The P value can be found in most nutritional research and is one of the fundamental principles to understand when interpreting the data from a study. The P value of the results is usually displayed in the abstract as well as in the relevant sections in the method and the results. Put simply, the P value is the an estimate of the probability that the results of the study could have occurred by chance. A smaller P value therefore indicate a lower probability that the results have occurred by chance and this increases the statistical significance of the data. It can never be proven definitely that something is so, only that the probability of it being so is high. This is the basis of statistical testing, and weight is given to the analysis as other studies reach similar conclusions. A meta-analysis can be performed on a number of studies and the P values recalculated.
The P values in papers will be displayed as a decimal such as P<0.05. The 0.05 in this example represents a 95% chance that the results displayed are not down to chance (or a 5% chance that they are). In other words there is a 1 in 20 chance that the results are due to chance. Other statistical significance levels that are encountered often include P<0.01 and P<0.001. These represent a 1 in 100 chance and a 1 in 1000 chance that the results are due to chance, respectively. Often asterisk are used to display levels of significance, with one asterisk representing P<0.05 (*), two representing P<0.01 (**) and three asterisk representing P<0.001 (***). In this case the results would be significant, highly significant or extremely significant. Results that are not significant (statistically) generally have P values greater than 0.05.