Prediction Intervals for Model Averaging

A rich set of frequentist model averaging methods has been developed, but their applications have largely been limited to point prediction, as measuring prediction uncertainty in general settings remains an open problem. In this paper we propose prediction intervals for model averaging based on conformal inference. These intervals cover out-of-sample realizations of the outcome variable with a pre-specified probability, providing a way to assess predictive uncertainty beyond point prediction. The framework allows general model misspecification and applies to averaging across multiple models that can be nested, disjoint, overlapping, or any combination thereof, with weights that may depend on the estimation sample. We establish coverage guarantees under two sets of assumptions: exact finite-sample validity under exchangeability, relevant for cross-sectional data, and asymptotic validity under stationarity, relevant for time-series data. We first present a benchmark algorithm and then introduce a locally adaptive refinement and split-sample procedures that broaden applicability. The methods are illustrated with a cross-sectional application to real estate appraisal and a time-series application to equity premium forecasting.