Estimating Subgroup Differences in Staffing Research When the Selection Mechanism Is Unknown: A Response to Li’s Case IV Correction
扩展了Li的Case IV校正，放宽了群体成员身份不影响选拔决策的假设，允许同时估计预测变量和效标上的子组差异，并通过蒙特卡洛模拟证明新方法在精度上优于原方法。
When estimating subgroup differences on incumbents, range restriction may bias estimates. Bobko, Roth, and Bobko recognized this problem and developed a Case II and Case III correction for Cohen’s d. Subsequently, Li developed a Case IV correction, which seeks to estimate group differences on a predictor using only incumbent data but must assume that group membership (e.g., ethnicity) plays no role in selection decisions. In this paper, we extend Li’s correction and relax this assumption. In addition, this new correction allows for the estimation of subgroup differences on both the criterion and predictor. Using Monte Carlo simulation, we study the performance of both estimators under situations where Li’s assumptions are violated and demonstrate that this new procedure almost always outperforms Li’s Case IV correction and does so with greater precision. We also provide R code to assist applied researchers in using these corrections.