Generalized optimal parameter-transfer learning through Mallows-type model averaging

TL;DR

This paper introduces a Mallows-type model averaging method for combining multiple source datasets in economic applications, effectively handling heterogeneity and model misspecification.

Contribution

It extends the classical Mallows criterion to a parameter-transfer framework, providing asymptotic optimality guarantees without requiring source models to be correctly specified.

Findings

Weights are asymptotically optimal under misspecification.

Method effectively allocates weights to informative sources.

Simulation and application demonstrate improved prediction accuracy.

Abstract

In many economic applications, multiple source datasets are available, but their effective combination is challenging due to heterogeneity across datasets. To address this problem, we study a parameter-transfer framework that shares only source-side estimates and propose a Mallows-type model averaging method for combining target and source models in the parametric setting. The weights are obtained from a Mallows-type criterion that is unbiased for the target prediction risk up to a weight-independent term, extending the classical Mallows criterion to the parameter-transfer framework. We establish that the proposed weights are asymptotically optimal when the target model is misspecified, and asymptotically allocate weights only to informative sources when the target model is correctly specified. These guarantees do not require any source model to be correctly specified. We also consider extensions of the framework to semiparametric and panel data settings. Simulation studies and house price application further demonstrate the effectiveness of our approach.