Unit 11: Statistics
1. Measures of Dispersion
While Measures of Central Tendency (Mean, Median, Mode) tell us about the center of data, Measures of Dispersion tell us how spread out or scattered the data points are from that center.
- Range: The difference between the maximum and minimum values in a dataset.
Range = Max Value - Min Value
- Need for Dispersion: Two datasets can have the same mean but look completely different. For example, {10, 10, 10} and {0, 10, 20} both have a mean of 10, but the second set is more "dispersed."
2. Mean Deviation
Mean Deviation (M.D.) is the arithmetic mean of the absolute differences between each data point and a central value (usually the Mean or Median).
For Ungrouped Data (about Mean x̄):
M.D.(x̄) = (∑ |xi - x̄|) / (n)
For Grouped Data:
M.D.(x̄) = (∑ fi |xi - x̄|) / (N), where N = ∑ fi
3. Variance and Standard Deviation
Variance (σ2) is the average of the squared deviations from the mean. Standard Deviation (σ) is the positive square root of the variance. It is the most widely used measure of dispersion because it is in the same units as the data.
Formula for Ungrouped Data:
Variance (σ2) = (∑ (xi - x̄)2) / (n)
Standard Deviation (σ) = √(σ2)
Formula for Grouped Data:
σ = √((∑ fi(xi - x))2) / (N)̄
4. Analysis of Frequency Distributions
When comparing two frequency distributions with the same mean, the one with the larger Standard Deviation is considered more variable or less stable.
Coefficient of Variation (C.V.):
To compare the variability of two series with different means or different units, we use the Coefficient of Variation.
C.V. = (σ) / (x̄) × 100
The series with a higher C.V. is more variable/less consistent.
5. Exam Focus Enhancements
Exam Tips
- Absolute Value: In Mean Deviation, always use |xi - x̄|. This means if the difference is negative, you treat it as positive.
- Short-cut Method: For large numbers in Variance, use the assumed mean method (di = xi - A) to simplify your table calculations.
- Units: Remember that Variance is in "units squared," while Standard Deviation is in the same units as the original data.
Common Mistakes
- Negative Deviation: Forgetting to square the deviations or take absolute values. Summing raw deviations (xi - x̄) will always equal zero.
- n vs n-1: In introductory courses, we usually divide by n. In some advanced contexts, n-1 is used for samples. Stick to n unless specified by your examiner.
- Frequency Check: In grouped data, always ensure you multiply the squared deviation by the frequency fi before summing.
Frequently Asked Questions
Q: Why do we square the deviations in Variance?
A: Squaring ensures all deviations are positive (so they don't cancel out) and gives more weight to larger outliers.
Q: What is the difference between Mean Deviation and Standard Deviation?
A: M.D. uses absolute values, while S.D. uses squares. S.D. is mathematically more convenient for further statistical analysis.