“…These statistical methods lack satisfactory capacity to adjust for covariates, such as age and gender, which from our experience as well as that in the literature may heavily influence NCS results. 5,6,9,10,12,[16][17][18][19][20] For the purpose of generating reference data for use in clinical practice, statistical methods that do not allow for covariate adjustment will, therefore, not suffice. Among such methods, the most commonly employed is perhaps that which uses the mean AE some number of standard deviations (SD) to define the upper and lower bounds of the reference range assuming that data follow a bell-shaped normal distribution.…”