When presenting data, we should always report the estimated magnitude of the effect with a confidence interval, not just the P-value. The confidence interval gives us a plausible range for the size of the effect, and if this interval includes values with greatly varying interpretation, we know that we have to revisit the question with further data. We should look at a graphical presentation of the data to gauge the magnitude of the effect. The importance of a result depends on the value of the question and the size of the effect. Statistical significance tells us merely how confidently we can reject a null hypothesis, but not how big or how important the effect is.