Use of Statistical Tools
This chapter demonstrates how the statistical tools learned in previous chapters can be applied to real economic data. It integrates data collection, organisation, presentation, and analysis to investigate economic questions.
Purpose and Approach
- Statistical tools are used to:
- Convert raw economic data into meaningful information
- Identify patterns and trends in economic variables
- Draw conclusions and support economic decision-making
- 1.The typical statistical investigation follows these steps:
- 2.Identify the economic problem or question
- 3.Collect relevant data (primary or secondary)
- 4.Organise data into frequency distributions or tables
- 5.Present data through graphs and diagrams
- 6.Apply measures of central tendency, correlation, or index numbers
- 7.Interpret results and draw conclusions
Real-Life Application: Comparison of Two Villages
- A common Class 11 project involves comparing economic conditions (income, expenditure, savings) between two groups — for instance, two villages or two income groups. Statistical tools applied include:
- Frequency distributions and cumulative frequency tables
- Histograms, frequency polygons, and ogives
- Mean, median, and mode for each group
- Measures of dispersion (range, mean deviation) to compare variability
- Correlation between income and expenditure
Measures of Dispersion (Quick Review for Application)
Range: Largest value - Smallest value. Simple but affected by extremes.
Mean Deviation (MD): Average of absolute deviations from mean or median.
MD from Mean = Sum|X - X-bar| / N
Standard Deviation (SD): Most important measure of dispersion.
SD = √(Sum(X - X-bar)2 / N)
Or: SD = √(Sum(X2)/N - (Sum(X)/N)2)
Coefficient of Variation (CV): (SD / Mean) × 100
Used to compare variability between two datasets with different units or magnitudes.
Lorenz Curve
- A Lorenz Curve is a graphical representation of income inequality. It plots cumulative percentage of income against cumulative percentage of the population.
- The line of equal distribution is a diagonal line (45 degrees) showing perfect equality.
- The greater the bow of the Lorenz curve from the diagonal, the greater the inequality.
- The Gini Coefficient measures the area between the Lorenz curve and the line of equality.
Interpreting Statistical Results
Two villages are compared. Village A has mean income Rs 8,000 and SD Rs 1,000. Village B has mean income Rs 8,000 and SD Rs 3,000.
Both villages have the same mean income. However, Village B has much higher variability — incomes are more spread out, suggesting greater inequality.
CV for Village A = (1000/8000) × 100 = 12.5%. CV for Village B = (3000/8000) × 100 = 37.5%. Village B is relatively more variable (unequal).
A scatter diagram of income vs. food expenditure for 20 households shows a rising pattern. Calculate r and find: r = +0.85. Interpretation: High positive correlation — as income rises, food expenditure rises too.
A student compares monthly incomes of 30 workers using a frequency polygon. The polygon for Factory A is more peaked (less spread) than Factory B. This visually confirms Factory A has less variability in wages.
Constructing an Ogive for cumulative data:
Given: Classes 0-1000, 1000-2000, 2000-3000 with frequencies 5, 12, 8. Cumulative frequencies: 5, 17, 25.
Plot (1000, 5), (2000, 17), (3000, 25). The point where cumulative frequency = N/2 = 12.5 on the y-axis gives the median on the x-axis.
Using index numbers in the project: A student finds CPI rose from 100 to 140 over 5 years. This represents a 40% rise in prices — real income fell for workers whose nominal wages rose by less than 40%.
Crop yield comparison: District X yields (40, 42, 38, 41, 39) have MD = 1.12 kg. District Y yields (20, 50, 35, 55, 40) have MD = 11 kg. District X is far more stable.
Common mistakes
Common mistakes
Presenting data without interpretation. Statistics is not just about computing — the conclusions drawn from the numbers are equally important. Also, students often forget to state the source of secondary data or the base period of index numbers used in their projects.
Summary
Statistical tools work together to investigate economic problems. A complete analysis includes data collection, tabular and graphical presentation, measures of central tendency and dispersion, correlation, and index numbers. The Lorenz Curve visualises income inequality. The Coefficient of Variation compares relative variability across datasets. Statistical findings must always be interpreted in an economic context.