Correlation and Coefficient of Variation (CAT-Level)
Quantitative Aptitude › Statistics · Topic 24.5
Correlation measures how strongly two variables move together, and the Karl Pearson coefficient r ranges from -1 to +1. The coefficient of variation, standard deviation divided by the mean times 100, compares the relative spread of two data sets with different units or means.
5 min read · Quantitative Aptitude · Statistics
Quick Answer
Correlation measures how strongly two variables move together, and the Karl Pearson coefficient r ranges from -1 to +1. The coefficient of variation, standard deviation divided by the mean times 100, compares the relative spread of two data sets with different units or means.
At a Glance
- Range of r -1 to +1
- r = +1 Perfect positive
- r = -1 Perfect negative
- r = 0 No linear relation
- CV (SD / Mean) × 100
Where Does It Fit?
This topic builds on the mean and standard deviation of Measures of Central Tendency – Mean, Median and Mode and Measures of Dispersion – Range, Mean Deviation, Variance and Standard Deviation. The effect of scaling on these measures is in Effect on Mean, Median and Mode When a Constant Is Added to or Multiplied with Every Observation.
What Is the Correlation Coefficient?
In short: correlation shows the direction and strength of a straight-line relation between two variables x and y.
Karl Pearson coefficient
- r = Σ(x – x̄)(y – ȳ) / √[Σ(x – x̄)² × Σ(y – ȳ)²].
- r lies between -1 and +1.
- r is not changed by adding a constant to x or y, or by multiplying both by positive constants.
- Correlation does not prove cause and effect.
| Value of r | Meaning |
|---|---|
| +1 | Perfect positive: y rises exactly with x |
| Close to +1 | Strong positive |
| 0 | No linear relation |
| Close to -1 | Strong negative |
| -1 | Perfect negative: y falls exactly as x rises |
How Do You Calculate r Step by Step?
In short: find the means, then the deviations, then three sums.
| x | y | x – 3 | y – 4 | Product | (x – 3)² | (y – 4)² |
|---|---|---|---|---|---|---|
| 1 | 2 | -2 | -2 | 4 | 4 | 4 |
| 2 | 3 | -1 | -1 | 1 | 1 | 1 |
| 3 | 5 | 0 | 1 | 0 | 0 | 1 |
| 4 | 4 | 1 | 0 | 0 | 1 | 0 |
| 5 | 6 | 2 | 2 | 4 | 4 | 4 |
| Sum | 9 | 10 | 10 |
So r = 9/√(10 × 10) = 0.9, a strong positive correlation.
What Is the Coefficient of Variation?
In short: the coefficient of variation expresses the standard deviation as a percentage of the mean, so spreads of different data sets can be compared.
Rule
- CV = (standard deviation / mean) × 100.
- A smaller CV means more consistent data.
- CV is unchanged when every value is multiplied by the same constant.
The standard deviation comes from Measures of Dispersion – Range, Mean Deviation, Variance and Standard Deviation.
Solved Examples
Example 1
Question: Find r for x = 1, 2, 3, 4, 5 and y = 2, 3, 5, 4, 6.
- Means: x = 3 and y = 4.
- Σ(x – 3)(y – 4) = 9, Σ(x – 3)² = 10 and Σ(y – 4)² = 10.
- r = 9/√(10 × 10) = 9/10.
Answer: r = 0.9, a strong positive correlation.
Example 2
Question: Series A has mean 50 and SD 5. Series B has mean 80 and SD 6. Which is more consistent?
- CV of A = 5/50 × 100 = 10%.
- CV of B = 6/80 × 100 = 7.5%.
Answer: B is more consistent because its CV is smaller.
Example 3
Question: If y = 2x, find r.
- y rises exactly in proportion to x with a positive factor.
Answer: r = +1, a perfect positive correlation.
Example 4
Question: If y = -3x + 1, find r.
- y falls exactly as x rises, because the factor -3 is negative.
Answer: r = -1, a perfect negative correlation.
Example 5
Question: A data set has mean 40 and variance 64. Find the coefficient of variation.
- SD = √64 = 8.
- CV = 8/40 × 100.
Answer: The coefficient of variation is 20%.
Shortcuts and Tricks
- If y is an exact straight-line function of x, r is +1 or -1 depending on the sign of the slope.
- Use deviations from the means to keep numbers small.
- A smaller CV always means more consistent data, even if the mean is larger.
- r does not change if both variables are rescaled by positive numbers.
- Always compute SD from variance before finding CV.
Common Mistakes
- Concluding that correlation proves cause and effect.
- Giving r a value outside -1 to +1.
- Comparing standard deviations directly instead of CVs for data with different means.
- Forgetting to multiply by 100 in the CV.
- Using variance instead of the standard deviation in the CV.
Practice Questions
- If r = -1, describe the relation.
- Find the CV for mean 25 and SD 5.
- Series with CV 12% and CV 9%: which is more consistent?
- If y = 5x + 2, find r.
- If x and y have no linear relation, what is r?
- Find the CV for mean 100 and variance 100.
Answers: 1) perfect negative linear relation; 2) 20%; 3) the one with 9%; 4) +1; 5) 0; 6) 10%.
Why Is This Topic Important?
- Interpretation They help judge relationships and consistency in data.
- Exam use CAT asks about r properties and CV comparison.
- Link They extend Measures of Dispersion – Range, Mean Deviation, Variance and Standard Deviation.
What Comes Next?
The next topic is Combined Mean and Combined Standard Deviation of Two or More Groups, which combines means and standard deviations of two or more groups.
Key Terms and Formulas
- Correlation A measure of the relation between two variables
- Karl Pearson r The standard coefficient of linear correlation
- Coefficient of variation SD divided by mean, times 100
- Consistency Low relative spread
Related Topics
- Histogram, Frequency Polygon and Ogive Construction and Interpretation
- Combined Mean and Combined Standard Deviation of Two or More Groups
- Measures of Central Tendency – Mean, Median and Mode
- Measures of Dispersion – Range, Mean Deviation, Variance and Standard Deviation
Exam Corner
Points to Remember
- r lies between -1 and +1.
- r = +1 or -1 means exact straight-line relation.
- CV = SD / mean × 100.
- Smaller CV means more consistent.
Do Not Confuse With
- Correlation vs causation A strong r does not show cause and effect.
- SD vs CV The CV is relative; the SD is absolute.
- Positive vs negative correlation Positive means both rise together; negative means one rises as the other falls.
Memory Hook
Plus one rises together, minus one moves apart; smaller CV means steadier.
GS Relevance
Frequently Asked Questions
What is the correlation coefficient?
The correlation coefficient measures the strength and direction of the linear relation between two variables. The Karl Pearson coefficient r lies between minus 1 and plus 1, with plus 1 meaning a perfect positive relation, minus 1 a perfect negative relation, and 0 no linear relation.
What is the range of the correlation coefficient?
The correlation coefficient r always lies between minus 1 and plus 1. Values near plus 1 show a strong positive relation, values near minus 1 a strong negative relation, and values near 0 show little linear relation between the two variables.
What is the coefficient of variation?
The coefficient of variation is the standard deviation divided by the mean, multiplied by 100, so it expresses spread as a percentage of the mean. It allows data sets with different means or units to be compared, and a smaller value means the data are more consistent.
How do you compare consistency of two series?
Calculate the coefficient of variation for each series and compare them. A series with mean 50 and standard deviation 5 has a CV of 10 per cent, while one with mean 80 and standard deviation 6 has 7.5 per cent, so the second is more consistent.
Does correlation prove causation?
No, a strong correlation shows only that two variables move together in a straight-line pattern. It does not prove that one causes the other, because a third factor or chance may explain the relation, so further evidence is needed to claim cause.
PYQ Practice — Statement Analysis
1 The correlation coefficient can be 1.5.
It lies between -1 and +1.
2 The CV equals standard deviation divided by mean times 100.
It is a relative measure of spread.
3 If y = 2x, then r = +1.
The relation is exactly linear with a positive slope.
4 A series with a smaller CV is more consistent.
It has less relative spread.
Related Topics
Browse the full Quantitative Aptitude index