A Comment on "Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting" by Hanming Fang and Yang Wang

Jaap Abbring, Øystein Daljord

Research output: Working paperOther research output

Abstract

The recent literature often cites Fang and Wang (2015) for analyzing the identification of time preferences in dynamic discrete choice under exclusion restrictions (e.g. Yao et al., 2012; Lee, 2013; Ching et al., 2013; Norets and Tang, 2014; Dubé et al., 2014; Gordon and Sun, 2015; Bajari et al., 2016; Chan, 2017; Gayle et al., 2018). Indeed, Fang and Wang's Proposition 2 claims generic identification of a dynamic discrete choice model with hyperbolic discounting. However, this claim uses a definition of "generic" that does not preclude the possibility that a generically identified model is nowhere identified. To illustrate this point, we provide two simple examples of models that are generically identified in Fang and Wang's sense, but that are, respectively, everywhere and nowhere identified. We conclude that Proposition 2 is void: It has no implications for identification of the dynamic discrete choice model. We show how its proof is incorrect and incomplete and suggest alternative approaches to identification.
Original languageEnglish
Place of PublicationIthaca
PublisherCornell University Library
Number of pages11
Publication statusPublished - 16 May 2019

Publication series

NamearXiv
Volume1905.07048

Fingerprint

Discrete choice models
Dynamic discrete choice
Hyperbolic discounting
Exclusion
Time preference

Cite this

Abbring, J., & Daljord, Ø. (2019). A Comment on "Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting" by Hanming Fang and Yang Wang. (arXiv; Vol. 1905.07048). Ithaca: Cornell University Library.
@techreport{51cdd7c112c849ccb2ff6b5ce00d4b96,
title = "A Comment on {"}Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting{"} by Hanming Fang and Yang Wang",
abstract = "The recent literature often cites Fang and Wang (2015) for analyzing the identification of time preferences in dynamic discrete choice under exclusion restrictions (e.g. Yao et al., 2012; Lee, 2013; Ching et al., 2013; Norets and Tang, 2014; Dub{\'e} et al., 2014; Gordon and Sun, 2015; Bajari et al., 2016; Chan, 2017; Gayle et al., 2018). Indeed, Fang and Wang's Proposition 2 claims generic identification of a dynamic discrete choice model with hyperbolic discounting. However, this claim uses a definition of {"}generic{"} that does not preclude the possibility that a generically identified model is nowhere identified. To illustrate this point, we provide two simple examples of models that are generically identified in Fang and Wang's sense, but that are, respectively, everywhere and nowhere identified. We conclude that Proposition 2 is void: It has no implications for identification of the dynamic discrete choice model. We show how its proof is incorrect and incomplete and suggest alternative approaches to identification.",
author = "Jaap Abbring and {\O}ystein Daljord",
note = "arXiv:1905.07048",
year = "2019",
month = "5",
day = "16",
language = "English",
series = "arXiv",
publisher = "Cornell University Library",
type = "WorkingPaper",
institution = "Cornell University Library",

}

A Comment on "Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting" by Hanming Fang and Yang Wang. / Abbring, Jaap; Daljord, Øystein.

Ithaca : Cornell University Library, 2019. (arXiv; Vol. 1905.07048).

Research output: Working paperOther research output

TY - UNPB

T1 - A Comment on "Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting" by Hanming Fang and Yang Wang

AU - Abbring, Jaap

AU - Daljord, Øystein

N1 - arXiv:1905.07048

PY - 2019/5/16

Y1 - 2019/5/16

N2 - The recent literature often cites Fang and Wang (2015) for analyzing the identification of time preferences in dynamic discrete choice under exclusion restrictions (e.g. Yao et al., 2012; Lee, 2013; Ching et al., 2013; Norets and Tang, 2014; Dubé et al., 2014; Gordon and Sun, 2015; Bajari et al., 2016; Chan, 2017; Gayle et al., 2018). Indeed, Fang and Wang's Proposition 2 claims generic identification of a dynamic discrete choice model with hyperbolic discounting. However, this claim uses a definition of "generic" that does not preclude the possibility that a generically identified model is nowhere identified. To illustrate this point, we provide two simple examples of models that are generically identified in Fang and Wang's sense, but that are, respectively, everywhere and nowhere identified. We conclude that Proposition 2 is void: It has no implications for identification of the dynamic discrete choice model. We show how its proof is incorrect and incomplete and suggest alternative approaches to identification.

AB - The recent literature often cites Fang and Wang (2015) for analyzing the identification of time preferences in dynamic discrete choice under exclusion restrictions (e.g. Yao et al., 2012; Lee, 2013; Ching et al., 2013; Norets and Tang, 2014; Dubé et al., 2014; Gordon and Sun, 2015; Bajari et al., 2016; Chan, 2017; Gayle et al., 2018). Indeed, Fang and Wang's Proposition 2 claims generic identification of a dynamic discrete choice model with hyperbolic discounting. However, this claim uses a definition of "generic" that does not preclude the possibility that a generically identified model is nowhere identified. To illustrate this point, we provide two simple examples of models that are generically identified in Fang and Wang's sense, but that are, respectively, everywhere and nowhere identified. We conclude that Proposition 2 is void: It has no implications for identification of the dynamic discrete choice model. We show how its proof is incorrect and incomplete and suggest alternative approaches to identification.

M3 - Working paper

T3 - arXiv

BT - A Comment on "Estimating Dynamic Discrete Choice Models with Hyperbolic Discounting" by Hanming Fang and Yang Wang

PB - Cornell University Library

CY - Ithaca

ER -