Some remarks on CCP-based estimators of dynamic models

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Some remarks on CCP-based estimators of dynamic models. / Fosgerau, Mogens; Melo, Emerson; Shum, Matthew; Sørensen, Jesper R.V.

In: Economics Letters, Vol. 204, 109911, 07.2021.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Fosgerau, M, Melo, E, Shum, M & Sørensen, JRV 2021, 'Some remarks on CCP-based estimators of dynamic models', Economics Letters, vol. 204, 109911. https://doi.org/10.1016/j.econlet.2021.109911

APA

Fosgerau, M., Melo, E., Shum, M., & Sørensen, J. R. V. (2021). Some remarks on CCP-based estimators of dynamic models. Economics Letters, 204, [109911]. https://doi.org/10.1016/j.econlet.2021.109911

Vancouver

Fosgerau M, Melo E, Shum M, Sørensen JRV. Some remarks on CCP-based estimators of dynamic models. Economics Letters. 2021 Jul;204. 109911. https://doi.org/10.1016/j.econlet.2021.109911

Author

Fosgerau, Mogens ; Melo, Emerson ; Shum, Matthew ; Sørensen, Jesper R.V. / Some remarks on CCP-based estimators of dynamic models. In: Economics Letters. 2021 ; Vol. 204.

Bibtex

@article{867489f68c374716aa7a0346298768a5,

title = "Some remarks on CCP-based estimators of dynamic models",

abstract = "This note provides several remarks relating to the conditional choice probability (CCP) based estimation approaches for dynamic discrete-choice models. Specifically, the Arcidiacono and Miller (2011) estimation procedure relies on the ”inverse-CCP” mapping ψ(p) from CCPs to choice-specific value functions. Exploiting the convex-analytic structure of discrete choice models, we discuss two approaches for computing this mapping, using either linear or convex programming, for models where the utility shocks can follow arbitrary parametric distributions. Furthermore, the ψ function is generally distinct from the ”selection adjustment” term (i.e. the expectation of the utility shock for the chosen alternative), so that computational approaches for computing the latter may not be appropriate for computing ψ.",

keywords = "Convex analysis, Convex optimization, Dynamic discrete choice, Linear programming, Random utility",

author = "Mogens Fosgerau and Emerson Melo and Matthew Shum and S{\o}rensen, {Jesper R.V.}",

note = "Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2021",

month = jul,

doi = "10.1016/j.econlet.2021.109911",

language = "English",

volume = "204",

journal = "Economics Letters",

issn = "0165-1765",

publisher = "Elsevier",

}

RIS

TY - JOUR

T1 - Some remarks on CCP-based estimators of dynamic models

AU - Fosgerau, Mogens

AU - Melo, Emerson

AU - Shum, Matthew

AU - Sørensen, Jesper R.V.

PY - 2021/7

Y1 - 2021/7

N2 - This note provides several remarks relating to the conditional choice probability (CCP) based estimation approaches for dynamic discrete-choice models. Specifically, the Arcidiacono and Miller (2011) estimation procedure relies on the ”inverse-CCP” mapping ψ(p) from CCPs to choice-specific value functions. Exploiting the convex-analytic structure of discrete choice models, we discuss two approaches for computing this mapping, using either linear or convex programming, for models where the utility shocks can follow arbitrary parametric distributions. Furthermore, the ψ function is generally distinct from the ”selection adjustment” term (i.e. the expectation of the utility shock for the chosen alternative), so that computational approaches for computing the latter may not be appropriate for computing ψ.

AB - This note provides several remarks relating to the conditional choice probability (CCP) based estimation approaches for dynamic discrete-choice models. Specifically, the Arcidiacono and Miller (2011) estimation procedure relies on the ”inverse-CCP” mapping ψ(p) from CCPs to choice-specific value functions. Exploiting the convex-analytic structure of discrete choice models, we discuss two approaches for computing this mapping, using either linear or convex programming, for models where the utility shocks can follow arbitrary parametric distributions. Furthermore, the ψ function is generally distinct from the ”selection adjustment” term (i.e. the expectation of the utility shock for the chosen alternative), so that computational approaches for computing the latter may not be appropriate for computing ψ.

KW - Convex analysis

KW - Convex optimization

KW - Dynamic discrete choice

KW - Linear programming

KW - Random utility

U2 - 10.1016/j.econlet.2021.109911

DO - 10.1016/j.econlet.2021.109911

M3 - Journal article

AN - SCOPUS:85106240246

VL - 204

JO - Economics Letters

JF - Economics Letters

SN - 0165-1765

M1 - 109911

ER -

ID: 270558278

Department of Economics