Regression to the Mean for Nonnormal Populations
针对非正态分布数据，基于Edgeworth级数和鞍点近似给出了均值回归效应的估计方法，适用于生物变量等非正态场景。
Regression to the mean is the term used to describe the effect by which individuals selected on the basis of an initial measurement which is particularly high or low compared with other members of the population have, upon remeasurement, values nearer to the population mean. For the normal distribution simple expressions for estimates of the magnitude of this effect are available. Many biological variables, however, are not normally distributed. Estimates for regression to the mean for nonnormal data are given based on Edgeworth series and saddlepoint approximations.