Robust Forecasting

TL;DR

This paper develops a decision-theoretic approach to produce robust forecasts for discrete outcomes under model uncertainty, optimizing for worst-case risk and regret, and introduces efficient methods for practical implementation.

Contribution

It introduces a novel framework for robust forecasting that accounts for model uncertainty and partial identification, with efficient computational techniques and asymptotic theory.

Findings

Robust forecasts depend on a small number of convex optimization problems.

Efficient robust forecasts outperform naive estimators in simulations.

The framework applies to semiparametric panel data models for dynamic discrete choice.

Abstract

We use a decision-theoretic framework to study the problem of forecasting discrete outcomes when the forecaster is unable to discriminate among a set of plausible forecast distributions because of partial identification or concerns about model misspecification or structural breaks. We derive "robust" forecasts which minimize maximum risk or regret over the set of forecast distributions. We show that for a large class of models including semiparametric panel data models for dynamic discrete choice, the robust forecasts depend in a natural way on a small number of convex optimization problems which can be simplified using duality methods. Finally, we derive "efficient robust" forecasts to deal with the problem of first having to estimate the set of forecast distributions and develop a suitable asymptotic efficiency theory. Forecasts obtained by replacing nuisance parameters that characterize the set of forecast distributions with efficient first-stage estimators can be strictly dominated by our efficient robust forecasts.