EM algorithms for nonparametric estimation of mixing distributions
Reads0
Chats0
TLDR
In this article, the authors describe and implement three computationally attractive procedures for nonparametric estimation of mixing distributions in discrete choice models, which are specific types of the well known EM (Expectation-Maximization) algorithm based on three different ways of approximating the mixing distribution nonparametrically.Abstract:
This paper describes and implements three computationally attractive procedures for nonparametric estimation of mixing distributions in discrete choice models. The procedures are specific types of the well known EM (Expectation-Maximization) algorithm based on three different ways of approximating the mixing distribution nonparametrically: (1) a discrete distribution with mass points and frequencies treated as parameters, (2) a discrete mixture of continuous distributions, with the moments and weight for each distribution treated as parameters, and (3) a discrete distribution with fixed mass points whose frequencies are treated as parameters. The methods are illustrated with a mixed logit model of households' choices among alternative-fueled vehicles.read more
Citations
More filters
Journal ArticleDOI
Assuring Finite Moments for Willingness to Pay in Random Coefficient Models
TL;DR: In this article, the authors identify a criterion to determine whether, with a given distribution for the cost coefficient, the distribution of WTP has finite moments, and they show that some popular distributions used for WTP in random coefficient models, including normal, truncated normal, uniform and triangular, imply infinite moments for the distribution, even if truncated or bounded at zero.
Journal ArticleDOI
Are consumers willing to pay to let cars drive for them? Analyzing response to autonomous vehicles
TL;DR: Semiparametric random parameter logit estimates suggest that the demand for automation is split approximately evenly between high, modest and no demand, highlighting the importance of modeling flexible preferences for emerging vehicle technology.
Assuring Finite Moments for Willingness to Pay in Random Coefficient Models
TL;DR: In this paper, the authors identify a criterion to determine whether the distribution of WTP has finite moments, and they show that some popular distributions used for the cost coefficient in random coefficient models, including normal, truncated normal, uniform and triangular, imply infinite moments for WTP, even if truncated or bounded at zero.
Journal ArticleDOI
A choice experiment on alternative fuel vehicle preferences of private car owners in the Netherlands
Anco Hoen,Mark J. Koetse +1 more
TL;DR: In this article, the authors present results of an online stated choice experiment on preferences of Dutch private car owners for alternative fuel vehicles (AFVs) and their characteristics, and show that negative preferences for AFVs are large, especially for the electric and fuel cell car, mostly due to their limited driving range and considerable refueling times.
Journal ArticleDOI
Comparing alternative models of heterogeneity in consumer choice behavior
Michael Keane,Nada Wasi +1 more
TL;DR: In this article, the authors compare the performance of six alternative models, i.e., generalized multinomial logit (G-MNL), mixed-mixed-mixture (MM-MMNL), scale heterogeneity logit, latent class (LC), and T-MIXL, and find that none of these models dominates the others.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Book
Discrete Choice Methods with Simulation
TL;DR: In this paper, the authors describe the new generation of discrete choice methods, focusing on the many advances that are made possible by simulation, and compare simulation-assisted estimation procedures, including maximum simulated likelihood, method of simulated moments, and methods of simulated scores.
Book
The EM algorithm and extensions
TL;DR: The EM Algorithm and Extensions describes the formulation of the EM algorithm, details its methodology, discusses its implementation, and illustrates applications in many statistical contexts, opening the door to the tremendous potential of this remarkably versatile statistical tool.
Journal ArticleDOI
Mixed mnl models for discrete response
Daniel McFadden,Kenneth Train +1 more
TL;DR: In this article, the adequacy of a mixing specification can be tested simply as an omitted variable test with appropriately definedartificial variables, and a practicalestimation of aarametricmixingfamily can be run by MaximumSimulated Likelihood EstimationorMethod ofSimulatedMoments, andeasilycomputedinstruments are provided that make the latter procedure fairly eAcient.
Journal ArticleDOI
On the convergence properties of the em algorithm
TL;DR: In this paper, the EM algorithm converges to a local maximum or a stationary value of the (incomplete-data) likelihood function under conditions that are applicable to many practical situations.