用机器学习预测老年研究中新冠随访的失访情况
Analysis of ELSA COVID-19 Substudy response rate using machine learning algorithms
- 用六种机器学习模型分析失访原因，随机森林表现最佳
- 随机森林在平衡准确率上最高，达到78.6%
- 适合关注调查数据质量与失访预测的研究者
各国统计局每年投入大量资源开展调查，部分调查包含随访研究。由于死亡、移民、就业变动、健康状况等影响，部分参与者无法参与后续调查。本研究聚焦英国老年纵向研究（ELSA）新冠子研究，该研究在疫情期间分两波进行。第一波部分参与者未参加第二波。本文采用K近邻（KNN）、随机森林（RF）、AdaBoost、逻辑回归、神经网络（NN）和支持向量分类器（SVC）等机器学习算法预测非响应情况。结果表明，随机森林在平衡准确率上表现最优，达到78.6%；KNN在精确率和测试准确率上领先；逻辑回归在受试者工作特征曲线下面积（AUC）上表现最好。
原文摘要 · Abstract (English)
National Statistical Organisations every year spend time and money to collect information through surveys. Some of these surveys include follow-up studies, and usually, some participants due to factors such as death, immigration, change of employment, health, etc, do not participate in future surveys. In this study, we focus on the English Longitudinal Study of Ageing (ELSA) COVID-19 Substudy, which was carried out during the COVID-19 pandemic in two waves. In this substudy, some participants from wave 1 did not participate in wave 2. Our purpose is to predict non-responses using Machine Learning (ML) algorithms such as K-nearest neighbours (KNN), random forest (RF), AdaBoost, logistic regression, neural networks (NN), and support vector classifier (SVC). We find that RF outperforms other models in terms of balanced accuracy, KNN in terms of precision and test accuracy, and logistics regressions in terms of the area under the receiver operating characteristic curve (ROC), i.e. AUC.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。