Testing for zero correlation
Studying this course? Keep your progress in one place.
Key facts
- Hypotheses use the population coefficient: (or ), never the sample value.
- is (two-tailed), or (one-tailed).
- For a two-tailed 5% test, use the one-tailed 2.5% column of the table.
- Compare (or in the right direction) with the critical value, then conclude in context.
- Not rejecting means insufficient evidence, not proof of no correlation.
Hypotheses
says there is no correlation in the population; says what you are testing for.
A sample or comes from sample data, but we want to know about the population, with coefficient (product moment) or (Spearman).
The null hypothesis is (or ). The alternative hypothesis is for any correlation, for positive, or for negative.
Hypotheses are about the population parameter, never the sample value.
Any correlation
- Two-tailed
Positive correlation
- One-tailed
Negative correlation
- One-tailed
A teacher tests whether revision time is positively correlated with marks. Which alternative hypothesis is correct?
Critical values
Find the row for and the column for the significance level, halving the level for a two-tailed test.
Tables give critical values for each sample size , for one-tailed tests at several levels.
For a two-tailed test at the 5% level, use the one-tailed 2.5% column. The critical region is the critical value for a two-tailed test, it for , and it for . The significance level is the probability of rejecting when it is true.
| Product moment | Spearman | |
|---|---|---|
| Sample size n | 10 | 8 |
| One-tailed 5% | 0.5494 | 0.6429 |
| Two-tailed 5% | 0.6319 | 0.7381 |
Product moment
- Sample size n:
- 10
- One-tailed 5%:
- 0.5494
- Two-tailed 5%:
- 0.6319
Spearman
- Sample size n:
- 8
- One-tailed 5%:
- 0.6429
- Two-tailed 5%:
- 0.7381
Product moment, , two-tailed test at 5%. Which critical value do you use?
Carrying out the test
State the hypotheses, find the critical value, compare, then conclude in context.
Follow the same four steps every time:
- State and .
- Find the critical value for and the significance level.
- Compare the sample coefficient with it.
- Write a conclusion in two parts: whether to reject , and what it means in context.
Worked example
, . Test for any correlation at the 5% level.
- 1
, (two-tailed).
- 2
The critical value is , so the critical region is .
- 3
, so is not in the critical region.
, , test for negative correlation at 5%. Is rejected?
Product moment or Spearman?
The product moment test needs bivariate normality; Spearman's only needs a monotonic relationship.
The product moment test requires data from a bivariate normal distribution. Formal checking is not required, but the scatter should look roughly elliptical.
The Spearman test makes no such assumption and only needs a monotonic relationship, so it suits ranked data and small samples.
The tests can disagree near a critical value: for , exceeds (reject ), but is below (do not reject).
| Product moment | Spearman | |
|---|---|---|
| Assumption | Bivariate normal data | No normality needed |
| Data | Elliptical scatter | Ranks or measured data |
| Detects | Linear association | Monotonic association |
Product moment
- Assumption:
- Bivariate normal data
- Data:
- Elliptical scatter
- Detects:
- Linear association
Spearman
- Assumption:
- No normality needed
- Data:
- Ranks or measured data
- Detects:
- Monotonic association
Which test makes no assumption of bivariate normality?
Try an exam question
A sample of 8 students gives a product moment correlation coefficient of between height and arm span. Test, at the 5% level, whether there is positive correlation in the population. The critical value is .
[4 marks]
- [1] and .
- [1]Critical value (one-tailed 5%, ).
- [1], so lies in the critical region.
- [1]Reject : there is evidence of positive correlation between height and arm span.
That's the notes covered.
Carry on to the next subtopic.
Try a question
Which pair of hypotheses is correct for this test?
1 mark, marked against the mark scheme
Which pair of hypotheses is correct for this test?
1 mark, marked against the mark scheme