The mean rather than the median was used to analyze both ICU and hospital length of stay, concluding that ICU length of stay was shorter for the group using midodrine. The mean was also used when comparing the Acute Physiology and Chronic Health Evaluation (APACHE) IV scores between both groups. One can argue that using the median would have given a more relevant comparison. The median is less prone to be affected by skewed data and outliers, which would be anticipated in such retrospective studies. Weissman retrospectively analyzed the length-of-stay pattern of 4,499 patients in the ICU and demonstrated that when analyzing length-of-stay data, the median is more useful in comparing intergroup differences, and is the most useful measure of central tendency. Marik and Hedman made a similar observation, noting that length of stay is highly skewed toward longer stays because of the many outliers. This would imply that a single patient with a prolonged ICU stay, out of proportion compared with the rest of the patients, would significantly shift the mean and alter the statistical significance. The same argument can be made regarding a comparison of APACHE IV scores between both groups. It would be interesting to determine whether the statistical significance—or the lack of statistical significance in the case of APACHE IV scores—would hold if the median was used instead.