P-value

A p-value is the probability, calculated under a stated null hypothesis, of obtaining a result at least as extreme as the one actually observed; a small p-value is conventionally read as evidence against the null hypothesis. Ronald Fisher popularized the concept and the term in his 1925 book Statistical Methods for Research Workers, proposing a threshold of 0.05 as a conventional, though not absolute, mark of statistical significance. It remains the most widely reported statistic in applied research, and also the most widely debated, with decades of methodological criticism aimed at its frequent misuse as a measure of the size or importance of an effect rather than of how surprising the data are under the null hypothesis.