Estimating structural models is often viewed as computationally difficult, an impression partly due to a focus on the nested fixed-point (NFXP) approach.We propose a new constrained optimization approach for structural estimation.We show that our approach and the NFXP algorithm solve the same estimation problem, and yield the same estimates.Computationally, our approach can have speed advantages because we do not repeatedly solve the structural equation at each guess of structural parameters.Monte Carlo experiments on the canonical Zurcher bus-repair model demonstrate that the constrained optimization approach can be significantly faster.

[A tractable dynamic general equilibrium model of continuous product innovation is developed. Patents, or any imitation lag, of infinite duration may achieve too much, too little, or the socially optimum level of innovation. Most surprising, finite-life patents may induce undamped oscillations in innovation.]

[It is shown that wquilibria with dispersed prices exist in environments with identical and rational agents on both sides of the market. In particular, the original Stigler model of nonsequential search often has many equilibria, some with price dispersion. Also, price dispersion holds in equilibrium in general if search is "noisy," i.e., there is some chance of learning two or more prices when an agent is looking for one price.]

We present a general method for computing the set of supergame equilibria in infinitely repeated games with perfect monitoring and public randomization. We present a three-stage algorithm that constructs a convex set containing the set of equilibrium values, constructs another convex set contained in the set of equilibrium values, and produces strategies that support them. We explore the properties of this algorithm by applying it to familiar games.

We propose a novel methodology for evaluating the accuracy of numerical solutions to dynamic economic models. It consists in constructing a lower bound on the size of approximation errors. A small lower bound on errors is a necessary condition for accuracy: If a lower error bound is unacceptably large, then the actual approximation errors are even larger, and hence, the approximation is inaccurate. Our lower‐bound error analysis is complementary to the conventional upper‐error (worst‐case) bound analysis, which provides a sufficient condition for accuracy. As an illustration of our methodology, we assess approximation in the first‐ and second‐order perturbation solutions for two stylized models: a neoclassical growth model and a new Keynesian model. The errors are small for the former model but unacceptably large for the latter model under some empirically relevant parameterizations.