Sir, as dental clinicians, we should be all aware of the increased effort to incorporate an evidence-based approach to enable best decisions about patient care. However, there has been little discussion in dentistry of the limits of P values in interpreting the results of published studies. This is despite a growing consensus in medicine that the simple use of P values to determine whether the results of a study are valid are insufficient or misleading.1,2

Discussion of the limitations of P values are beyond the scope of this letter but there is a growing movement in medicine to include alternative approaches including Bayesian methods. The P value is the probability of observing events as extreme or more extreme than the observed data if the null hypothesis is true.3 One of the most common concerns described in the medical literature is that students and clinicians simply end up with an incorrect interpretation of what P values mean. As described by Goodman, when presenting the results of a study to physicians that the study results had a P value of 0.05, the majority will state that there is a 95% or greater chance that the null hypothesis is incorrect.2 This is the wrong interpretation because the P value is calculated on the assumption that the null hypothesis is true and it is not a direct measure of the probability that the null hypothesis is false.

Other limitations of the P value are that it: does not take into consideration the clinical magnitude of the observed association; does not consider biologic plausibility; overstates the evidence against the null hypothesis.4 I encourage readers to explore some of the recent published literature in medicine that describe alternative approaches to the analysis of data besides only looking at P values including greater consideration of confidence intervals and the observed clinical magnitude of the associations.