Measuring the predictability of life outcomes with a scientific mass collaboration
Measuring the predictability of life outcomes with a scientific mass collaboration
复制标题
DOI：
10.1073/pnas.1915006117
复制
发表时间：
2020-04-14
影响因子：
11.1
通讯作者：
McLanahan, Sara
中科院分区：
文献类型：
--
作者：
Salganik, Matthew J.;Lundberg, Ian;McLanahan, Sara
生命轨迹的可预测性如何？我们使用共同的任务方法，通过科学的大规模协作来研究这个问题；160个团队使用高质量的出生队列研究--脆弱家庭和儿童福祉研究的数据，为六种生活结果建立了预测模型。尽管使用了丰富的数据集，并应用了针对预测进行优化的机器学习方法，但最佳预测并不是非常准确，仅略好于简单基准模型的预测。在每个结果中，预测误差与被预测的家庭密切相关，而与用于生成预测的技术弱相关。总体而言，这些结果表明，在某些情况下，生活结果的可预测性存在实际限度，并说明了社会科学中大规模合作的价值。
How predictable are life trajectories? We investigated this question with a scientific mass collaboration using the common task method; 160 teams built predictive models for six life outcomes using data from the Fragile Families and Child Wellbeing Study, a high-quality birth cohort study. Despite using a rich dataset and applying machine-learning methods optimized for prediction, the best predictions were not very accurate and were only slightly better than those from a simple benchmark model. Within each outcome, prediction error was strongly associated with the family being predicted and weakly associated with the technique used to generate the prediction. Overall, these results suggest practical limits to the predictability of life outcomes in some settings and illustrate the value of mass collaborations in the social sciences.