Research

• Choosing What to Calibrate and What to Estimate in Structural Models

[Paper]

Abstract

Structural models often fix (calibrate) some parameters and estimate the rest, but this calibration-estimation partition is usually chosen by convention. This paper treats that choice as an econometric partition-selection problem. For each admissible partition, I construct a scalar sensitivity statistic measuring the local response of a target object, such as a policy effect, welfare measure, impulse response, or treatment effect, to perturbations of the calibrated parameters.

The selected partition minimizes this statistic and therefore minimizes worst-case local bias from calibration errors. I first illustrate the decision problem in two canonical examples. I then apply it to the New Keynesian model of Nakamura and Steinsson (2018), where the partition choice has large implications for credibility: some partitions remain reliable under sizeable miscalibrations, whereas others generate large bias from small calibration errors.

The procedure requires only local derivatives, avoids repeated re-estimation, and applies to a broad class of structural models.

Keywords: Model selection; structural parameters; sensitivity analysis; partial identification
JEL: C10; C12; C16

• What to Fix and What to Estimate in Bayesian Structural Models

[Paper]

Abstract

Structural models often calibrate some parameters and estimate others, yet this partition is typically chosen informally. We propose a partition-selection criterion that selects, among admissible partitions, the one minimizing the worst-case local bias of the posterior mean induced by calibration errors. We derive an exact finite-sample sensitivity formula, avoiding Bernstein-von Mises approximations. The Bayesian rule is asymptotically equivalent to its minimum-distance counterpart, but Monte Carlo and Smets-Wouters evidence shows substantial finite-sample differences. The method is straightforward to implement and available for MATLAB/Dynare.

Keywords: Model selection; structural parameters; sensitivity analysis; partial identification
JEL: C10; C12; C16

• Is Your Macro Model Matching the Targets?

with Juan Carlos Escanciano

[Paper]

Abstract

Testing whether a macroeconomic model can match its empirical targets is difficult when those targets come from multiple databases, structural parameters are not point identified, and the covariance matrix of the target estimators may be singular. We develop a minimum distance correct specification test that is robust to all three complications. Because cross-database covariances are unavailable, the test uses the worst-case critical value over all positive-semidefinite covariance completions consistent with the observable within-database blocks. This is the smallest critical value that guarantees asymptotic size control for every admissible dependence structure. We develop a residual-space reparameterization that reduces the dimensionality of the optimization problem and facilitates computation of the worst-case critical value. We illustrate the test in an impulse-response-matching exercise based on the New Keynesian model of An and Schorfheide (2007).

Keywords: Minimum distance estimation; partial identification; multiple databases; specification testing
JEL: C10; C12