2. Appraising the relevance of results

2.3 The eight steps

7. What are the results?

The p-value

The reviewer should demythify the well-known p-value. The p-value is the probability of obtaining a test statistic, determined from randomly collected data, that is greater or equal to what has actually been observed. The accepted risk of acknowledging that there is a difference between the two groups, when there is actually none, is called the level of significance.

A significance level de 5 % means that there is a risk of 5 chances out of 100 that finding a difference is an error. Significance levels of 5 % are 1 % are usually chosen, which means that there are respectively 5 chances or 1 chance out of 100 that the observed difference has occurred strictly due to chance and not due to the factor being studied.