Bayesian Statistics and Marketing

By Peter E. Rossi, Greg M. Allenby. 2005

1,697 citations recorded by the source corpus.

Bayesian methods have become widespread in marketing literature. We review the essence of the Bayesian approach and explain why it is particularly useful for marketing problems. While the appeal of the Bayesian approach has long been noted by researchers, recent developments in computational methods and expanded availability of detailed marketplace data has fueled the growth in application of Bayesian methods in marketing. We emphasize the modularity and flexibility of modern Bayesian approaches. The usefulness of Bayesian methods in situations in which there is limited information about a large number of units or where the information comes from different sources is noted. We include an extensive discussion of open issues and directions for future research.

Subfields: Management Science and Operations Research, Marketing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Management Science and Operations Research

In Marketing

Citations in the corpus

Whatever the customer wants, the customer gets? Exploring the gap between consumer preferences and default electricity products in Germany (2013, methodology): “The estimation of the partworth vector is done by an iterative process using Markov Chain Monte Carlo, which is a numerical method for computing integrals (Rossi et al., 2005).”
A Bayesian approach for envelope models (2017, methodology): “We consider two versions: the Bayesian standard model, which refers to a Bayesian envelope model with u = r (see Remark 1); and the Bayesian Wishart standard model, which specifies an inverse Wishart distribution for # and a matrix normal prior for β | # (see [12], page 33).”
A Bayesian mixed logit-probit model for multinomial choice (2008, methodology): “For assessing convergence, we use the criterion given in Allenby, Rossi, and McCulloch (2005) characterizing draws as having the same mean value and variability over iterations.”
Nonparametric identification and estimation of random coefficients in multinomial choice models (2016, background): “Even papers that emphasizes the flexibility of a particular specification for heterogeneity do not formally prove identification (McFadden and Train, 2000; Rossi et al., 2005; Burda et al., 2008; Train, 2008).”
Assortment Optimization Under General Choice (2011, neutral): “The conditions are from Rusmevichientong et al. (2010). The proof is challenging and requires careful exploitation of the MNL structure that was established in Rusmevichientong et al.”
The random coefficients logit model is identified (2012, methodology): “…least squares for models with both homogeneous parameters α and a distribution of heterogeneous parameters β. 7As a referee points out, the sign restriction or the monotonicity assumption for a special regressor may not be too restrictive because it is testable and the sign can be…”
Bayesian forecasting in economics and finance: A modern review (2022, methodology): “Electronic Journal of Statistics, 10(2):3265–3286. Capone, A., Helminger, C., and Hirche, S. (2020). Day-ahead scheduling of thermal storage systems using Bayesian neural networks.”
Discrete Choice Modeling (2007, background): “There have been many other functional forms proposed for count data models, including the generalized Poisson, gamma, and Polya-Aeppli forms described in Winkelmann (2003) and Greene (2007a, Chapter 24).”
Foundations of Stated Preference Elicitation: Consumer Behavior and Choice-based Conjoint Analysis (2019, methodology): “Additional efficiency may be achievable using Monte Carlo Markov Chain (MCMC) methods, see Tierney (1994), Albert and Chib (1996), and Chib and Greenberg (1996), and McFadden (1996).”
Graphical Multi-Task Learning (2008, positive): “Task similarity is leveraged by allowing the examples from one task to inuence the training of other tasks: for example, in a hierarchical Bayes framework, tasks share hyperparameters ( Rossi & Allenby, 2003; Yu et al., 2005); in neural networks, tasks share hidden layers, allowing joint learning o”
Understanding Large-Scale Dynamic Purchase Behavior (2020, positive): “Traditionally, this problem has been circumvented by using Markov chain Monte Carlo (MCMC) methods (Rossi and Allenby 2003), in which the posterior 6 In our notation we implicitly condition on other exogenous information that is available, i.e. the parameters describing the prior distribution p(Ω)…”
COMPARING ALTERNATIVE MODELS OF HETEROGENEITY IN CONSUMER CHOICE BEHAVIOR (2012, methodology): “Figure 5.7 in Rossi et al (2005) provides a nice illustration of how flexible the distribution of household posterior means can be in a mixture-of-normals model compared to standard MIXL.”
Sentence-Based Text Analysis for Customer Reviews (2016, methodology): “As discussed in the appendix, we post-process the draws from the MCMC chain, arbitrarily picking one of the topics to form a contrast for the remaining topics (see Rossi et al. (2005), Chapter 4).”