Outliers in clinical chemistry quality-control schemes.

摘要: Results submitted to large-scale quality-control schemes are commonly judged against the mean and standard deviation (SD) of results from other laboratories. It is desirable ignore outlying values in estimating this deviation, more than 2.5 or 3 SD rejected. I show that an outlier can so inflate estimated its presence not detected by method. Alternative estimators less influenced outliers described, their application data discussed.