It is interesting that if a two-side test had been made in the example above (for which the critical value for t5=2.57) the null hypothesis would not have been rejected! This apparently contradictory result is explained by the fact that the decision on whether to use a one- sided or two-sided test depends on the degree of prior knowledge, in this case a suspicion or expectation of positive bias. It is obviously essential that the decision on using a one- sided or two-sided test should be made before the experiment has been done, and not with hindsight, when the results might prejudice the choice. In general, two-sided tests are much more commonly used than one-sided ones and the relatively rare circumstances in which one-sided tests are necessary are easily identified.