Testing the nested fixed-point algorithm in BLP random coefficients demand estimation

Jinhyuk Lee; Kyoungwon Seo

Testing the nested fixed-point algorithm in BLP random coefficients demand estimation

Jinhyuk Lee
, Kyoungwon Seo^*

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

Abstract

This paper examines the numerical properties of the nested fixed point algorithm (NFP) using Monte Carlo experiments in the estimation of Berry, Levinsohn, and Pakes’s (1995) random coefficient logit demand model. We find that in speed, convergence and accuracy, nested fixed-point (NFP) approach using Newton’s method performs well like a mathematical programming with equilibrium constraints (MPEC) approach adopted by Dubé, Fox, and Su (2012).

Original language	English
Pages (from-to)	1-21
Number of pages	21
Journal	Journal of Economic Theory and Econometrics
Volume	28
Issue number	4
Publication status	Published - 2017 Dec

Bibliographical note

Funding Information:
Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee’s work is supported by a Korea Unversity Grant (K1613461).

Funding Information:
∗Corresponding author: Kyoungwon Seo, Business School, Seoul National University, Seoul, South Korea, [email protected]. Jinhyuk Lee is at Department of Economics, Korea University, Seoul, South Korea, [email protected]. Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee’s work is supported by a Korea Unversity Grant (K1613461).

Publisher Copyright:
© 2017, Korean Econometric Society. All rights reserved.

Keywords

Nested fixedpoint algorithm
Newton’s method
Numerical methods
Random coefficients logit demand

ASJC Scopus subject areas

Economics and Econometrics

Cite this

@article{7e96b57454154eaf996e8a3975b6c779,

title = "Testing the nested fixed-point algorithm in BLP random coefficients demand estimation",

abstract = "This paper examines the numerical properties of the nested fixed point algorithm (NFP) using Monte Carlo experiments in the estimation of Berry, Levinsohn, and Pakes{\textquoteright}s (1995) random coefficient logit demand model. We find that in speed, convergence and accuracy, nested fixed-point (NFP) approach using Newton{\textquoteright}s method performs well like a mathematical programming with equilibrium constraints (MPEC) approach adopted by Dub{\'e}, Fox, and Su (2012).",

keywords = "Nested fixedpoint algorithm, Newton{\textquoteright}s method, Numerical methods, Random coefficients logit demand",

author = "Jinhyuk Lee and Kyoungwon Seo",

note = "Funding Information: Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee{\textquoteright}s work is supported by a Korea Unversity Grant (K1613461). Funding Information: ∗Corresponding author: Kyoungwon Seo, Business School, Seoul National University, Seoul, South Korea, [email protected]. Jinhyuk Lee is at Department of Economics, Korea University, Seoul, South Korea, [email protected]. Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee{\textquoteright}s work is supported by a Korea Unversity Grant (K1613461). Publisher Copyright: {\textcopyright} 2017, Korean Econometric Society. All rights reserved.",

year = "2017",

month = dec,

language = "English",

volume = "28",

pages = "1--21",

journal = "Journal of Economic Theory and Econometrics",

issn = "1229-2893",

publisher = "Korean Econometric Society",

number = "4",

}

TY - JOUR

T1 - Testing the nested fixed-point algorithm in BLP random coefficients demand estimation

AU - Lee, Jinhyuk

AU - Seo, Kyoungwon

N1 - Funding Information: Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee’s work is supported by a Korea Unversity Grant (K1613461). Funding Information: ∗Corresponding author: Kyoungwon Seo, Business School, Seoul National University, Seoul, South Korea, [email protected]. Jinhyuk Lee is at Department of Economics, Korea University, Seoul, South Korea, [email protected]. Seo gratefully acknowledges the financial support of the SNU Invitation Program for Distinguished Scholar, the Institute of Finance and Banking, and Management Research Center at Seoul National University. Lee’s work is supported by a Korea Unversity Grant (K1613461). Publisher Copyright: © 2017, Korean Econometric Society. All rights reserved.

PY - 2017/12

Y1 - 2017/12

N2 - This paper examines the numerical properties of the nested fixed point algorithm (NFP) using Monte Carlo experiments in the estimation of Berry, Levinsohn, and Pakes’s (1995) random coefficient logit demand model. We find that in speed, convergence and accuracy, nested fixed-point (NFP) approach using Newton’s method performs well like a mathematical programming with equilibrium constraints (MPEC) approach adopted by Dubé, Fox, and Su (2012).

AB - This paper examines the numerical properties of the nested fixed point algorithm (NFP) using Monte Carlo experiments in the estimation of Berry, Levinsohn, and Pakes’s (1995) random coefficient logit demand model. We find that in speed, convergence and accuracy, nested fixed-point (NFP) approach using Newton’s method performs well like a mathematical programming with equilibrium constraints (MPEC) approach adopted by Dubé, Fox, and Su (2012).

KW - Nested fixedpoint algorithm

KW - Newton’s method

KW - Numerical methods

KW - Random coefficients logit demand

UR - https://www.scopus.com/pages/publications/85039857942

M3 - Article

AN - SCOPUS:85039857942

SN - 1229-2893

VL - 28

SP - 1

EP - 21

JO - Journal of Economic Theory and Econometrics

JF - Journal of Economic Theory and Econometrics

IS - 4

ER -

Testing the nested fixed-point algorithm in BLP random coefficients demand estimation

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this