Class 11 โ Statistics for Economics (Complete Notes)
Point-wise notes, formula boxes, diagram descriptions, distinguish-between tables, and board exam tips โ covering all 6 topics of Statistics for Economics, CBSE Class 11.
1. Introduction to Statistics in Economics
- Statistics is the science of collecting, organising, presenting, analysing and interpreting numerical data to draw meaningful conclusions.
- In Economics, statistics helps convert real-world economic problems into measurable, comparable data โ without it, economic theories would remain purely abstract.
- Economics + Statistics = Econometrics โ the branch that uses statistical methods to test economic theories using real data.
- Statistics has both singular sense (the science/method itself) and plural sense (numerical data/facts) โ a favourite 1-mark definition question.
Statistics (plural sense): numerical facts systematically collected. Statistics (singular sense): the science of methods used to collect, analyse and interpret numerical data.
๐ Distinguish Between: Micro Statistics vs Macro Statistics (not to be confused with Microeconomics/Macroeconomics)
| Basis | Descriptive Statistics | Inferential Statistics |
|---|---|---|
| Meaning | Organises and summarises data | Draws conclusions/generalisations from a sample about the population |
| Scope | Limited to given data only | Extends beyond given data using probability |
Board exams love asking 'statistics is singular or plural' as a 1-mark trick โ always mention BOTH senses in your answer for full marks.
Don't confuse Statistics (the subject) with 'statistics' (data) โ examiners specifically test this dual meaning.
2. Collection, Organisation and Presentation of Data
- Data can be Primary (collected firsthand by the investigator โ surveys, interviews, questionnaires) or Secondary (already collected by someone else โ government reports, NSSO, Census).
- Methods of collecting primary data: Direct Personal Investigation, Indirect Oral Investigation, Information from Local Correspondents, Mailed Questionnaire, Schedules filled by Investigators.
- Sources of secondary data: Published (government publications, journals, newspapers) and Unpublished (records, diaries, unpublished dissertations).
- Sampling methods: Random Sampling (every unit has an equal chance โ includes Lottery method, use of random number tables) and Non-Random Sampling (Judgement, Quota, Convenience sampling).
- Organisation of data uses a frequency distribution โ grouping raw data into class intervals, either exclusive (upper limit excluded) or inclusive (upper limit included).
- Data presentation methods: Textual (paragraph form), Tabular (rows and columns), and Diagrammatic (bar diagrams, pie charts, histograms, frequency polygons, ogives).
Census method: every unit of the population is studied. Sample method: only a representative subset of the population is studied and results are generalised.
๐งฎ Formulas
๐ How to draw a Histogram (frequently asked construction question)
- Take class intervals on the X-axis and frequency on the Y-axis.
- Ensure class intervals are continuous (convert inclusive to exclusive if needed using the correction factor).
- Draw adjacent rectangles for each class โ width equal to class interval, height equal to frequency, with NO gaps between bars (unlike a bar diagram).
- For unequal class intervals, adjust the height using frequency density = frequency/class width, not raw frequency.
๐ Distinguish Between: Census Method vs Sample Method
| Basis | Census Method | Sample Method |
|---|---|---|
| Coverage | Entire population studied | Only a representative sample studied |
| Cost & Time | High cost, more time | Low cost, less time |
| Accuracy | More accurate (no sampling error) | Possible sampling error, but often more practical |
For 'inclusive to exclusive series' conversion questions, remember the correction factor = (lower limit of next class โ upper limit of current class)/2 โ subtract it from lower limits and add it to upper limits.
Students often draw a histogram with GAPS between bars like a bar diagram โ a histogram must have NO gaps since it represents continuous data, this is a very frequently deducted mark.
3. Measures of Central Tendency (Mean, Median, Mode)
- A measure of central tendency gives a SINGLE representative value that describes the entire data set.
- Arithmetic Mean is the most commonly used measure โ sum of all observations divided by the number of observations.
- Median is the middle value when data is arranged in ascending/descending order โ it divides the data into two equal halves, and is not affected by extreme values (outliers).
- Mode is the value that occurs most frequently in the data set โ useful for categorical/qualitative-style data like 'most common shoe size sold'.
- Relationship (empirical formula, for moderately skewed distributions): Mode = 3 Median โ 2 Mean.
Arithmetic Mean is the sum of all values divided by the total number of values. It is the most widely used but is heavily affected by extreme (outlier) values.
๐งฎ Formulas
๐ Distinguish Between: Mean vs Median vs Mode
| Basis | Mean | Median | Mode |
|---|---|---|---|
| Definition | Average of all values | Middle value of arranged data | Most frequently occurring value |
| Affected by extreme values? | Yes, heavily | No, unaffected | No, unaffected |
| Best used when | Data has no extreme outliers | Data is skewed/has outliers | Data is categorical or has a clear peak |
For 'which measure is most appropriate' HOTS questions, always check whether the data has extreme values โ if yes, prefer Median or Mode over Mean, since Mean gets distorted by outliers.
In the assumed mean method, students often forget that 'd = X โ A' can be NEGATIVE for values below the assumed mean โ dropping the negative sign in ฮฃd is the most common calculation error in this topic.
4. Measures of Dispersion
- Dispersion measures HOW SPREAD OUT the data is around the central value โ two data sets can have the same mean but very different spreads.
- Range is the simplest measure: difference between the highest and lowest values โ easy to calculate but ignores all values in between.
- Quartile Deviation uses only the middle 50% of data (between Q1 and Q3), making it less sensitive to extreme values than Range.
- Mean Deviation is the average of absolute deviations from the mean (or median) โ uses ALL values but ignores the sign of deviation.
- Standard Deviation is the most scientifically robust measure โ the square root of the average of squared deviations from the mean; it's the only measure used further in correlation and other advanced statistical tools.
- Coefficient of Variation (CV) is used to COMPARE the variability of two different data sets (especially with different units or means) โ lower CV means more consistency.
Standard Deviation (ฯ) is the positive square root of the arithmetic mean of the squares of deviations of observations from their mean. It is always โฅ 0, and a higher value means more spread/inconsistency in the data.
๐งฎ Formulas
๐ Distinguish Between: Absolute Measures vs Relative Measures of Dispersion
| Basis | Absolute Measures | Relative Measures |
|---|---|---|
| Meaning | Expressed in the same unit as the data (Range, QD, MD, SD) | Expressed as a ratio/percentage, unit-free (Coefficient of Variation) |
| Use case | Comparing spread within the SAME data set | Comparing spread ACROSS two different data sets/units |
Whenever a question asks to compare 'consistency' or 'stability' between two data sets (like two students' marks, or two companies' profits), always calculate and compare the Coefficient of Variation โ LOWER CV means MORE consistent/stable.
Standard Deviation is never reported as negative โ since it's a square root of squared values, forgetting to take only the POSITIVE root, or reporting variance (ฯยฒ) instead of SD (ฯ) when the question specifically asks for SD, are both common errors.
5. Correlation
- Correlation measures the DEGREE and DIRECTION of the linear relationship between two variables (like income and expenditure).
- Positive correlation: both variables move in the SAME direction (e.g., more study hours โ higher marks).
- Negative correlation: variables move in OPPOSITE directions (e.g., price of a good โ โ demand for it โ).
- Correlation coefficient (r) always lies between -1 and +1 โ r=+1 is perfect positive correlation, r=-1 is perfect negative correlation, r=0 means no linear correlation.
- Karl Pearson's Coefficient of Correlation is the most precise and widely used method โ measures the degree of linear relationship.
- Spearman's Rank Correlation is used when data is in RANKS/ordinal form (like ranking of beauty, honesty) rather than exact numerical values.
Correlation is a statistical technique that measures and analyses the degree and direction of relationship between two variables, without implying that one variable CAUSES the other (correlation โ causation, a very important distinction).
๐งฎ Formulas
๐ Scatter Diagram โ how to describe it in your answer
- Plot one variable (like Income) on the X-axis and the other (like Expenditure) on the Y-axis.
- Each pair of values is plotted as a single dot/point on the graph.
- If dots move upward from left to right in a rough line โ positive correlation.
- If dots move downward from left to right โ negative correlation.
- If dots are scattered with no visible pattern โ little or no correlation.
๐ Distinguish Between: Karl Pearson's Method vs Spearman's Rank Method
| Basis | Karl Pearson's Method | Spearman's Rank Method |
|---|---|---|
| Data type | Actual numerical values | Ranks/ordinal data |
| Use case | When exact quantitative data is available | When data is qualitative or given as ranks (e.g., judges' rankings) |
| Precision | More precise/mathematically exact | Less precise, but useful when exact values are unavailable |
Whenever a question mentions 'correlation โ causation,' always give the classic example โ ice cream sales and drowning deaths are positively correlated (both rise in summer), but ice cream doesn't CAUSE drowning; a third factor (hot weather) causes both.
Assuming a high correlation coefficient (like r=0.9) automatically means one variable CAUSES the other โ correlation only tells you variables move together, never that one is the reason for the other's movement.
6. Index Numbers
- An Index Number is a statistical device that measures the RELATIVE change in a variable (or group of variables) over time, comparing a 'current' period to a fixed 'base' period.
- The base period is always assigned a value of 100 โ all other periods are expressed relative to this base.
- Wholesale Price Index (WPI) measures price changes at the wholesale/producer level; used to track inflation and now largely replaced in policy by other measures.
- Consumer Price Index (CPI) measures price changes for a fixed 'basket' of goods and services consumed by a typical household โ directly relevant to cost of living and used for inflation targeting.
- Index of Industrial Production (IIP) measures the change in the volume/quantity of industrial production over time.
Index Number is a specialised statistical measure used to compare the level of a phenomenon (price, quantity, or value) at a given time relative to its level at some other (base) time.
๐งฎ Formulas
๐ Distinguish Between: Laspeyres' Index vs Paasche's Index
| Basis | Laspeyres' Index | Paasche's Index |
|---|---|---|
| Weights used | Base year quantities (q0) | Current year quantities (q1) |
| Tendency | Tends to overestimate price rise | Tends to underestimate price rise |
WPI vs CPI is one of the most frequently tested 'distinguish between' questions โ remember WPI doesn't include SERVICES (only goods, at the wholesale level), while CPI includes both goods AND services relevant to final consumers.
Confusing which quantities (base year vs current year) are used as WEIGHTS in Laspeyres' vs Paasche's index โ this single mix-up flips the entire formula and gives a wrong index value.