Selection Bias, Demographic Effects and Ability Effects in Common Value Auction Experiments
Selection Bias, Demographic Effects and Ability Effects in Common Value Auction Experiments
复制标题
共同价值拍卖实验中的选择偏差、人口效应和能力效应
DOI：
10.2139/ssrn.657581
复制
发表时间：
2005
期刊：
影响因子：
--
通讯作者：
J. Kagel
中科院分区：
文献类型：
--
作者：
Marco Casari;John C. Ham;J. Kagel
我们发现，在共同价值拍卖中，明显的人口统计学和能力对出价有影响：没有经验的女性比男性更容易受到赢家诅咒的影响，控制了SAT/ACT分数和大学专业；与其他专业相比，经济和商务专业的报价明显过高；SAT/ACT成绩优异的学生不太容易受到“赢家诅咒”的影响，主要影响来自于那些得分低于中位数的学生表现较差，而那些得分很高的学生表现明显较好，而且SAT/ACT综合成绩比单独的数学或语言成绩更可靠。对于没有经验和有经验的受试者，在投标评估中都有很强的选择效应，这些选择效应不是用标准的计量经济学技术确定的，而是通过我们的实验设计效应确定的。忽略这些选择效应对于没有经验的竞标者来说是最容易误导的，因为对投标函数的无偏估计表明，与有偏估计相比，单个竞标者对赢家诅咒的学习和调整要快得多。
We find clear demographic and ability effects on bidding in common value auctions: inexperienced women are much more susceptible to the winner's curse than men, controlling for SAT/ACT scores and college major; economics and business majors substantially overbid relative to other majors; and those with superior SAT/ACT scores are much less susceptible to the winner's curse, with the primary effect coming from those with below median scores doing worse, as opposed to those with very high scores doing substantially better, and with composite SAT/ACT score being a more reliable predictor than either math or verbal scores by themselves. There are strong selection effects in bid estimates for both inexperienced and experienced subjects that are not identified using standard econometric techniques but rather through our experimental design effects. Ignoring these selection effects is most misleading for inexperienced bidders, as the unbiased estimates of the bid function indicate much faster learning and adjustment to the winner's curse for individual bidders than do the biased estimates.