Comments on 'improving esthetic results in benign parotid surgery: statistical evaluation of facelift approach, sternocleidomastoid flap, and superficial musculoaponeurotic system flap application'.

摘要

We read the report by Bianchi et al1 with great interest. Their aim was to compare the outcomes of partial parotidectomy using a Blair incision without reconstruction and using a facelift incision with or without reconstruction. Although the study question is interesting, we have some discussion that can be listed as follows.First, it is a common misunderstanding that the P < .05 is considered statistically significant, and P < .01 is highly statistically significant. In fact, the P value does not and cannot show the magnitude. Instead, it is only either significant or not. AP value of .001 does not reflect a larger effect than a P value of .04. Any small difference will be statistically significant (P < .05) if the sample size is large enough, regardless of the clinical relevance. If one would like to understand the quality of the estimated value, it is necessary to consider the confidence interval (CI). The width of the CI indicates the size and direction of the effect, the amount of random error, and the precision of the estimate. At present, many journals prefer statistical analyses based on the CI, instead of the P value. For details, please refer to our recent publication.