Researchers often use regression-based (e.g., conservatism , misstatement ) from a stage 1 model as a dependent variable in stage 2. We argue that this analysis can cause coefficient biases and interpretation problems because (1) does not capture new sources of variation, and (2) the estimates often hinge on unacknowledged technical assumptions. Instead, we recommend that researchers include the test variables and the relevant controls in stage 1, obviating the need for an . In replication analyses, some important published findings change after we remove the coefficient bias caused by the use of as a dependent variable.

中文翻译：

---

滥用基于回归的 x 分数作为因变量

研究人员经常使用第一阶段模型中的基于回归（例如保守主义、误报）作为第二阶段的因变量。我们认为这种分析可能会导致系数偏差和解释问题，因为 (1) 没有捕获新的变异来源， (2) 估计通常取决于未经承认的技术假设。相反，我们建议研究人员在第一阶段包括测试变量和相关控制，从而消除对 .在复制分析中，在我们消除因使用 为因变量而导致的系数偏差后，一些重要的已发表的研究结果发生了变化。