An introduction to statistics, significance testing and the P value

Abstract P values come from statistical tests used for testing the null hypothesis (Ho) which states that there is no difference between treatment outcomes. If the P value is less than 0.05 there is a less than 5% probability that the difference is due to chance if the Ho is true. Given this low chance, the Ho is rejected and the alternate hypothesis (Ha) that there is a difference between treatment outcomes is accepted. In hypothesis testing, there is a risk of wrongly rejecting a true Ho (α error) and wrongly not rejecting a false Ho (β error). The t- and Chi-squared tests are the two most commonly used statistical tests for clinical hypothesis testing. Statistical significance derived from such tests, needs to be clinically significant for the finding to be relevant. P values need to be interpreted with the knowledge of several statistical concepts including sample size, multiple comparisons and the validity of the study.