Latent-variable models are central to economics but often entail intractable integration. Variational inference (VI), widely used in machine learning, turns this integration into tractable, differentiable optimization by replacing the likelihood with a variational objective. However, guarantees of recovering the true parameters remain limited when the variational family is insufficiently flexible—a key obstacle to the adoption of VI in economics. We first evaluate VI in models of earnings dynamics and show that the choice of variational posterior is crucial. We then introduce indirect variational inference (IVI), which treats VI as an auxiliary model and corrects the bias induced by the variational approximation. IVI retains much of VI’s tractability because it does not require computing the likelihood. We apply these methods to models allowing for nonlinear persistence, non-Gaussian and serially correlated transitory shocks, and latent heterogeneity. Across simulated and empirical applications, flexible variational families combined with IVI deliver reliable estimates.

More on this topic

BFI Working Paper·Nov 16, 2026

The Role of Parental Beliefs and Public Policies in Financing Higher Education: An Experimental Study

Francesco Agostinelli, Guglielmo Briscese, and Giovanni M. Topa
Topics: Economic Mobility & Poverty, Higher Education & Workforce Training
BFI Working Paper·Nov 10, 2026

When Food Stamps Became Free: Impacts and Implications of Removing the Purchase Requirement

Amy Finkelstein, Matthew Notowidigdo, and Charlie Rafkin
Topics: Economic Mobility & Poverty
BFI Working Paper·Nov 3, 2026

Deconstructing Job Search Behavior

Stefano Banfi, Sekyu Choi, and Benjamín Villena-Roldán
Topics: Employment & Wages