Metadata language
Prediction of reliability – pitfalls of using Pearson’s correlation
Subtitle:Raport Badawczy = Research Report ; RB/19/2012
Creator:Hryniewicz, Olgierd (1948– ) ; Karpiński, Janusz
Publisher:Instytut Badań Systemowych. Polska Akademia Nauk ; Systems Research Institute. Polish Academy of Sciences
Place of publishing: Date issued/created: Description:[29] pages ; 21 cm ; Bibliography p. [28-29]
Subject and Keywords:Spearman's rank correlation coefficient ; Measures of dependence ; Miary zależności ; Prediction of reliability ; Pearson's rho ; Prognoza niezawodności
Abstract:Pearson’s coefficient of linear correlation r is the most popular among practitioners measure of dependence. This paper presents, using comprehensive computer simulations, that its application is very limited when we search for informative variables that can be used for the prediction of reliability. Kendall’s τ coefficient has been shown to be much better for this purpose.
Relation:Raport Badawczy = Research Report
Resource type: Detailed Resource Type: Source: Language: Language of abstract: Rights:Creative Commons Attribution BY 4.0 license
Terms of use:Copyright-protected material. [CC BY 4.0] May be used within the scope specified in Creative Commons Attribution BY 4.0 license, full text available at: ; -
Digitizing institution:Systems Research Institute of the Polish Academy of Sciences
Original in:Library of Systems Research Institute PAS
Projects co-financed by: Access: