Constrained Optimization Approaches to Estimation of Structural Models: Comment

Fedor Iskhakov; John Rust; Bertel Schjerning; Lee  Jinhyuk; Kyoungwon Seo

Constrained Optimization Approaches to Estimation of Structural Models: Comment

Fedor Iskhakov, John Rust, Bertel Schjerning, Lee Jinhyuk, Kyoungwon Seo

Abstract

We revisit the comparison of mathematical programming with equilibrium constraints (MPEC) and nested fixed point (NFXP) algorithms for estimating structural dynamic models by Su and Judd (SJ, 2012). They used an inefficient version of the nested fixed point algorithm that relies on successive approximations. We re-do their comparison using the more efficient version of NFXP proposed by Rust (1987), which combines successive approximations and Newton-Kantorovich iterations to solve the fixed point problem (NFXP-NK). We show that MPEC and NFXP-NK are similar in performance when the sample size is relatively small. However, in problems with larger sample sizes, NFXP-NK outperforms MPEC by a significant margin.

Original language	English
Number of pages	10
Publication status	Published - 2015

Series	University of Copenhagen. Institute of Economics. Discussion Papers (Online)
Number	5
Volume	2015
ISSN	1601-2461

Access to Document

http://www.econ.ku.dk/english/research/publications/wp/dp_2015/1505.pdfLicence: Unspecified

Cite this

@techreport{f42caaf778314656b1d9f8ee33a41d8a,

title = "Constrained Optimization Approaches to Estimation of Structural Models: Comment",

abstract = "We revisit the comparison of mathematical programming with equilibrium constraints (MPEC) and nested fixed point (NFXP) algorithms for estimating structural dynamic models by Su and Judd (SJ, 2012). They used an inefficient version of the nested fixed point algorithm that relies on successive approximations. We re-do their comparison using the more efficient version of NFXP proposed by Rust (1987), which combines successive approximations and Newton-Kantorovich iterations to solve the fixed point problem (NFXP-NK). We show that MPEC and NFXP-NK are similar in performance when the sample size is relatively small. However, in problems with larger sample sizes, NFXP-NK outperforms MPEC by a significant margin.",

author = "Fedor Iskhakov and John Rust and Bertel Schjerning and Lee Jinhyuk and Kyoungwon Seo",

note = "JEL Classification: C10, C44, C61",

year = "2015",

language = "English",

series = "University of Copenhagen. Institute of Economics. Discussion Papers (Online)",

number = "5",

type = "WorkingPaper",

}

TY - UNPB

T1 - Constrained Optimization Approaches to Estimation of Structural Models

T2 - Comment

AU - Iskhakov, Fedor

AU - Rust, John

AU - Schjerning, Bertel

AU - Jinhyuk, Lee

AU - Seo, Kyoungwon

N1 - JEL Classification: C10, C44, C61

PY - 2015

Y1 - 2015

N2 - We revisit the comparison of mathematical programming with equilibrium constraints (MPEC) and nested fixed point (NFXP) algorithms for estimating structural dynamic models by Su and Judd (SJ, 2012). They used an inefficient version of the nested fixed point algorithm that relies on successive approximations. We re-do their comparison using the more efficient version of NFXP proposed by Rust (1987), which combines successive approximations and Newton-Kantorovich iterations to solve the fixed point problem (NFXP-NK). We show that MPEC and NFXP-NK are similar in performance when the sample size is relatively small. However, in problems with larger sample sizes, NFXP-NK outperforms MPEC by a significant margin.

AB - We revisit the comparison of mathematical programming with equilibrium constraints (MPEC) and nested fixed point (NFXP) algorithms for estimating structural dynamic models by Su and Judd (SJ, 2012). They used an inefficient version of the nested fixed point algorithm that relies on successive approximations. We re-do their comparison using the more efficient version of NFXP proposed by Rust (1987), which combines successive approximations and Newton-Kantorovich iterations to solve the fixed point problem (NFXP-NK). We show that MPEC and NFXP-NK are similar in performance when the sample size is relatively small. However, in problems with larger sample sizes, NFXP-NK outperforms MPEC by a significant margin.

M3 - Working paper

T3 - University of Copenhagen. Institute of Economics. Discussion Papers (Online)

BT - Constrained Optimization Approaches to Estimation of Structural Models

ER -