Constrained Optimization Approaches to Estimation of Structural Models

Abstract

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract 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. Terms of use: Documents in EconStor mayKeywords: structural estimation, dynamic discrete choice models, constrained optimization * We have greatly benefited from the comments and suggestions of a co-editor and four anonymous referees. We are grateful to Richard W. Cottle and Harry J. Paarsch for their careful reading of this paper and detailed suggestions. We thank

Enriching interactions: Incorporating outcome data into static discrete games

“…The equilibrium constraint forces the agents expectations to match the corresponding equilibrium probabilities. This equilibrium constraint can complicate the evaluation of the likelihood function since, absent a clear selection rule, the direct nested …xed point approach (Rust, 1987) to satisfying this constraint will be mis-speci…ed if there is more than one …xed point (see Su and Judd, 2007). Finally, we note that even with an equilibrium selection rule in place, maximizing the constrained likelihood is a numerically challenging task.…”

High performance quadrature rules: how numerical integration affects a popular model of product differentiation

“…In this paper, we use Mathematical Programming with Equilibrium Constraints (MPEC) (Su and Judd, 2008) to estimate the BLP model because it is faster and more robust than NFP. MPEC relies on a modern, state of the art solver such as KNITRO or SNOPT, to solve the model in one optimization step using constraints:…”

Racial discrimination in the U.S. labor market: Employment and wage differentials by skill

“…In practice, to estimate the model we reformulate the minimization problem as a mathematical programming problem with equilibrium constraints (MPEC), as described by Su and Judd (2012). 22 The advantage of this method is to allow the program to search for the minimum without requiring that at each iteration all equilibrium conditions are exactly satisfied.…”