Hierarchical Bayes versus Finite Mixture Conjoint Analysis Models: A Comparison of Fit, Prediction, and Partworth Recovery

By Rick L. Andrews, Asim Ansari, Imran S. Currim. 2002

205 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Marketing, Organizational Behavior and Human Resource Management

View Paper: https://www.semanticscholar.org/paper/412832351dc5a2d9626c844f81e2752639ffd955

How researchers see this paper

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

In Economics and Econometrics

In Marketing

In Organizational Behavior and Human Resource Management

Citations in the corpus

A Comparison of Segment Retention Criteria for Finite Mixture Logit Models (2003, methodology): “…the emergence of Bayesian error components models and other random coefficient procedures in recent years, applications of finite mixture models still accumulate (Wedel and Kamakura 2000) and should continue to do so given new evidence of their effectiveness (Andrews, Ansari, and Currim 2002).”
Latent Class Models (2004, unknown): “In conclusion, the LC regression model offers computational and interpretive advantages over the more traditional hierarchical modeling approach that tends to overfit data (Andrews, Ansari, and Currim, 2002).”
Enhancing Marketing with Engineering: Optimal Product Line Design for Heterogeneous Markets (2011, unknown): “…the discrete mixture is natively supported in many statistical packages, it might prove convenient for line optimization; recent literature suggests that discrete and continuous heterogeneity can often represent preferences about equally well (Rossi, Allenby & McCulloch 2005, Andrews et al. 2002).”
Evaluating farmers’ likely participation in a payment programme for water quality protection in the UK uplands (2013, methodology): “Following Swait (1994), Andrews et al. (2002) and Boxall and Adamowicz’s (2002) description of the primary attraction of the LCM being its ability to provide an interpretable depiction of heterogeneity, the statistical measures of fit, the interpretive simplicity and relevance of the segmentation…”
Foundations of Stated Preference Elicitation: Consumer Behavior and Choice-based Conjoint Analysis (2019, methodology): “…stated preference elicitation methods, and is relevant to questions of CBC reliability; see Acito and Jain (1980), Akaah and Korgaonkar (1983), Andrews et al. (2002), Carmone et al. (1978), Hauser et al. (1979,2002), Huber et al. (1993), Louvier (1988), Neslin (1981), Jain et al. (1979),…”
Linking Marketing and Engineering Product Design Decisions via Analytical Target Cascading (2005, methodology): “Andrews et al. (2002b) provided a full discussion of these issues specifically in the context of conjoint.”
Policy measures to promote electric mobility – A global perspective (2015, methodology): “Further, CA has frequently been refined over the past few decades, and one of the prevailing methods is the choice-based conjoint analysis with hierarchical Bayesian estimation (CBC/HB; Andrews et al., 2002; Arora et al., 1998; Lenk et al., 1996).”
Destination Choice Models for Rock Climbing in the Northeastern Alps: A Latent-Class Approach Based on Intensity of Preferences (2005, background): “The empirical evidence over continuous versus finite mixing distributions is still inconclusive, and the debate is still open ( Andrews, Ansari, and Currim 2002 ), although it is likely to remain a sample-specific empirical issue.”
The Strength of Strong Ties in an Emerging Industry: Experimental Evidence of the Effects of Status Hierarchies and Personal Ties in Venture Capitalist Decision Making: The Strength of Strong Ties (2015, unknown): “In a conjoint context, comparisons show that rating-based conjoint analyses using hierarchical Bayes outperform frequentist-based estimations in terms of hit rate (e.g., Andrews, Ansari, and Currim, 2002; Lenk et al., 1996; Moore, Gray-Lee, and Louviere, 1998).”
Leveraging Missing Ratings to Improve Online Recommendation Systems (2006, background): “Although marketing researchers have used both finite mixture and hierarchical Bayes models to capture customer heterogeneity, several studies suggest that these models offer roughly equal performance in various empirical settings (Andrews, Ansari, and Currim 2002; Wedel et al. 1999).”