Objective:

This study examined the effects of offering proactive student-success coaching, informed by predictive analytics, on student academic performance and persistence. Specifically, this study investigated semester grade point average (GPA) and semester-to-semester persistence of community college students as outcomes.

Methods:

This study involved two stages of analysis. First, we used inverse probability of treatment weighting to create appropriately balanced samples of the students offered proactive assistance and students not offered proactive assistance to approximate a randomized control trial with observational data. Then, we applied regression analyses with weights and covariates to the balanced samples to estimate outcomes.

Results:

Using regression analyses with weights and covariates, we estimated few statistically significant results in sample subgroup models and no statistically significant results for whole-group samples. Generally, our analyses found that the offer of the intervention had no effect on students’ persistence and semester GPAs.

Conclusions/Contributions:

This study contributes empirical results to the emerging literature regarding student-success coaching, predictive analytics, and student-monitoring systems. The results demonstrate the necessity of performing rigorous analyses on these predictive-analytic systems and reveals ethical concerns that should be considered in designing interventions.

中文翻译：

---

提供积极的学生成功辅导对社区大学生学习成绩和毅力的影响

客观的：

这项研究考察了通过预测分析提供主动的学生成功教练对学生学习成绩和毅力的影响。具体而言，本研究调查了社区大学生的学期平均学分（GPA）和学期至学期持续性作为结果。

方法：

这项研究涉及两个阶段的分析。首先，我们使用处理权重的反概率来创建适当平衡的样本，这些样本提供了积极的帮助，没有提供积极的帮助的学生使用观察数据来近似进行随机对照试验。然后，我们将权重和协变量的回归分析应用于平衡样本以估计结果。

结果：

使用具有权重和协变量的回归分析，我们估计样本亚组模型中几乎没有统计学上显着的结果，而整体样本中没有统计学上的显着结果。通常，我们的分析发现，提供干预措施不会对学生的坚持不懈和学期的GPA产生任何影响。

结论/贡献：

这项研究为有关学生成功辅导，预测分析和学生监控系统的新兴文献提供了经验性结果。结果证明了对这些预测分析系统进行严格分析的必要性，并揭示了在设计干预措施时应考虑的伦理问题。