A two-sample t-test checks whether the means of two independent groups are different. Here is the method we use with students, using test scores from two teaching methods.
The five steps
- State the hypotheses. H0: the means are equal. H1: the means differ.
- Check the assumptions. Independent samples, roughly normal data, similar variances.
- Calculate t. Divide the difference in means by the standard error of the difference.
- Find the p-value. Use the t distribution with the right degrees of freedom.
- Conclude in words. Reject H0 if p is below your significance level, and say what that means for the groups.
The last step is where most marks are lost. Always finish with a sentence in plain English, not just “reject H0”.
