The objective of this study is to evaluate and compare the z-scores calculated for mechanical parameters obtained from interlaboratory basis tests using five robust statistical methods defined in ISO 13528:20221: normalized interquartile range (nIQR), median absolute deviation (MADe), Algorithm A, Q/Hampel, and Qn. These methods are assessed in terms of their ability to suppress outliers, their effect on score variance, and their discriminatory power between laboratories. By analyzing the strengths and limitations of each method across different parameter types (such as Rp0.2, Rm, A%, and modulus of elasticity), this study aims to demonstrate the critical role that robust statistical method selection plays in ensuring fair, consistent, and technically reliable evaluation of laboratory performance in proficiency testing schemes.
KUŞ et al. (Mon,) studied this question.