Range is the simplest measure of dispersion—the difference between the highest and lowest values in a dataset.
## Core concept
Range measures how spread out data is by finding the gap between maximum and minimum observations. It's quick to calculate but uses only two values, ignoring all data points in between. In CA Foundation statistics, range forms the foundation for understanding dispersion before moving to more sophisticated measures like variance and standard deviation.
Formula: - Range = Maximum value − Minimum value - Coefficient of Range = (Max − Min) / (Max + Min)
The coefficient of range is a relative measure (unitless), useful for comparing spread across datasets with different scales or units.
## Why learn range?
- Foundation for understanding variability and dispersion
- Quick assessment tool in business decisions (e.g., stock price fluctuation, exam score spread)
- Precursor to quartile deviation, mean deviation, and standard deviation
- Appears in logical reasoning and data interpretation questions
## Step-by-step calculation
- Identify the maximum value in the dataset
- Identify the minimum value in the dataset
- Subtract: Range = Max − Min
- For coefficient of range, divide by (Max + Min)
## Worked example
Data: Daily sales (in ₹'000): 45, 52, 38, 61, 49, 55, 42
- Maximum = 61
- Minimum = 38
- Range = 61 − 38 = 23 (₹'000)
- Coefficient of Range = (61 − 38) / (61 + 38) = 23 / 99 = 0.232
## Common exam applications
- Grouped data: Range = Upper limit of highest class − Lower limit of lowest class
- Comparative analysis: "Which dataset has greater variability?" (student marks vs. product weights)
- Quality control: Monitoring production consistency; narrow range indicates uniformity
- Financial analysis: Share price range to assess volatility risk
## Common mistakes
| Mistake | Correct approach | |---------|---| | Using the range of class intervals instead of actual data | Always use actual max and min values from observations | | Forgetting coefficient of range is dimensionless | Use coefficient when comparing datasets with different units | | Confusing range with interquartile range (IQR) | Range uses all extreme values; IQR uses quartiles (Q₃ − Q₁) | | Calculating range on ungrouped vs. grouped data inconsistently | For grouped: use class boundaries; for ungrouped: use raw values |
## Limitations
- Unstable: Single outlier distorts the entire measure
- Ignores internal distribution: Two datasets with same range can have very different patterns
- Not suitable for inference: Range of sample may differ significantly from population range
- Superseded by mean deviation, variance, and standard deviation in rigorous analysis
## Relation to other dispersion measures
Range is the starting point in a hierarchy of dispersion measures. It's cruder than quartile deviation (which uses middle 50% of data) and far simpler than standard deviation (which weighs each observation). In exam questions progressing from "simple" to "advanced," expect range first, then QD, then MD, then SD or CV.
Key takeaway for revision: Range answers "how far apart are the extreme values?" It's essential for quick decisions but must be supplemented with other measures for complete dispersion analysis.