## When to use it:

You should use a Regression when:

- You are looking for a relationship between two samples, one sample from each of a dependent variable and an independent variable.
- You believe the relationship might be modelled by a straight line.
- Where data in the samples are measured at scale level.
- The data are related.

Do **not** use this test when:

- You want to compare frequency distributions.
- You cannot identify a dependent variable and an independent variable.
- The data do not fulfil parametric criteria.