Predictions as Surrogates: Revisiting Surrogate Outcomes in the Age of AI
将预测作为替代结果：人工智能时代重新审视替代结局
Abstract We establish a formal connection between the decades-old surrogate outcome model in biostatistics and economics and the emerging field of prediction-powered inference. The connection treats predictions from pre-trained models, prevalent in the age of AI, as cost-effective surrogates for expensive outcomes that are not fully observed. Building on the surrogate outcomes literature, we develop recalibrated prediction-powered inference, a more efficient approach to…