On incentive-compatible estimators

Kfir Eliaz; Ran Spiegler

doi:10.1016/j.geb.2022.01.002

On incentive-compatible estimators

Kfir Eliaz, Ran Spiegler

School of Economics

Tel Aviv University

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

Abstract

An estimator is incentive-compatible (for a given prior belief regarding the model's true parameters) if it does not give an agent an incentive to misreport the value of his covariates. Eliaz and Spiegler (2019) studied incentive-compatibility of estimators in a setting with a single binary explanatory variable. We extend this analysis to penalized-regression estimation in a simple multi-variable setting. Our results highlight the incentive problems that are created by the element of variable selection/shrinkage in the estimation procedure.

Original language	English
Pages (from-to)	204-220
Number of pages	17
Journal	Games and Economic Behavior
Volume	132
DOIs	https://doi.org/10.1016/j.geb.2022.01.002
State	Published - Mar 2022

Keywords

Incentive-compatible estimators
Lasso
Online platforms
Penalized regression

All Science Journal Classification (ASJC) codes

Finance
Economics and Econometrics

Access to Document

10.1016/j.geb.2022.01.002

Cite this

@article{fe5662609e8441889054af0b776415f9,

title = "On incentive-compatible estimators",

abstract = "An estimator is incentive-compatible (for a given prior belief regarding the model's true parameters) if it does not give an agent an incentive to misreport the value of his covariates. Eliaz and Spiegler (2019) studied incentive-compatibility of estimators in a setting with a single binary explanatory variable. We extend this analysis to penalized-regression estimation in a simple multi-variable setting. Our results highlight the incentive problems that are created by the element of variable selection/shrinkage in the estimation procedure.",

keywords = "Incentive-compatible estimators, Lasso, Online platforms, Penalized regression",

author = "Kfir Eliaz and Ran Spiegler",

note = "Publisher Copyright: {\textcopyright} 2022 Elsevier Inc.",

year = "2022",

month = mar,

doi = "10.1016/j.geb.2022.01.002",

language = "الإنجليزيّة",

volume = "132",

pages = "204--220",

journal = "Games and Economic Behavior",

issn = "0899-8256",

publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - On incentive-compatible estimators

AU - Eliaz, Kfir

AU - Spiegler, Ran

PY - 2022/3

Y1 - 2022/3

N2 - An estimator is incentive-compatible (for a given prior belief regarding the model's true parameters) if it does not give an agent an incentive to misreport the value of his covariates. Eliaz and Spiegler (2019) studied incentive-compatibility of estimators in a setting with a single binary explanatory variable. We extend this analysis to penalized-regression estimation in a simple multi-variable setting. Our results highlight the incentive problems that are created by the element of variable selection/shrinkage in the estimation procedure.

AB - An estimator is incentive-compatible (for a given prior belief regarding the model's true parameters) if it does not give an agent an incentive to misreport the value of his covariates. Eliaz and Spiegler (2019) studied incentive-compatibility of estimators in a setting with a single binary explanatory variable. We extend this analysis to penalized-regression estimation in a simple multi-variable setting. Our results highlight the incentive problems that are created by the element of variable selection/shrinkage in the estimation procedure.

KW - Incentive-compatible estimators

KW - Lasso

KW - Online platforms

KW - Penalized regression

UR - http://www.scopus.com/inward/record.url?scp=85122994601&partnerID=8YFLogxK

U2 - 10.1016/j.geb.2022.01.002

DO - 10.1016/j.geb.2022.01.002

M3 - مقالة

SN - 0899-8256

VL - 132

SP - 204

EP - 220

JO - Games and Economic Behavior

JF - Games and Economic Behavior

ER -

On incentive-compatible estimators

Abstract

Keywords

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this