Comparing More Than Two Samples
In geography, we often wish to compare not just two groups but several. A common approach to this problem is to use one of the two-sample tests but to run it for all possible pairs. For example, you might be interested in whether different farming practices result in differences in soil properties and wish to compare four fields treated in different ways: we can call the fields A, B, C and D. You could now use a two-sample test, such as the independent samples Student’s t-test to make the following comparisons:
A-B A-C A-D B-C B-D C-D
The problem with this approach is that the probabilities are not the same as when you run a single test.