Class 11 Humanities . Economics . Statistics For Economics . Organizing of Data

Chapter 3: Organizing of Data

Ch 3

Economics

Class 11 Humanities

Lecture 1

Introduction

Reference video · Lecture 1Introduction

Classification of Data

Definition

Classification — Arranging or organising things into groups or classes based on some criterion.

  • Purpose: Classification brings order to raw data and makes further statistical analysis easier.
  • Relevant grouping: The criterion should suit the purpose; including unrelated items defeats the purpose of grouping.
  • Benefits: Organised data are easier to locate, compare and use to draw conclusions.
  • Example: A junk dealer groups goods as newspapers, plastics, glass and metals, and may sort metals into iron, copper, aluminium and brass.
Disorganised data and records illustrate why classification is useful.
Disorganised data and records illustrate why classification is useful.

Raw Data and the Need for Organisation

Definition

Raw data — Collected data that have not yet been organised or classified.

  • Nature: Raw data consist of observations on one or more variables and may be large and cumbersome to handle.
  • Difficulty: Finding information or drawing conclusions from large, unclassified data is tedious.
  • Next step: After collecting data, organise and present them in classified form before systematic statistical analysis.
  • Examples: Marks in mathematics for 100 students and monthly food expenditure for 50 households are raw data when presented without arrangement.
  • Census example: India conducts a population census every ten years. In Census 2001, about 20 crore persons were contacted; classifying data by gender, education, marital status and occupation helps reveal the population's structure and nature.
Unorganised data can make it difficult to find information.
Unorganised data can make it difficult to find information.

Choosing How to Classify

  • Purpose matters: The way data are classified depends on the purpose of the investigation.
  • Example: A mathematics teacher may want to know how students performed and how many did not pass.
  • Chosen approach: To study the marks in depth, the teacher may construct a frequency distribution; its construction is discussed in the next section.

What is classification of data, and why is it useful?

Answer: Classification arranges data into groups based on a relevant criterion. It makes information easier to find, compare and analyse.

Why is raw data difficult to analyse?

Answer: Raw data are often unorganised and large. Finding information and drawing conclusions from them can be tedious.

What determines how data should be classified?

Answer: The purpose of the investigation determines how the data should be classified.

Quick recap

  • Classification groups things or data using a relevant criterion.
  • Classification brings order to raw data and supports further statistical analysis.
  • Raw data are unorganised observations on variables and can be difficult to handle when large.
  • Classified data are easier to locate, compare and use to draw conclusions.
  • The purpose of an investigation determines the appropriate way to classify data.
  • A teacher studying students' marks may construct a frequency distribution.
Lecture 2

Classification Of Data

Reference video · Lecture 2Classification Of Data
Definition

Classification of data — Arranging raw data into groups or classes according to a chosen purpose or characteristic.

Chronological Classification

Definition

Chronological classification — Arranging data in ascending or descending order according to time, such as years, quarters, months or weeks.

Example: Population of India

  • Time series: Population is a time series when its values are recorded for different years.
  • Reading the data: Population rose from 35.7 crores in 1951 to 121.0 crores in 2011.
Population of India
YearPopulation (crores)
195135.7
196143.8
197154.6
198168.4
199181.8
2001102.7
2011121.0

Spatial Classification

Definition

Spatial classification — Arranging data according to geographical locations, such as countries, states, cities or districts.

Wheat Yield by Country, 2013
CountryYield (kg/hectare)
Canada3594
China5055
France7254
Germany7998
India3154
Pakistan2787
Disorganized records compared with records neatly arranged in cabinets.
Disorganized records compared with records neatly arranged in cabinets.

Qualitative Classification

Definition

Qualitative classification — Grouping data according to attributes or qualities that cannot be measured numerically.

Attributes

  • Examples: Nationality, literacy, religion, gender and marital status.
  • Basis for grouping: An attribute is classified by whether a characteristic is present or absent.
  • More than one attribute: A population may first be grouped by gender, then each group by married or unmarried status.

Quantitative Classification

Definition

Quantitative classification — Grouping data into classes according to characteristics that can be expressed numerically.

Quantitative Characteristics

  • Examples: Height, weight, age, income and students’ marks.
  • Frequency distribution: A table that shows how many observations fall in each class.
Mathematics Marks of 100 Students
MarksFrequency
0–101
10–208
20–306
30–407
40–5021
50–6023
60–7019
70–806
80–905
90–1004
Total100
Definition

Relative frequency — A class frequency expressed as a proportion or percentage of the total frequency.

Relative Frequency as a Percentage
fN×100\frac{f}{N}\times 100

Here, ff is the class frequency and NN is the total frequency.

Reading the Marks Distribution

  • Maximum concentration: The 50–60 class has frequency 23, or 23% of the students.
  • Minimum concentration: The 0–10 class has frequency 1, or 1% of the students.
⚠ Common mistake

Do not confuse qualitative and quantitative classification: grouping objects as living or non-living uses a quality, so it is qualitative.

What is the difference between chronological and spatial classification?

Answer: Chronological classification groups data by time; spatial classification groups data by geographical location.

Quick recap

  • Classification arranges raw data into groups according to a chosen purpose.
  • Chronological classification groups observations by time; data across years can form a time series.
  • Spatial classification groups data by place, such as country or state.
  • Qualitative classification uses non-measurable attributes; quantitative classification uses measurable characteristics.
  • A frequency distribution records the number of observations in each quantitative class.
  • Relative frequency is a class frequency expressed as a proportion or percentage of the total.
Lecture 3

Variables: Continuous And Discrete

Reference video · Lecture 3Variables: Continuous And Discrete

Continuous and Discrete Variables

Definition

Continuous variable — A variable that can take any numerical value within a range, including whole, fractional and irrational values.

Definition

Discrete variable — A variable that takes only specific, separate values and changes in finite jumps, without taking intermediate values.

Continuous vs Discrete Variables
PointContinuousDiscrete
ValuesCan take any value in a range, including fractional values.Can take only distinct values; intermediate values are excluded.
ChangeVaries through infinitely many gradations.Changes by finite jumps.
ExamplesHeight, weight, time and distance.Number of students in a class; a variable taking only 1/81/8, 1/161/16, 1/321/32, ...

Examples and Classification

  • Height: A student's height can take values such as 9090 cm, 90.8590.85 cm or 149.99149.99 cm within a range.
  • Student count: A class can have 2525 or 2626 students, but not 25.525.5.
  • Fractions do not determine the type: A variable taking 1/81/8, 1/161/16, 1/321/32, ... is discrete if it cannot take values between successive listed values.
  • Continuous examples: Area, volume, temperature, crop yield, rainfall and age.
  • Discrete examples: Number appearing on a die, population and number of cars on a road.

Frequency Distribution and Its Terms

Definition

Frequency distribution — A systematic classification of quantitative raw data into classes, showing the number of observations in each class.

Classes and Class Frequency

  • Class: A range into which observations are grouped; for example, marks may be grouped into 00–1010, 1010–2020, ..., 9090–100100.
  • Class frequency: The number of observations in a particular class.
  • Example: The 3030–4040 class has marks 30,37,34,30,35,39,3230, 37, 34, 30, 35, 39, 32 in the example, so its frequency is 77.
  • Endpoint note: The raw data also contain two marks of 4040, which are not included in the stated 3030–4040 frequency. The reason for this is left for explanation later in the chapter.
Definition

Class limits — The two endpoints of a class: the lower class limit is the lower endpoint and the upper class limit is the upper endpoint.

Definition

Class interval (class width) — The difference between a class's upper and lower limits.

Class Interval
W=U−LW=U-L

For the class 6060–7070, the class interval is 1010.

Definition

Class midpoint (class mark) — The value halfway between a class's lower and upper limits; it represents the class in calculations using grouped data.

Class Midpoint
m=U+L2m=\frac{U+L}{2}

For the class 6060–7070, the class midpoint is 6565.

Grouped Marks: Class Frequencies and Midpoints
ClassFrequencyLower limitUpper limitClass mark
00–101010105
1010–20208102015
2020–30306203025
3030–40407304035
4040–505021405045
5050–606023506055
6060–707019607065
7070–80806708075
8080–90905809085
9090–10010049010095

Using Grouped Data

  • Grouped observations: Once raw data are arranged into classes, individual observations are generally replaced by their class marks in further calculations.

Frequency Curve

Definition

Frequency curve — A graphical representation of a frequency distribution, made by plotting class marks against their frequencies.

Axes

  • X-axis: Class marks.
  • Y-axis: Class frequencies.
Frequency curve showing the distribution across marks from 0 to 100.
Frequency curve showing the distribution across marks from 00 to 100100.

Why is the number of students in a class a discrete variable?

Answer: It can take only whole-number values; fractional values such as 25.525.5 students are not possible.

How is a class midpoint found, and what does it represent?

Answer: Add the lower and upper class limits and divide by 22. It represents that class in calculations with grouped data.

Quick recap

  • Continuous variables can take any value within a range; discrete variables take separate values without intermediate values.
  • A discrete variable may take fractional values if only specific fractions are allowed.
  • A frequency distribution groups quantitative data into classes and records each class frequency.
  • Class width equals upper limit minus lower limit; class midpoint is the average of the two limits.
  • For grouped calculations, class marks represent the classes.
  • A frequency curve plots class marks on the X-axis and frequencies on the Y-axis.
Lecture 4

How to prepare a Frequency Distribution?

Reference video · Lecture 4How to prepare a Frequency Distribution?

Decisions in Preparing a Frequency Distribution

Five key decisions

  • Class intervals: Decide whether intervals should be equal or unequal in size.
  • Number of classes: Decide how many classes to use.
  • Class size: Decide the size of each class interval.
  • Class limits: Determine clear lower and upper limits for each class.
  • Frequencies: Decide how to obtain the frequency for each class.

Equal or Unequal Class Intervals?

Definition

Class interval — A class interval is a range used to group values of a variable.

When to use unequal intervals

  • Very wide range: For income, equal moderate-sized intervals may produce too many classes, while large intervals may hide information at the low or high end.
  • Concentrated values: If many observations lie in a small part of the range, equal intervals may provide little information about many values.
  • Usual choice: Use equal-sized intervals in other cases.

Number of Classes and Class Width

  • Typical number: A frequency distribution usually has between 66 and 1515 classes.
  • Range: The range is the largest value minus the smallest value.
  • Linked decisions: The number of classes and class size are interdependent; deciding one depends on the other.
Range
R=Xmax⁡−Xmin⁡R = X_{\max} - X_{\min}

Subtract the smallest value from the largest value.

Number of equal-width classes
k=Rhk = \frac{R}{h}

For equal-sized class intervals, divide the range by the class size.

Example

  • Given: If the range is 100100 and there are 1010 equal classes, each class has size 1010.
  • Unequal option: Classes may instead have different widths when unequal intervals are chosen.

Determining Class Limits

  • Clear limits: State definite lower and upper limits for each class.
  • Avoid open-ended classes: Classes such as “less than 10” or “70 and over” are generally undesirable.
  • Class placement: Choose limits so that values tend to concentrate near the middle of their class intervals.
Inclusive vs Exclusive Class Intervals
PointInclusiveExclusive
Boundary valuesValues equal to the lower or upper limit are included in that class.A value equal to either class limit is excluded from that class.
Discrete variablesCan be used.Can be used.
Continuous variablesUsed very often.Boundary conventions should be clearly specified.

Discrete-variable example: marks

  • Data: Marks are discrete when fractional marks are not allowed; suppose they range from 00 to 100100.
  • Inclusive classes: One option is 00–1010, 1111–2020, 2121–3030, continuing to 9191–100100.
  • Exclusive classes: Another option is 00–1010, 1010–2020, 2020–3030, continuing to 9090–100100; boundary values need a stated allocation rule.
  • Lower limit excluded: Values such as 1010 and 3030 go into 00–1010 and 2020–3030, respectively.
  • Upper limit excluded: Values such as 1010 and 3030 go into 1010–2020 and 3030–4040, respectively.

Continuous-variable example: height or weight

  • Class notation: Weight intervals may be written as 3030 kg to under 4040 kg, 4040 kg to under 5050 kg, and 5050 kg to under 6060 kg.
  • Boundary convention: Each interval includes its lower limit but excludes its upper limit; for example, the first covers 3030 kg and above but under 4040 kg.

Finding the Frequency of Each Class

  • Final decision: Determine how the frequency for each class will be obtained.
Income Distribution of 550 Employees
Income (Rs.)Number of employees
800–89950
900–999100
1000–1099200
1100–1199150
1200–129940
1300–139910
Total550

When are unequal class intervals suitable?

Answer: When the variable has a very wide range, such as income, or when values are concentrated in a small part of the range.

How do inclusive and exclusive class intervals differ?

Answer: Inclusive intervals include values equal to either limit in that class. Exclusive intervals exclude values equal to either limit from that class.

How are the number and size of equal class intervals related to the range?

Answer: The number of classes is the range divided by the class size: k=R/hk = R/h.

Quick recap

  • Frequency distributions usually have between 66 and 1515 classes.
  • Unequal intervals suit very wide ranges or concentrated values; equal intervals are usual otherwise.
  • For equal-sized classes, the number of classes equals the range divided by class size.
  • Use definite class limits and generally avoid open-ended classes.
  • Discrete variables can use inclusive or exclusive intervals; continuous variables often use inclusive intervals.
  • Continuous-variable classes may be written to include the lower limit and exclude the upper limit.
Lecture 5

Adjustment in Class Interval

Reference video · Lecture 5Adjustment in Class Interval

Making Inclusive Class Intervals Continuous

Definition

Class-interval adjustment — A correction to class limits that removes gaps between successive classes and represents a continuous variable continuously.

Adjustment procedure

  • Why adjust? Inclusive classes such as 800800–899899 and 900900–999999 leave a gap between successive limits.
  • Find the gap: Subtract the first class’s upper limit from the next class’s lower limit.
  • Split the gap: Divide the difference by 22; subtract this amount from every lower limit and add it to every upper limit.
Adjusted Income Distribution of 550 Employees
Adjusted income class (Rs.)Number of employees
799.5799.5–899.5899.55050
899.5899.5–999.5999.5100100
999.5999.5–1099.51099.5200200
1099.51099.5–1199.51199.5150150
1199.51199.5–1299.51299.54040
1299.51299.5–1399.51399.51010
Total550550
Adjusted class mark
Ua+La2\frac{U_a+L_a}{2}

The adjusted class mark is the midpoint of the adjusted class limits.

Finding Class Frequencies with Tally Marks

Definition

Class frequency — The number of observations that fall within a particular class interval.

Frequency and tallying

  • Raw-data frequency: Counts how many times a particular value occurs; for example, 4040 occurs 33 times and 4949 occurs 55 times in the given data.
  • Grouped-data frequency: Counts the observations in a whole class, rather than repetitions of one specific value.
  • Tallying: Record one tally against a class for each observation belonging to it. A mark of 5757 goes in 5050–6060, 7171 in 7070–8080, and 4040 in 4040–5050.
  • Groups of five: Four tallies are crossed by the fifth to make counting easier; class frequency equals the total number of tallies.
Marks of 100 Students: Class Frequencies and Class Marks
Class intervalTally marksFrequencyClass mark
00–1010|1155
1010–2020||||/ |||881515
2020–3030||||/ |662525
3030–4040||||/ ||773535
4040–5050||||/ ||||/ ||||/ ||||/ |21214545
5050–6060||||/ ||||/ ||||/ ||||/ |||23235555
6060–7070||||/ ||||/ ||||/ ||||19196565
7070–8080||||/ |667575
8080–9090||||/558585
9090–100100||||449595
Total100100

Loss of Information in Grouping

What grouping preserves and loses

  • Benefit: A frequency distribution condenses raw data and makes it easier to understand.
  • Limitation: Grouping records how many observations are in each class, but not their individual values.
  • Approximation in calculations: Statistical calculations use the class mark as a representative value for every observation in that class.
  • Example: The class 2020–3030 contains 25,25,20,22,25,2825, 25, 20, 22, 25, 28. Once grouped, it shows frequency 66 and class mark 2525, not those six individual values.
Raw Data vs Grouped Data
PointRaw dataGrouped data
Detail retainedIndividual observations remain visible.Only the class and its frequency are shown.
Example for class 2020–3030The observations are 25,25,20,22,25,2825, 25, 20, 22, 25, 28.It shows frequency 66 and class mark 2525, not the six individual values.
Use in calculationsCalculations can use the actual observations.Calculations use class marks, so information is lost.

How are inclusive class limits adjusted to remove a gap?

Answer: Find the gap between successive limits, divide it by 22, subtract the result from every lower limit, and add it to every upper limit.

Why does grouping data into a frequency distribution cause information loss?

Answer: The grouped table gives the number of observations in each class, but not their actual values; calculations then use the class mark as a substitute.

Quick recap

  • Adjust inclusive limits by splitting the gap equally between lower and upper limits.
  • Adjusted example: The gap between 899899 and 900900 is 11, so the correction is 0.50.5.
  • Class frequency is the number of observations in a class, counted conveniently using groups of five tallies.
  • Class mark is the midpoint of the class limits.
  • Grouping simplifies data but hides individual observations; calculations use class marks instead.
Lecture 6

Frequency distribution with unequal classes

Reference video · Lecture 6Frequency distribution with unequal classes

Why Use Unequal Class Intervals?

Definition

Unequal class intervals — A frequency distribution with unequal class intervals uses classes of different widths to represent the data more appropriately.

When they are useful

  • Concentration: In the example of 100 students' marks, classes 40–50, 50–60 and 60–70 contain 21, 23 and 19 students respectively.
  • Middle range: Together, these classes contain 63 students, or 63% of the total; observations are concentrated between 40 and 70.
  • Sparse classes: The remaining 37% of observations lie in the other classes, which are more sparsely populated.
  • Better representation: Narrower classes can make class marks closer to where observations cluster, so the class marks represent the data better.
Class mark
L+U2\frac{L+U}{2}

The midpoint of a class interval.

Unequal-class distribution of students' marks
ClassFrequencyClass mark
0–1015
10–20815
20–30625
30–40735
40–45942.5
45–501247.5
50–55752.5
55–601657.5
60–651062.5
65–70967.5
70–80675
80–90585
90–100495
Total100—

How the classes are adjusted

  • Split: Each of the original classes 40–50, 50–60 and 60–70 is divided into two classes of width 5.
  • Retain: The other classes—0–10, 10–20, 20–30, 30–40, 70–80, 80–90 and 90–100—keep their width of 10.
  • Result: The new class marks are closer to the observations in the densely populated classes than the old class marks.
Frequency curve: class marks are plotted on the X-axis and frequencies on the Y-axis.
Frequency curve: class marks are plotted on the X-axis and frequencies on the Y-axis.

Frequency Array

Definition

Frequency array — A classification of data for a discrete variable, showing the frequency corresponding to each value it takes.

Key points

  • Discrete values: A discrete variable takes separate values rather than intermediate fractional values between integers.
  • Frequency: Count the observations at each value and list the corresponding frequencies.
Household size frequency array
Household sizeNumber of households
15
215
325
435
510
65
73
82
Total100

Why can unequal class intervals be more suitable than equal intervals?

Answer: They allow narrower classes where observations are concentrated, making class marks more representative of the data in those groups.

Quick recap

  • Use unequal class intervals when they represent the distribution more appropriately.
  • The 40–70 range contains 63 of the 100 students in the example.
  • The three central classes are split into classes of width 5; the other classes retain width 10.
  • A class mark is the midpoint of its class interval.
  • A frequency array lists the frequency at each discrete value.
  • Household size is discrete; the example frequency array totals 100 households.
Lecture 7

Bivariate Frequency Distribution

Reference video · Lecture 7Bivariate Frequency Distribution

Meaning and Purpose

Definition

Bivariate frequency distribution — A frequency distribution that shows the frequencies of values or classes for two variables together.

How It Is Organised

  • Bivariate data arise when two types of information are collected from each element in a sample.
  • Rows and columns represent the classes of the two variables; each cell gives the frequency for the matching pair of classes.
  • Use: It summarises the joint distribution of two variables; such distributions are used in studying correlation.
Sales and Advertisement Expenditure of 20 Firms
Advertisement expenditure (thousand Rs) / Sales (lakh Rs)115–125125–135135–145145–155155–165165–175Total
62–6421————3
64–661—3———4
66–681121——5
68–70—2—2——4
70–72—11—114
Total45631120

Reading a Cell

  • Example: The cell at advertisement expenditure 64–66 thousand Rs and sales 135–145 lakh Rs has frequency 3.
  • Meaning: Three of the 20 firms fall in both of those class intervals.

Classification of Data

  • Raw data collected from primary or secondary sources are unclassified; classification organises the data for further statistical analysis.
  • Frequency distribution groups values into classes and records the corresponding class frequencies.
  • Further calculations in a frequency distribution use class marks rather than the original observations.
  • Good class formation places each class mark as close as possible to the value around which that class’s observations tend to concentrate.
Exclusive vs Inclusive Class Intervals
PointExclusive methodInclusive method
Class limitsOne limit—upper or lower—is excluded.Both upper and lower limits are included.
Key terms
Bivariate data
Data containing two variables recorded for each sample element.
Cell frequency
Number of observations belonging to the row and column classes of a cell.

Quick recap

  • A bivariate frequency distribution summarises two variables together.
  • Rows and columns classify the two variables; each cell records the frequency for a pair of classes.
  • In the example, three firms have sales of 135–145 lakh Rs and advertisement expenditure of 64–66 thousand Rs.
  • Classification organises raw data for statistical analysis.
  • Exclusive classes exclude one limit; inclusive classes include both limits.
  • Frequency-distribution calculations use class marks, which should represent where observations in each class tend to concentrate.

Economics — ALL CHAPTERS

1

Introduction

View

2

Theory of Consumer Behaviour

View

3

Production And Costs

View

4

The Theory Of The Firm Under Perfect Competition

View

5

Market Equilibrium

View

1

Introduction

View

2

Collection of Data

View

3

Organizing of Data

View

4

Presentation of Data

View

5

Measures of Central Tendency

View

6

Correlation

View

7

Index Numbers

View

8

Use of Statistical Tools

View