We propose a robust method for constructing conditionally valid prediction intervals based on models for conditional distributions such as quantile and distribution regression. Our approach can be applied to many important prediction problems including cross-sectional prediction, $k$-step-ahead forecasts, synthetic controls and counterfactual prediction, and individual treatment effects prediction. Our method exploits the probability integral transform and relies on permuting estimated ranks. Unlike regression residuals, ranks are independent of the predictors, allowing us to construct conditionally valid prediction intervals under arbitrary heteroskedasticity. We establish the conditional validity under consistent estimation and also provide theoretical performance guarantees under model misspecification, overfitting, and with time series data.
翻译:我们建议了一种稳健的方法,用以根据量化和分布回归等有条件分布模型构建有条件有效的预测间隔。我们的方法可以适用于许多重要的预测问题,包括跨部门预测、美元零位预测、合成控制和反事实预测以及个人治疗效果预测。我们的方法利用概率整体变换,并依赖估计等级。与回归残留值不同的是,等级与预测值无关,使我们能够在任意的四重心状态下构建有条件有效的预测间隔。我们根据一致的估算确定有条件的有效性,并在模型识别错误、超配和时间序列数据下提供理论性能保障。