Demand Models With Random Partitions

被引:11
作者
Smith, Adam N. [1 ]
Allenby, Greg M. [2 ]
机构
[1] UCL, UCL Sch Management, London E14 5AA, England
[2] Ohio State Univ, Fisher Coll Business, Columbus, OH 43210 USA
关键词
Bayesian inference; Location-scale family; Markov chain Monte Carlo; Polya urn; Price elasticity; VARIABLE SELECTION; PURCHASE INCIDENCE; BAYESIAN-ANALYSIS; REGRESSION; PRICE; AUGMENTATION; ELASTICITIES; COMPETITION; COVARIANCE; SHRINKAGE;
D O I
10.1080/01621459.2019.1604360
中图分类号
O21 [概率论与数理统计]; C8 [统计学];
学科分类号
020208 ; 070103 ; 0714 ;
摘要
Many economic models of consumer demand require researchers to partition sets of products or attributes prior to the analysis. These models are common in applied problems when the product space is large or spans multiple categories. While the partition is traditionally fixed a priori, we let the partition be a model parameter and propose a Bayesian method for inference. The challenge is that demand systems are commonly multivariate models that are not conditionally conjugate with respect to partition indices, precluding the use of Gibbs sampling. We solve this problem by constructing a new location-scale partition distribution that can generate random-walk Metropolis-Hastings proposals and also serve as a prior. Our method is illustrated in the context of a store-level category demand model, where we find that allowing for partition uncertainty is important for preserving model flexibility, improving demand forecasts, and learning about the structure of demand. for this article, including a standardized description of the materials available for reproducing the work, are available as an online supplement.
引用
收藏
页码:47 / 65
页数:19
相关论文
共 50 条
[41]   Bayesian inference for finite mixtures of generalized linear models with random effects [J].
Peter J. Lenk ;
Wayne S. DeSarbo .
Psychometrika, 2000, 65 :93-119
[42]   RANDOM LASSO [J].
Wang, Sijian ;
Nan, Bin ;
Rosset, Saharon ;
Zhu, Ji .
ANNALS OF APPLIED STATISTICS, 2011, 5 (01) :468-485
[43]   Effect of a secondary market on a system with random demand and uncertain costs [J].
Gurel, Yucel ;
Gullu, Refik .
INTERNATIONAL JOURNAL OF PRODUCTION ECONOMICS, 2019, 209 :112-120
[44]   Random partition models with regression on covariates [J].
Muellner, Peter ;
Quintana, Fernando .
JOURNAL OF STATISTICAL PLANNING AND INFERENCE, 2010, 140 (10) :2801-2808
[45]   Rational habits in gasoline demand [J].
Scott, K. Rebecca .
ENERGY ECONOMICS, 2012, 34 (05) :1713-1723
[46]   Marginalized Exponential Random Graph Models [J].
Suesse, Thomas .
JOURNAL OF COMPUTATIONAL AND GRAPHICAL STATISTICS, 2012, 21 (04) :883-900
[47]   On generating random Gaussian graphical models [J].
Cordoba, Irene ;
Varando, Gherardo ;
Bielza, Concha ;
Larranaga, Pedro .
INTERNATIONAL JOURNAL OF APPROXIMATE REASONING, 2020, 125 :240-250
[48]   Longitudinal threshold models with random components [J].
Saei, A ;
McGilchrist, CA .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES D-THE STATISTICIAN, 1998, 47 (02) :365-375
[49]   Random autoregressive models: A structured overview [J].
Regis, Marta ;
Serra, Paulo ;
van den Heuvel, Edwin R. .
ECONOMETRIC REVIEWS, 2022, 41 (02) :207-230
[50]   Bayesian computations for random environment models [J].
Al-Mutairi, DK .
JOURNAL OF APPLIED STATISTICS, 2004, 31 (06) :645-659