Testing for zero correlation
Studying this course? Keep your progress in one place.
Key facts
- A sample coefficient can be non-zero by chance, so test whether the population coefficient is non-zero.
- . The tail of comes from the wording of the question.
- Compare (or ) with the critical value from the table, not with the significance level.
- Not rejecting never proves there is no correlation.
Why test a correlation
A sample can show a non-zero value by chance, even when the population has no correlation.
A sample correlation coefficient comes from only some of the population. A hypothesis test decides whether the sample value is far enough from 0 to be convincing evidence of correlation in the population.
The population correlation coefficient is (product moment) or (Spearman). Hypotheses are about the population parameter, never about the sample correlation coefficient or .
- 1
Population
Correlation coefficient ρ, usually unknown
- 2
Sample taken
Gives r or rₛ from the data
- 3
Hypothesis test
Is r far enough from 0 to be evidence about ρ?
Sample
- or
- Calculated from the data
- Varies from sample to sample
Population
- or
- Fixed, usually unknown
- What the hypotheses are about
Which is a correct null hypothesis?
Hypotheses and tails
The direction comes from the wording of the question, not from the sign of the sample value.
(no correlation). For a two-tailed test, , when the question asks whether there is any correlation. For a one-tailed test, or , when the question states a direction in advance.
Use the same pattern for Spearman's, with .
Two-tailed
- "any correlation"
One-tailed positive
- "positive correlation"
One-tailed negative
- "negative correlation"
A researcher asks whether there is a positive correlation between hours revised and mark. What is ?
The product moment test
Use random pairs from a bivariate Normal distribution; compare with the critical value for .
Use this test when the data are random pairs from a bivariate Normal distribution, so the relationship is linear. Find , find the critical value for and the significance level from the tables, and compare.
Two-tailed: reject if the critical value. One-tailed positive: reject if it. One-tailed negative: reject if it.
Worked example
, . Test for correlation at the level (two-tailed). The critical value is .
- 1
, .
- 2
Compare: .
- 3
The value is not in the critical region, so do not reject .
One-tailed negative test, critical value . Sample . What is the decision?
Spearman's test
Rank the data, find , and compare with the critical value for .
Use this test when the data are ranks, when the relationship is monotonic but not necessarily linear, or when the data are not bivariate Normal. Rank the data, find , and compare with the tabulated critical value, using the same rules.
For the critical values are (one-tailed) and (two-tailed). For they are and .
- One-tailed
- Two-tailed
| Product moment test | Spearman's test | |
|---|---|---|
| Use when | Linear relationship | Ranks, or monotonic relationship |
| Statistic | r | r_s |
| Assumption | Bivariate Normal | None about the distribution |
Product moment test
- Use when:
- Linear relationship
- Statistic:
- r
- Assumption:
- Bivariate Normal
Spearman's test
- Use when:
- Ranks, or monotonic relationship
- Statistic:
- r_s
- Assumption:
- None about the distribution
Worked example
and . Test at the level (a) for positive correlation, (b) for any correlation.
- 1
.
- 2
(a) . Critical value and , so reject .
- 3
(b) . Critical value and , so do not reject .
Which test should you use for data that are ranks from two judges?
Writing the conclusion
Say "sufficient" or "insufficient evidence of correlation", in context.
If the sample value is in the critical region, reject : "there is sufficient evidence of (positive/negative) correlation between ... and ...". If not, do not reject : "there is insufficient evidence of correlation". Never say this proves there is no correlation: the sample may be too small to detect one.
A significant result shows evidence of correlation, not that one variable causes the other.
- 1
Compare r with the critical value
Is it in the critical region?
- 2
If yes, reject H₀
Sufficient evidence of correlation
- 3
If no, do not reject H₀
Insufficient evidence of correlation
- 4
Write it in context
Correlation does not show cause
In the critical region
- Reject
- Sufficient evidence of correlation
Not in the critical region
- Do not reject
- Insufficient evidence of correlation
A test does not reject . Which conclusion is correct?
Try an exam question
A researcher claims that there is negative correlation between the price of a product and the number sold. For shops the product moment correlation coefficient is . Test the claim at the level. The one-tailed critical value for is .
[4 marks]
- [1], .
- [1]The critical value is .
- [1], so is in the critical region: reject .
- [1]There is sufficient evidence of negative correlation between price and number sold.
That's the notes covered.
Carry on to the next subtopic.
Try a question
Which pair of hypotheses should the teacher use, where is the population product moment correlation coefficient?
1 mark, marked against the mark scheme
Which pair of hypotheses should the teacher use, where is the population product moment correlation coefficient?
1 mark, marked against the mark scheme