Interactive resources for schools

Select an age range to seek interactive content for...

Choosing a statistical test

There are many different statistical tests and functions that are used in research, all of which serve a slightly different purpose. Here we will focus on three commonly used statistical tests, the Student’s t-test, Spearman’s rank correlation coefficient, and the chi-squared test. Each test will be covered in the upcoming pages, for now we will focus purely on how to choose the correct statistical test for the specific data set you have.

The Student’s t-test is used when you want to compare the means of two data sets to see if there is a difference between them. For example, whether the height of a certain species of plant is different in one area compared to another.

The Spearman’s rank correlation coefficient (or simply correlation coefficient) is utilised when wanting to investigate the relationship between two variables. For example, looking at the correlation of people’s weight and their resting heart rate. This sort of information is often plotted as a scatter graph.

The chi-squared test is used on frequency data, where we know the ‘expected’ frequency outcome. For example, we may expect the number of red, blue and yellow cars to be the same on any given street, and the chi-squared test allows us to compare this prediction with our observations.

Exam style questions

1.