迈向实证软件工程数据的因果分析：编程语言对编程竞赛的影响
Towards Causal Analysis of Empirical Software Engineering Data: The Impact of Programming Languages on Coding Competitions
AI总结：
本文提出基于结构因果模型分析软件工程观测数据的方法，并以 Google Code Jam 数据评估编程语言对竞赛成绩的因果影响，证明因果分析比纯预测建模更稳健。
摘要：
软件工程领域存在大量观测数据，而开展大规模受控实验在实践中往往不可行。因此，大多数实证研究只能报告统计相关性，而非可能更具洞察力且更稳健的因果关系。为支持分析纯观测数据中的因果关系，并评估同一数据的纯预测模型与因果模型之间的差异，本文讨论了一些基于结构因果模型（例如因果贝叶斯网络的有向无环图）的新技术。利用这些技术，人们可以严谨地表达并部分验证因果假设；随后利用因果信息指导构建捕捉真实因果关系的统计模型，从而使相关性确实蕴含因果性。我们将这些思路应用于分析有关程序员在 Code Jam 中表现的公开数据；Code Jam 是由 Google 每年组织的一项大型全球编程竞赛。具体而言，我们考察不同编程语言对参赛者竞赛表现的影响。尽管无论考虑相关联系还是因果联系，与编程语言相关的总体效应相较于其他变量都较弱，但我们发现，对完全相同的数据进行纯关联分析与因果分析会产生显著差异。核心启示是，即使是对观测数据进行不完美的因果分析，也比仅使用纯预测技术更精确、更稳健地帮助回答突出的研究问题，因为在纯预测技术中，真实因果效应可能受到混杂因素干扰。
英文摘要：
There is abundant observational data in the software engineering domain, whereas running large-scale controlled experiments is often practically impossible. Thus, most empirical studies can only report statistical correlations -- instead of potentially more insightful and robust causal relations. To support analyzing purely observational data for causal relations, and to assess any differences between purely predictive and causal models of the same data, this paper discusses some novel techniques based on structural causal models (such as directed acyclic graphs of causal Bayesian networks). Using these techniques, one can rigorously express, and partially validate, causal hypotheses; and then use the causal information to guide the construction of a statistical model that captures genuine causal relations -- such that correlation does imply causation. We apply these ideas to analyzing public data about programmer performance in Code Jam, a large world-wide coding contest organized by Google every year. Specifically, we look at the impact of different programming languages on a participant's performance in the contest. While the overall effect associated with programming languages is weak compared to other variables -- regardless of whether we consider correlational or causal links -- we found considerable differences between a purely associational and a causal analysis of the very same data. The takeaway message is that even an imperfect causal analysis of observational data can help answer the salient research questions more precisely and more robustly than with just purely predictive techniques -- where genuine causal effects may be confounded.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
