RELIABILITY ASSESSMENT FOR REMOTE SENSING DATA: BEYOND COHEN'S KAPPA

摘要

Cohen's κ coefficient has been widely used for assessing classification results derived from remote sensing data. It however presents several limitations, which are preventing both an efficient use as well as a generalisation of its use. This paper reviews these problems and proposes as an alternative to prefer the Krippendorff's α-coefficient over Cohen's κ. Krippen-dorff's α indeed presents less flaws while dealing with more data types - hence allowing the rating of quantitative data - and managing the case where more than two judgements are issued and finally dealing with cases where no judgement is issued. These concepts are be illustrated by some exemplary data-sets.