Individual-specific posterior distributions from Mixed Logit models: Properties, limitations and diagnostic checks

Abstract Individual-specific posterior distributions are an attractive tool for disentangling the tastes for each person in the sample. However, there exists some risks and certain limitations regarding their use. This study reviews and summarizes the theoretical literature about the individual-specific posterior distributions derived from the Mixed Logit model, focusing on their properties, limitations and common pitfalls. It also reviews and analyzes the behavior of some diagnostic checks proposed in the literature for the reliability of such estimates in applied works using Monte Carlo experiments. Finally, this article provides reasonable guidelines for the correct use of individual-specific posterior distributions.

[1]  Jens Abildtrup,et al.  Spatial preference heterogeneity in forest recreation , 2013 .

[2]  K. Train.  Discrete Choice Methods with Simulation , 2003 .

[3]  Kenneth Train,et al.  Discrete Choice Models in Preference Space and Willingness-to Pay Space , 2005 .

[4]  Juan de Dios Ortúzar,et al.  Willingness-to-Pay Estimation with Mixed Logit Models: Some New Evidence , 2005 .

[5]  K. Train,et al.  On the Similarity of Classical and Bayesian Estimates of Individual Mean Partworths , 2000 .

[6]  Nada Wasi,et al.  COMPARING ALTERNATIVE MODELS OF HETEROGENEITY IN CONSUMER CHOICE BEHAVIOR , 2012 .

[7]  Kenneth Train,et al.  Customer-Specific Taste Parameters and Mixed Logit: Households' Choice of Electricity Supplier , 2000 .

[8]  Peter E. Rossi,et al.  Marketing models of consumer heterogeneity , 1998 .

[9]  Ricardo A. Daziano,et al.  Multinomial Logit Models with Continuous and Discrete Individual Heterogeneity in R: The gmnl Package , 2017 .

[10]  S. Hess.  Conditional parameter estimates from Mixed Logit models: distributional assumptions and a free software tool , 2010 .

[11]  Danny Campbell,et al.  Disentangling the influence of knowledge on attribute non-attendance , 2017 .

[12]  D. Hensher,et al.  Predicting Firm Financial Distress: A Mixed Logit Model , 2004 .

[13]  Michael G. Pollitt,et al.  Which smart electricity service contracts will consumers accept? The demand for compensation in a platform market , 2018 .

[14]  Stephane Hess,et al.  Posterior analysis of random taste coefficients in air travel behaviour modelling , 2007 .

[15]  R. Daziano,et al.  Individual-specific point and interval conditional estimates of latent class logit parameters , 2017, Journal of Choice Modelling.

[16]  W. Greene,et al.  Deriving Willingness-to-Pay Estimates of Travel-Time Savings from Individual-Based Parameters , 2006 .

[17]  Andrew Daly,et al.  Assuring finite moments for willingness to pay in random coefficient models , 2009 .

[18]  David A. Hensher,et al.  Using Conditioning on Observed Choices to Retrieve Individual-Specific Attribute Processing Strategies , 2010 .

[19]  John M. Rose,et al.  Applied Choice Analysis: A Primer , 2005 .

[20]  John M. Rose,et al.  Using Classical Simulation-Based Estimators to Estimate Individual WTP Values , 2005 .

[21]  Stephane Hess,et al.  Individual level models vs. sample level models: contrasts and mutual benefits , 2015 .

[22]  N. Hanley,et al.  Using Geographically Weighted Choice Models to Account for the Spatial Heterogeneity of Preferences , 2018 .

[23]  R. Scarpa,et al.  Using Choice Experiments to Explore the Spatial Distribution of Willingness to Pay for Rural Landscape Improvements , 2009 .