A modified statistical approach for the detection of outlying values in external quality control: comparison with other techniques.

Laboratory results submitted to External Quality Assessment Schemes (EQAS) are evaluated against the arithmetic mean (m) and standard deviation (SD) of the result from other participants assuming a normal distribution of individual results. The sample statistics m and SD can only be reliable estimates of the theoretical mean (mu) and standard deviation (sigma), if they are not distorted by outlying values. Outliers are commonly detected by defining a confidence interval m +/- k SD, typically with k-values fixed at 3.0 or 3.2. The objective of our study was to prove the deficiency of the use of these fixed limits in large-scale EQAS, because it results in an unacceptable increase of outlier rate and hence in a serious distortion of the estimate of sigma. We have proposed a modified approach using a variable k-value which is dependent upon sample size and keeping the significance level constant at 5%. The influence of different decision limits on the number of outliers and on the sample statistics m and SD was compared using data from the Belgian National EQAS obtained in 6 consecutive surveys.

A method for the statistical evaluation of results in external quality control surveys.

A method for the evaluation of results in external quality control surveys is developed on purely statistical grounds. This system allows to establish accuracy and precision of assay methods by comparing statistical data from subsequent surveys. However, for a particular survey the overall accuracy, precision and quality of each laboratory are defined in statistical terms and visually displayed. Results for each laboratory are summarized on a two-page computer printout. Per component assayed and combining all components determined in the particular survey, the laboratory is assigned one of the four possible qualifications i.e. "very good", "moderate" or "bad". A few general conclusions drawn from experimental data of previous surveys are reported.

External quality control of clinical chemistry laboratories in Belgium.

A description is given of one of the existing National External Quality Assessment Schemes as organised in Belgium. The results of the six surveys held in 1981 in the disciplines Clinical Chemistry and Hormonology are reported. A few general conclusions are drawn from experimental data.