P-value

A p value is a value calculated from a research study, which is intended to show whether an outcome is likely to have occurred by chance, when taking into consideration a number of other factors. P values are not actually defined as a probability. P-hacking is the manipulation of research data to produce a clinically significant result for the calculated p value; meaning manipulating research results in order to achieve p < 0.05 rather than publishing a null result.

Articles and blogs

 * 2010, Odds are it's wrong - Article


 * 2016, The ASA's Statement on p-Values: Context, Process, and Purpose - Editorial

Notable studies

 * 2012, A peculiar prevalence of p values just below .05 (Abstract)


 * 2013, The life of p: “Just significant” results are on the rise (Abstract)


 * 2015, What p-Hacking really looks like: A comment on Masicampo & Lalande (2012) (Full text)


 * 2015, Blinded by the Light: How a Focus on Statistical “Significance” May Cause p-Value Misreporting and an Excess of p-Values Just Below .05 in Communication Science (Full text)


 * 2016, Degrees of Freedom in Planning, Running, Analyzing, and Reporting Psychological Studies: A Checklist to Avoid p-Hacking (Full text)


 * 2016, Why are p-Values Controversial? (Full text)