1 McMaster Children's Hospital, Hamilton, Ontario, Canada 2 Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, Ontario, Canada 3 Strategic Market Leadership and Health Services Management, DeGroote School of Business, McMaster University, Hamilton, Ontario, Canada 4 Health Research Methodology, Department of Health Science, McMaster University, Hamilton, Ontario, Canada.
Patient. 2010 Dec 1;3(4):257-73. doi: 10.2165/11537870-000000000-00000.
Conjoint analysis (CA) has emerged as an important approach to the assessment of health service preferences. This article examines Adaptive Choice-Based Conjoint Analysis (ACBC) and reviews available evidence comparing ACBC with conventional approaches to CA. ACBC surveys more closely approximate the decision-making processes that influence real-world choices. Informants begin ACBC surveys by completing a build-your-own (BYO) task identifying the level of each attribute that they prefer. The ACBC software composes a series of attribute combinations clustering around each participant's BYO choices. During the Screener section, informants decide whether each of these concepts is a possibility or not. Probe questions determine whether attribute levels consistently included in or excluded from each informant's Screener section choices reflect 'Unacceptable' or 'Must Have' simplifying heuristics. Finally, concepts identified as possibilities during the Screener section are carried forward to a Choice Tournament. The winning concept in each Choice Tournament set advances to the next choice set until a winner is determined.A review of randomized trials and cross-over studies suggests that, although ACBC surveys require more time than conventional approaches to CA, informants find ACBC surveys more engaging. In most studies, ACBC surveys yield lower standard errors, improved prediction of hold-out task choices, and better estimates of real-world product decisions than conventional choice-based CA surveys.
联合分析（CA）已成为评估卫生服务偏好的重要方法。本文探讨了自适应选择式联合分析（ACBC），并回顾了比较 ACBC 与传统 CA 方法的现有证据。ACBC 调查更接近影响现实世界选择的决策过程。受访者通过完成自建（BYO）任务开始 ACBC 调查，确定他们偏好的每个属性的水平。ACBC 软件围绕每个参与者的 BYO 选择组合一系列属性组合。在筛选器部分，受访者决定这些概念中的每一个是否是一种可能性。探测问题确定每个受访者筛选器部分选择中始终包含或排除的属性水平是否反映“不可接受”或“必须有”简化启发式。最后，在筛选器部分被确定为可能性的概念被推进到选择锦标赛。每个选择锦标赛集中的获胜概念都会进入下一个选择集，直到确定获胜者。对随机试验和交叉研究的回顾表明，尽管 ACBC 调查比传统的 CA 方法需要更多的时间，但受访者发现 ACBC 调查更具吸引力。在大多数研究中，ACBC 调查产生的标准误差更低，对保留任务选择的预测更好，并且对现实产品决策的估计优于传统的基于选择的 CA 调查。
