification • This is usually applicable to discrete
Class LC UC variable.
L L • All observation including UCL and LCL
10-19 10 20 will be taken in the same class interval
20-19 20 30 as there is no confusion.
30-39 30 40
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

In case of Exclusive / Class Boundary = Class Limit

Overlapping Class LC UC LCB UC
Classification L L B
10-20 10 20 10 20
20-30 20 30 20 30
30-40 30 40 30 40
In case of Inclusive / Lower Class Boundary
Class Boundary
Overlapping LCB = LCL – 0.5
Classification UCB = UCL + 0.5
Class LC UC LCB UCB
L L
10-19 10 19 9.5 19.5
20-29 20 29 19.5 29.5
30-39 30 39 29.5 39.5
Mid-Point / LCL+UCL LCB+UCB
Class Mark / 2 2
Mid Value of • Useful in calculation of AM, GM, HM, SD in case of grouped
Class Interval frequency distribution
Class Length/
UCB – LCB only
Width or Size
• Less than type: It shows no. of observations less than UCB
• More than type: It shows no. of observations more than UCB

Class Freq. UCB Less than More than Total of

Interval type CF type CF both CF
Cumulative 44-48 3 48.5 3 33 36
Frequency 49-53 4 53.5 7 29 36
54-58 5 58.5 12 24 36
59-63 7 63.5 19 17 36
64-68 9 68.5 28 8 36
69-73 8 73.5 36 0 36
Total 36
Frequency Class Frequency
Density Class Length of class
Class frequency
Relative
Frequency Total Frequency
Its can have values between 0 and 1
Percentage Class frequency
× 100
Frequency Total Frequency
Frequency Dist. • It is a convenient way to represent FD
Diagram – • Comparison between frequency of two different classes possible
Histogram • It is useful to calculate mode also
Frequency • Usually preferable for ungrouped frequency distribution
Polygon • Can be used for grouped also but only if class lengths are even
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Ogives/ • This graph can be made by both type of Cumulative Frequency and
Cumulative called as Less than Ogive or More than Ogive
Frequency • It can be used for calculating quartiles, median
• It is a limiting form of Area Diagram (Histogram) or Frequency Polygon
Frequency • It is obtained by drawing smooth and free hand curve though the mid
Curve points
• Most used curve is Bell Shaped

Index Numbers

• Index numbers are convenient devices for measuring relative

changes (generally in %) of differences from time to time or from
Practical
place to place
Examples of
• Series of numerical figures which show relative position
Index Numbers
• Index Numbers show percentage changes rather than absolute
amounts of change
• It depends on the purpose for which the index is used.
• Index numbers are often constructed from the sample. Random
sampling, and if need be, a stratified random sampling can be
Data Selection
used to ensure that sample is representative.
• Data should be comparable by ensuring consistency in selection
method.
• It is a point of reference in comparing various data.
• Standard point of comparison.
Base Period • The period should be normal.
• It should be relatively recent
• Choice of suitable base period is a temporary solution
• The geometric mean is better in averaging relatives,
Use of
• But for most of the index’s arithmetic mean is used because of its
Averages
simplicity
Price/ For Individual Commodity,
Quantity/ Value Current Period Price/ Quantity/ Value
Relative Base Period Price/ Quantity/ Value
P1 P2 P3 Pn
, , ,…,
Link Relative P0 P1 P2 Pn-1
Same can be created for quantities also
When the above relatives are in respect to a fixed base period these are also
called the chain relatives
Chain relatives P1 P2 P3 Pn
, , ,…,
P0 P0 P0 P0
Formula for Link relative of current year × Chain Index of previous year
Chain Index 100
(when direct
data is not
available)
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

The chain index is an unnecessary complication unless of course where data

for the whole period are not available or where commodity basket or the
weights have to be changed.

• Chances of errors due to Sampling

Limitations of
• It gives broad trend not real picture
Index Numbers
• Due to many methods, at times it creates confusion
• Index numbers are very useful in deflating (eg. Nominal wages into
real)
• Framing suitable policies in economics and business
Usefulness of
• They reveal trends and tendencies in making important
Index Numbers
conclusions
• They are used in time series analysis to study long-term trend,
seasonal variations and cyclical developments
Formula for Current Value
Deflated Value =
Deflated Value Price Index of the current year

Shifted Price Original Price Index

× 100
Index Price Index of the year on which it has to be shifted
• This test requires that the formula should be independent of the unit
in which or for which prices and quantities are quoted.
Unit Test
• Except for the simple (unweighted) aggregative index all other
formulae satisfy this test.
• It is a test to determine whether a given method will work both ways
in time, forward and backward.
Time Reversal
• P01 × P10 = 1
Test
• Laspeyres’ method and Paasche’s method do not satisfy this test, but
Fisher’s Ideal Formula does.
• This holds when the product of price index and the quantity index
should be equal to the corresponding value index.
Factor Reversal • Symbolically
Test P01 × Q01 = V01
• Fisher’s Index Number is ideal as it satisfies Unit, Time Reversal and
Factor Reversal Test
• This property therefore enables us to adjust the index values from
period to period without referring each time to the original base.
• It is an extension of time reversal test
• The test of this shiftability of base is called the circular test.
• This test is not met by Laspeyres, or Paasche’s or the Fisher’s ideal
Circular Test
index.
• The weighted GM of relative, simple geometric mean of price
relatives and the weighted aggregative with fixed weights meet this
test.
(These methods are not in syllabus)
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

• CLI is defined as the weighted AM of index numbers of few groups of

Cost of Living basic necessities.
Index (also • AM of group indices gives the General Index
called General • Generally, for calculating CLI; food, clothing, house rent, fuel &
Index) lightning and miscellaneous groups are taken into consideration.
• Examples of CLI: WPI, CPI, etc.
• 𝑃01 is the index for time 1 on 0
Symbol • 𝑃10 is the index for time 0 on 1

Measures of Central Tendency

Arithmetic Mean

Property 1 If all the observations are constant, AM is also constant

the algebraic sum of deviations of a set of observations from their
Property 2
AM is zero
AM is affected both due to change of origin and scale
Property 3
If y = a + bx then y = a + bx
Combined AM
Property 4 n1 x1 + n2 x2
xc =
n1 + n2
• AM is best measure of central tendency
• AM is based on all observations
General Review • AM is affected by sampling fluctuations
• AM is amenable to mathematical property
• AM cannot be used in case of open end classification

Median

For a set of observations, the sum of absolute deviations is

Property 1 minimum, when the deviations are taken from the median.
 xi − Me
Property 2 Median is also affected by both change of origin and scale.
• Median is also called as positional average
• Median is not based on all observations
General Review • Median is not affected by sampling fluctuations
• Median is best measure of central tendency in case of open
end classification
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Partition Values

• These may be defined as values dividing a given set of

observations into number of equal parts
• When we want to divide the given set of observations into
two equal parts, we consider median, similarly there are
quartiles, deciles, percentiles
Name of PV No. of equal No. of PVs Symbol
Meaning
parts
Median 2 1 Me
Quartile 4 3 Q1 ,Q2 ,Q3
Decile 10 9 D1 ,D2 ,...,D9
Percentile 100 99 P1 ,P2 ,...,P99

Mode – Concept/ Formula

Meaning Mode is the value that occurs the maximum number of times
• If two or more observations are having maximum frequency
then there are multiple modes [multimodal distribution]
• If there are exactly two modes then distribution is called as
Special Thing about
Bimodal Distribution
Mode
• If all observations are having same frequency then
distribution has no mode
• We can say that Mode is not rigidly defined
Property 1 If all the observations are constant, mode is also constant
Property 2 Mode is also affected both due to change of origin and scale
• Mode is not based on all observations
General Review • Mode is not rigidly defined
• Mode is not amenable to Mathematical Property

Relationship between Mean, Median and Mode

In case of Symmetric
Mean = Median = Mode
Distribution
In case of Moderately
Skewed Distribution
Mean – Mode = 3 (Mean – Median)
(Empirical
relationship)
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Geometric Mean

For a given set of 𝑛 positive observations, the geometric mean is

Definition
defined as the 𝑛𝑡ℎ root of the product of the observations
Logarithm of G for a set of observations is the AM of the logarithm
of the observations
Property 1
1
log G =  log x
n
Property 2 If all the observations are constant, GM is also constant
Property 3 GM of z = GM of x  GM of y
GM of x
Property 4 GM of z =
GM of y

Harmonic Mean

For a given set of non-zero observations, harmonic mean is

Definition defined as the reciprocal of the AM of the reciprocals of the
observation
Property 1 If all observations are constant HM is also constant

Use of GM and HM

Both Both are used for calculating average rates

GM Appropriate for rates having percentages
HM Appropriate for rates other than percentages

Measures of Dispersion

• Dispersion for a given set of observations may be defined

Meaning of Measure of as
Dispersion • the amount of deviation of the observations,
• usually, from an appropriate measure of central tendency
Absolute • These are with units
Measures of • These are not useful for comparison of two
Dispersion variables with different units.
• Example: Range, Mean Deviation, Standard
Deviation, Quartile Deviation
Types of Measure of
Relative • These are unit free measures
Dispersion
Measures of • These are useful for comparison of two
Dispersion variables with different units.
• Example: Coefficient of Range, Coefficient of
Mean Deviation, Coefficient of variation,
Coefficient of Quartile Deviation
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Range

• Not affected by change of origin

• Affected by change of scale (only value)
Property 1
• No impact of sign of change of scale
• Note: Measure of Dispersion can never be negative
• Not Based on All Observations
General Review
• Easy to Compute

Mean Deviation

• Mean deviation is defined as the

• arithmetic mean of the
Meaning
• absolute deviations of the observations
• from an appropriate measure of central tendency
Mean Deviation takes its minimum value when deviations are
Property 1
taken from Median
Change of Origin – No Affect, Change of Scale – Affect of value
Property 2
not sign
• Based on all observations
• Improvement over Range
General Review • Difficult to compute
• Not amenable to Mathematical Property because of
usage of Modulus

Standard Deviation

• Improvement over Mean Deviation

Meaning • It is defined as the root mean square deviation when the
deviations are taken from the AM of the observations
Coefficient of SDx
Variation
 100
x
SD for any two |a − b|
numbers
SD =
2
SD for first n natural
n2 − 1
numbers s=
12
Property 1 If all the observations are constant, SD is ZERO
No effect of change of origin but affected by change of scale in the
Property 2
magnitude (ignore sign)
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

n1s12 + n2s22 + n1d12 + n2d22

SDc =
Property 3
n1 + n2
d1 = xc − x1
d2 = xc − x2

Quartile Deviation

Meaning It is semi-inter quartile range

• It is the best measure of dispersion for open-end
classification
General Review • It is also less affected due to sampling fluctuations
• Like other measures of Dispersion, QD is also not affected
by change of origin but affected by scale ignoring sign

Correlation and Regression

Bivariate Data

• When data are collected on two variables simultaneously,

they are known as bivariate data
Definition
• and the corresponding frequency distribution, derived from it,
is known as Bivariate Frequency Distribution
• It is the frequency distribution of one variable (x or y) across
Marginal Distribution the other variable’s full range of values
• Number of Marginal Distribution = 2
• It is the frequency distribution of one variable (x or y) across
a particular sub-population of the other variable.
Conditional
• No. of Conditional Distributions = m + n
Distribution
m = no. of class interval of x
n = no. of class interval of y

Scatter Diagram

• It helps us to find Nature and Relative Strength of

Correlation
Concept Points • It is useful for Non-Linear Correlation also
• It cannot be used to determine value
• Diagrams are time taking
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Karl Pearson’s Correlation Coefficient

Correlation Coefficient is the ratio of covariance with product of

How to Calculate
standard deviations
Property 1 The Coefficient of Correlation is a unit-free measure
Property 2 Value lies from -1 to +1
Change of No impact
Origin
Property 3 Change of No impact of value, but if change of scale of
Scale both variables are of different sign then sign
of r will also change
Value of r Interpretation
-1 Perfect Negative
Between -1 and 0 Negative
Closer to -1 Strong Negative
Interpretation of Value Far from -1 Weak Negative
of r 0 No Correlation
Between 0 and 1 Positive
Far from +1 Weak Positive
Near to +1 Strong Positive
+1 Perfect Positive

Spearman’s Rank Correlation Coefficient

• find the level of agreement (or disagreement) between

two judges so far as assessing a qualitative characteristic
Usage
(attribute) is concerned
• Use in case of ranks
In case of tie, simple average of ranking should be assigned to tied
Ranking in case of Tie
values

Coefficient of Concurrent Deviations

A very quick, simple and casual method of finding correlation

Usage
when we are not serious about the magnitude of the two variables

Regression Basics

Estimation of one variable for a given value of another variable on

Meaning the basis of an average mathematical relationship between the
two variables
• Estimation of Y when X is given
Requirements
• Estimation of X when Y is given
THEORY HAI ZAROORI NOTES 2025 | COMPILED BY CA. PRANAV POPAT

Perfect • When linear relationship exists between

Correlation two variables, correlation is perfect.
• Perfect Correlation is represented by a
linear equation and this equation can be
used for regression purpose directly.
General Points
• Same equation can be used in both ways
Imperfect • In case of imperfect correlation there is no
Correlation definite line and equation
• We will use method of least square to
estimate both regression lines

Estimation of Y • Use Regression line of Y on X

when X is given • Equation Format:
Y − Y = byx (X − X)
Formula of Regression byx is regression coefficient of Y on X
Equations/ Lines Estimation of X • Use Regression line of X on Y
when Y is given • Equation Format:
X − X = bxy (Y − Y)
bxy is regression coefficient of X on Y
Change of Origin and Scale
• Origin: No Impact
• Scale: If original pair is x, y and modified pair is u, v
Property 1 change of scale of y
bvu = byx 
change of scale of x
change of scale of x
buv = bxy 
change of scale of y
Two regression lines (if not identical) will intersect at the point
Property 2
[means] ( x, y )
Relation between Correlation and Regression Coefficients
Property 3 rxy =  bxy  b yx
rxy ,bxy ,byx will always have same sign

Coefficient of Determination and Non-Determination

Coefficient of Determination
Accounted Variance/ Explained Variance r2
Coefficient of Non-Determination
Unaccounted Variance/ Unexplained Variance 1 − r2