A Comparison of Hierarchical Bayes and Maximum Simulated Likelihood for Mixed Logit

By Kenneth Train. 2001

133 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/6f94176310495a67f34d8d0e512c4e79331adf44

How researchers see this paper

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

Citations in the corpus

Uncovering the Distribution of Motorists' Preferences for Travel Time and Reliability (2005, unknown): “5 indicated, we specified the components of ζ i as normally distributed; we also tried log-normal and truncated normal distributions but similar to others (Train (2001)) we were unable to obtain convergence.”
Spatial preference heterogeneity in forest recreation (2013, background): “…distance can be viewed as a cost) is kept fixed in order to avoid a number of severe problems associated with specifying a random price parameter (Train, 2001; Hensher and Greene, 2003; 2003; Hensher et al., 2005; Hess et al., 2005; Train and Sonnier, 2005; Train and Weeks, 2005; Campbell et…”
Simulation estimation of mixed discrete choice models using randomized and scrambled Halton sequences (2003, methodology): “Fifth, it would be useful to examine the effectiveness of quasi-Monte Carlo sequences within a Bayesian estimation framework for complex discrete choice models (see Brownstone, 2000 and Train, 2001 for reviews of Bayesian estimation for discrete choice models).”
Discrete Choice Methods with Simulation by Kenneth E. Train (2003, methodology): “Comparisons performed by Vijverberg (1997) and Sándor and András (2001) show that antithetics substantially improve the estimation of probit models.”
Willingness-to-Pay Estimation with Mixed Logit Models: Some New Evidence (2005, unknown): “The two estimation procedures presented below yield the same type of results for two groups of parameters: (1) the mean and standard deviation of the parameter distributions over the population; and (2) individual-level marginal utility parameters.”
Analysis of mode choice for intercity travel: Application of a hybrid choice model to two distinct US corridors (2018, methodology): “The resulting flexibility meant that classical estimation of the model became computationally intractable and we instead relied on Bayesian estimation, using the implementation of Hierarchical Bayes (see Train, 2001 for a comparison with classical estimation) in RSGHB (Dumont & Keller, 2015).”
The Mixed Logit model: The state of practice (2003, background): “Brownstone (2001) provides a useful overview as do Chen, Shao, and Ibrahim (2000), Geweke (1999) and Train (2001).”
Mixed Logit with Bounded Distributions of Correlated Partworths (2005, methodology): “However, each estimation procedure, while feasible with bounded distributions, entails numerical difficulties that are intrinsic to its form, as described and illustrated by Train (2001).”
Combining RP and SP data: biases in using the nested logit ‘trick’: contrasts with flexible mixed logit incorporating panel and scale effects (2008, methodology): “…of the SP alternatives were found to be statistically significant and greater than one for the bus and train modes; although not statistically 4 The triangular distribution was first used for random coefficients by Train and Revelt (2000) and Train (2001), later incorporated into Train (2003).”
Choosing Between Internet and Mail Survey Modes for Choice Experiment Surveys Considering Non-Market Goods (2009, background): “…avoids a number of severe problems associated with specifying a random price parameter (see Meijer and Rouwendal 2006; Hensher et al. 2005; Hess et al. 2005; Train and Sonnier 2005; Campbell et al. 2006; Hensher and Greene 2003; Rigby and Burton 2006; Train 2003; Train and Weeks 2005, Train 2001).”
Hybrid Choice Models: Progress and Challenges (2002, methodology): “As described by Train (2001) , the simulated mean of the Bayesian posterior (SMPE) provides an alternative estimator to MSLE.”