- p -value The probability, when the null hypothesis is true, of obtaining a sample result that is at least as unlikely as what is observed. It is often called statistical significance. The p -value is a statement about the null hypothesis. A numerically small value indicates a rejection of the null hypothesis. The convention is to use p = 0.05 as the borderline. Hence if a test yields a p -value lower than this the result is said to be (statistically) 'significant at the 5 per cent level'.