CONSIDERATIONS IN CHOICE OF INTEROBSERVER RELIABILITY ESTIMATES
CONSIDERATIONS IN CHOICE OF INTEROBSERVER RELIABILITY ESTIMATES
复制标题
DOI：
10.1901/jaba.1977.10-103
复制
发表时间：
1977-01-01
影响因子：
2.9
通讯作者：
HARTMANN, DP
中科院分区：
文献类型：
--
作者：
HARTMANN, DP
在人类观察者构成主要数据采集系统的行为治疗研究中，可能需要两种类型的观察者间可靠性值：试验可靠性和随后分析的复合评分单位的可靠性，例如，每日或每周的会议总数。两种方法来确定观察者间的可靠性进行了描述：百分比协议和相关措施的可靠性。对这些估计数的解释、影响其大小的因素以及每种方法的优点和局限性都作了介绍。
Two types of interobserver reliability values may be needed in behavioral treatment studies in which human observers constitute the primary data-acquisition system: trial reliability and the reliability of the composite unit of score which is subsequently analyzed, e.g., daily or weekly session totals. Two approaches to determining interobserver reliability were described: percentage agreement and correlational measures of reliability. The interpretation of these estimates, factors affecting their magnitude and the advantages and limitations of each approach were presented.