Julius Sim1, Chris C Wright. 1. Primary Care Sciences Research Centre, Keele University, Keele, Staffordshire ST5 5BG, United Kingdom. j.sim@keele.ac.uk
Abstract
PURPOSE: This article examines and illustrates the use and interpretation of the kappa statistic in musculoskeletal research. SUMMARY OF KEY POINTS: The reliability of clinicians' ratings is an important consideration in areas such as diagnosis and the interpretation of examination findings. Often, these ratings lie on a nominal or an ordinal scale. For such data, the kappa coefficient is an appropriate measure of reliability. Kappa is defined, in both weighted and unweighted forms, and its use is illustrated with examples from musculoskeletal research. Factors that can influence the magnitude of kappa (prevalence, bias, and non-independent ratings) are discussed, and ways of evaluating the magnitude of an obtained kappa are considered. The issue of statistical testing of kappa is considered, including the use of confidence intervals, and appropriate sample sizes for reliability studies using kappa are tabulated. CONCLUSIONS: The article concludes with recommendations for the use and interpretation of kappa.
PURPOSE: This article examines and illustrates the use and interpretation of the kappa statistic in musculoskeletal research. SUMMARY OF KEY POINTS: The reliability of clinicians' ratings is an important consideration in areas such as diagnosis and the interpretation of examination findings. Often, these ratings lie on a nominal or an ordinal scale. For such data, the kappa coefficient is an appropriate measure of reliability. Kappa is defined, in both weighted and unweighted forms, and its use is illustrated with examples from musculoskeletal research. Factors that can influence the magnitude of kappa (prevalence, bias, and non-independent ratings) are discussed, and ways of evaluating the magnitude of an obtained kappa are considered. The issue of statistical testing of kappa is considered, including the use of confidence intervals, and appropriate sample sizes for reliability studies using kappa are tabulated. CONCLUSIONS: The article concludes with recommendations for the use and interpretation of kappa.
Authors: E M Arsava; E Ballabio; T Benner; J W Cole; M P Delgado-Martinez; M Dichgans; F Fazekas; K L Furie; K Illoh; K Jood; S Kittner; A G Lindgren; J J Majersik; M J Macleod; W J Meurer; J Montaner; A A Olugbodi; A Pasdar; P Redfors; R Schmidt; P Sharma; A B Singhal; A G Sorensen; C Sudlow; V Thijs; B B Worrall; J Rosand; H Ay Journal: Neurology Date: 2010-10-05 Impact factor: 9.910
Authors: Todd S Ellenbecker; W Ben Kibler; David S Bailie; Roger Caplinger; George J Davies; Bryan L Riemann Journal: Clin Orthop Relat Res Date: 2012-06 Impact factor: 4.176
Authors: Linda Berg; Oivind Gjertsen; Christian Hellum; Gesche Neckelmann; Lars G Johnsen; Geir E Eide; Ansgar Espeland Journal: Skeletal Radiol Date: 2012-03-20 Impact factor: 2.199
Authors: Annika Schuhbäck; Mohamed Marwan; Sören Gauss; Gerd Muschiol; Dieter Ropers; Christian Schneider; Michael Lell; Johannes Rixe; Christian Hamm; Werner G Daniel; Stephan Achenbach Journal: Eur Radiol Date: 2012-03-27 Impact factor: 5.315
Authors: Benjamin Haibe-Kains; Nehme El-Hachem; Nicolai Juul Birkbak; Andrew C Jin; Andrew H Beck; Hugo J W L Aerts; John Quackenbush Journal: Nature Date: 2013-11-27 Impact factor: 49.962
Authors: S A Nagy; I Juhasz; H Komaromy; K Pozsar; I Zsigmond; G Perlaki; G Orsi; A Schwarcz; N Walter; T Doczi; P Bogner Journal: Clin Neuroradiol Date: 2013-11-12 Impact factor: 3.649