Abstract Desvousges et al. (2016), in their reply to Chapman et al. (2016) in this journal, reference the empirical adding-up test in Desvousges et al. (2015). Desvousges et al. (2015) find that their contingent valuation method (CVM) survey data does not pass the adding-up test using a conservative, nonparametric estimate of mean willingness-to-pay. In this comment I show theoretically that the survey fielded by Desvousges et al. (2015) is missing important features necessary for the conduct of an adding-up test. Next, I describe how the CVM data collected by Desvousges et al. (2015) suffers from non-monotonicity, flat bid curve and fat tails problems, each of which will cause willingness-to-pay estimates and standard errors to be sensitive to the approach chosen to measure the central tendency. Using additional parametric approaches that are standard in the CVM literature, I find that willingness-to-pay for the whole is not statistically different from the sum of the parts in two of three additional estimates. In other words, the data passes the adding-up test. The negative result in Desvousges et al. (2015) is not robust to these alternative approaches to willingness-to-pay estimation. The primary reason is low data quality.

中文翻译：

---

对 Desvousges 等人的评论。（Land Economics 2015）：“对河流和湖泊质量的或有估值的加总测试”

摘要 Desvousges 等。(2016)，在他们对查普曼等人的回复中。(2016) 在本期刊中，参考了 Desvousges 等人的经验加总测试。(2015)。Desvousges 等人。(2015) 发现他们的条件估值法 (CVM) 调查数据没有通过使用平均支付意愿的保守、非参数估计的累加测试。在这篇评论中，我从理论上展示了 Desvousges 等人进行的调查。(2015) 缺少进行累加测试所需的重要特征。接下来，我将描述 Desvousges 等人如何收集 CVM 数据。(2015) 存在非单调性、平坦的投标曲线和肥尾问题，每个问题都会导致支付意愿估计和标准误差对选择的测量集中趋势的方法敏感。使用 CVM 文献中标准的附加参数方法，我发现整体的支付意愿与三个附加估计中的两个估计中的部分总和没有统计学差异。换句话说，数据通过了累加测试。Desvousges 等人的否定结果。(2015) 对这些支付意愿估计的替代方法并不稳健。主要原因是数据质量低。