Halton Sequences for Mixed Logit

By Kenneth Train. 2000

561 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/dafe6644c686d7e6950941223d33ef0677624228

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

Foundations of Stated Preference Elicitation: Consumer Behavior and Choice-based Conjoint Analysis (2019, methodology): “We specified 100 Halton draws per person, which has been shown to be more accurate for mixed logit estimation than 1000 pseudo-random draws per person (Bhat, 2001; Train, 2000, 2009).”
Customer-Specific Taste Parameters and Mixed Logit: Households' Choice of Electricity Supplier (2000, background): “6 See Bhat, 1999, and Train, 1999, for a discussion of Halton draws with mixed logit.”
Disaggregate Behavioral Travel Demand's RUM Side A 30-Year Retrospective (2000, methodology): “This approach to estimation benefitted from a great of research in the decade on various practical simulators, including the use of Gibbs, ngs, and other Monte Carlo Markov Chain samplers, use of pseudo-random patterned random numbers such as Halton Sobel sequences, and tools such as the EM algorith”
High Performance Quadrature Rules: How Numerical Integration Affects a Popular Model of Product Differentiation (2011, methodology): “14The current industry standard is to use Halton draws and Kenneth Train’s code, which is available on his website(Train, 1999).”
Valuing wetland attributes: an application of choice experiments (2003, methodology): “This reflects an underlying assumption of stable preference structures for all individuals (Train, 1999a).”
A UNIFIED MIXED LOGIT FRAMEWORK FOR MODELING REVEALED AND STATED PREFERENCES: FORMULATION AND APPLICATION TO CONGESTION PRICING ANALYSIS IN THE SAN FRANCISCO BAY AREA (2002, methodology): “More general structures for qitzµ′ in equation (1) are presented by Ben-Akiva and Bolduc (1996), and Brownstone and Train (1999).”
Best practices for differentiated products demand estimation with PyBLP (2020, background): “9McFadden and Train (2000) show that any random utility model (RUM) can be approximated with some mixture of multinomial logits with a sufficient basis of characteristics xjt.”
MIXED MNL MODELS FOR DISCRETE RESPONSE (2000, methodology): “This requires more computation than a MNL base model; see Train (1995) .”
On the use of a Modified Latin Hypercube Sampling (MLHS) method in the estimation of a Mixed Logit Model for vehicle choice (2006, methodology): “Finally, it should be noted that the use of pseudo-random draws leads to surprisingly good relative performance, given earlier results, for example by Bhat (1999) and Train (1999).”
Discrete Choice Methods with Simulation (2016, methodology): “Comparisons performed by Vijverberg (1997) and Sandor and Andras (2001) show that antithetics substantially improve the estimation of probit models.”
Alternative sampling methods for estimating multivariate normal probabilities (2003, methodology): “Other applications (Bhat, 2001, 2003; Train, 2000, 2002) employ the Halton sequence or its randomized version (described in Section 2.3 below) for estimating probabilities arising in logit models with random coeecients (Revelt and Train, 1998).”
Economic valuation of cultural heritage sites: A choice modeling approach (2010, methodology): “One hundred Halton draws (K. Train, 1999) were applied to simulate distributions that were assumed to be normal, and panel formulation was used to distinguish answers from the same respondents.”