TY - JOUR
T1 - BLP-2LASSO for aggregate discrete choice models with rich covariates
AU - Gillen, Benjamin J.
AU - Montero, Sergio
AU - Moon, Hyungsik Roger
AU - Shum, Matthew
N1 - Publisher Copyright:
© 2019 Royal Economic Society. Published by Oxford University Press on behalf of Royal Economic Society. All rights reserved.
Copyright:
Copyright 2019 Elsevier B.V., All rights reserved.
PY - 2019/9/1
Y1 - 2019/9/1
N2 - We introduce the BLP-2LASSO model, which augments the classic BLP (Berry, Levinsohn, and Pakes, 1995) random-coefficients logit model to allow for data-driven selection among a high-dimensional set of control variables using the 'double-LASSO' procedure proposed by Belloni, Chernozhukov, and Hansen (2013). Economists often study consumers' aggregate behaviour across markets choosing from a menu of differentiated products. In this analysis, local demographic characteristics can serve as controls formarket-specific preference heterogeneity. Given rich demographic data, implementing these models requires specifying which variables to include in the analysis, an ad hoc process typically guided primarily by a researcher's intuition. We propose a data-driven approach to estimate these models, applying penalized estimation algorithms from the recent literature in high-dimensional econometrics. Our application explores the effect of campaign spending on vote shares in data fromMexican elections.
AB - We introduce the BLP-2LASSO model, which augments the classic BLP (Berry, Levinsohn, and Pakes, 1995) random-coefficients logit model to allow for data-driven selection among a high-dimensional set of control variables using the 'double-LASSO' procedure proposed by Belloni, Chernozhukov, and Hansen (2013). Economists often study consumers' aggregate behaviour across markets choosing from a menu of differentiated products. In this analysis, local demographic characteristics can serve as controls formarket-specific preference heterogeneity. Given rich demographic data, implementing these models requires specifying which variables to include in the analysis, an ad hoc process typically guided primarily by a researcher's intuition. We propose a data-driven approach to estimate these models, applying penalized estimation algorithms from the recent literature in high-dimensional econometrics. Our application explores the effect of campaign spending on vote shares in data fromMexican elections.
UR - http://www.scopus.com/inward/record.url?scp=85074136255&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85074136255&partnerID=8YFLogxK
U2 - 10.1093/ectj/utz010
DO - 10.1093/ectj/utz010
M3 - Article
AN - SCOPUS:85074136255
VL - 22
SP - 262
EP - 281
JO - Econometrics Journal
JF - Econometrics Journal
SN - 1368-4221
IS - 3
ER -