Significance Testing A basic outline of the principles of significance testing follows below.  You will not be expected to carry out significance tests on your data, though if you are already familiar with the statistical techniques involved, it is probably a good idea to practice them, as they are an important part of psychological research at university level. When we carry out an experiment we are attempting to prove our hypothesis. The process of hypothesis testing involves: 1. Formulating an experimental hypothesis. This is a statement about how the independent variable will affect the dependent variable. For example, our hypothesis might be that a certain drug (independent variable) will alleviate depression (dependent variable).   2. The null hypothesis (abbreviated as H0). This states that our independent variable will not have the proposed effect on the dependent variable. And that any differences we find between the groups in our experiment will be purely due to chance. For example, we might find a group of depressed people split them randomly into two groups, one of which (the experimental group) does receive the drug and other of which (the control group) receives a dummy drug known as a ‘placebo’ to control for psychological effects.  If we later found that the experimental group was less depressed, the null hypothesis (H0) would assert that this was simply due to chance (i.e. when we randomly selected the subjects into the 2 groups, we just happened by chance to put all those who were going to get better anyway into the experimental group.