A Guide to Measuring and Interpreting Attribute Importance
A Guide to Measuring and Interpreting Attribute Importance
复制标题
DOI：
10.1007/s40271-019-00360-3
复制
发表时间：
2019-06-01
影响因子：
3.6
通讯作者：
Gonzalez, Juan Marcos
中科院分区：
文献类型：
--
作者：
Gonzalez, Juan Marcos
陈述偏好（SP）方法，例如离散选择实验（DCE）和最佳-最差标度（BWS），越来越多地用于衡量对医疗干预属性的偏好。偏好信息通常使用属性重要性来表征。然而，属性重要性度量的值和解释可能会有所不同，具体取决于用于引发偏好的方法、问题的具体上下文以及用于标准化属性效应的方法。这种变化使偏好结果的解释以及样本中各子组结果的可比性变得复杂。本文强调了忽略属性重要性度量变化的潜在后果，并为更清楚地报告如何获取和计算这些度量提供了理由。计算的透明度可以阐明结果支持哪些结论，并有助于在子样本之间进行更准确和更有意义的比较。
Stated-preference (SP) methods, such as discrete-choice experiments (DCE) and best-worst scaling (BWS), have increasingly been used to measure preferences for attributes of medical interventions. Preference information is commonly characterized using attribute importance. However, attribute importance measures can vary in value and interpretation depending on the method used to elicit preferences, the specific contextof the questions, and the approach used to normalize attributeeffects. This variationcomplicates the interpretation ofpreference resultsandthe comparability of results across subgroups in a sample. This article highlightsthe potentialconsequences of ignoring variations in attribute importance measures, and makes the case for reportingmore clearly how these measures are obtained andcalculated.Transparency inthecalculations canclarify what conclusions aresupported by the results, and helpmake more accurate and meaningful comparisons across subsamples.