Abstract
The letter to the editor by Buser et al expanding the discussion on kappa statistics is a welcome addition to our article, “Kappa and Beyond: Is There Agreement?” 1 Assessing agreement among observers in areas such as classification, outcomes assessment, and diagnosis is crucial to the discipline of spine surgery. When the observation of interest is categorical, kappa is the most widely used statistic characterizing interobserver agreement. And, as the authors rightly point out, weighted versions of kappa enable partial credit to be awarded for near agreement, most notably in the case of ordinal categories. We encourage researchers to consider the various tools available in measuring interobserver reliability, considering the strengths and weakness of each.