Investigating the Effect of Attribute Non‐Attendance in Different Elicitation Formats: Single Discrete Choice, Rank‐Order Discrete Choice, and Best Worst Scaling
研究了选择实验中属性不关注（ANA）在不同诱导格式下的普遍性差异，以及如何通过自报ANA信息改善模型拟合度，但对预测能力提升有限。
ABSTRACT This paper investigates methodological issues related to attribute non‐attendance (ANA) in choice experiments (CEs). First evaluates the variation in the prevalence of ANA across various non‐hypothetical choice experiments (NHCEs) elicitation formats compared to hypothetical choice experiments (HCEs). Second, it investigates whether eliciting respondents’ self‐reported ANA after each choice set (choice task (CT)) or at the end of the choice task (seria task (ST)yields comparable results. Finally, it examines how incorporating self‐reported ANA information affects respondents’ willingness to pay (WTP) and the external predictive powers of the estimated choice models. To answer these research questions, four treatments were conducted: HCE, NHCE, non‐hypothetical rank‐order discrete choice experiment (NHROCE), and non‐hypothetical best worst scaling (NHBWS). The results indicate that accounting for ANA information significantly improves the goodness‐of‐fit of the estimated choice models, especially when full ranking information (NHROCE and NHBWS) is used. In terms of marginal WTP estimates, the results show that modeling ANA, independently of the elicitation approach of ANA (ST or CT), significantly influences consumers’ WTP values. However, the results suggest that incorporating ANA information does not substantially enhance the predictive power of the estimated choice model.