Statistical Inferences For Interobserver Agreement Studies With Nominal Outcome Data

Abstract

Most statistical methods for interobserver agreement studies involving categorical data focus on dichotomous outcome variables, whereas only a limited number of methods have been developed for nominal outcome data. As a consequence, researchers may resort to dichotomization simply to facilitate the analysis of data, hence discarding potentially valuable information. We present three inference procedures for hypothesis testing concerning interobserver agreement studies with nominal data. These procedures may be applied to studies characterized by two observers and three or more outcome categories. We illustrate these methods by using previously published data sets.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.