Quasi-random maximum simulated likelihood estimation of the mixed multinomial logit model

By Chandra R. Bhat. 2001

1,091 citations recorded by the source corpus.

Subfields: Economics and Econometrics, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/2c7f0ce257d5026d0eb1a83ecd3f16faf704765d

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 Statistics and Probability

Citations in the corpus

Trial-by-trial data analysis using computational models (2011, background): “…parameters the optimizer tries can therefore cause problems, but this can generally be addressed by using the same underlying random numbers at each evaluation (i.e., resetting the random seed to the same value each time the likelihood function is evaluated; Bhat, 2001; Ng and Jordan, 2000) .”
Discrete games with flexible information structures: an application to local grocery markets (2014, background): “The next 22For details about Halton sequences, see Bhat (2001). section uses this result to propose a test for the null hypotheses that a given θ is included in the identified set.”
Consumers’ willingness to pay for alternative fuel vehicles: A comparative discrete choice analysis between the US and Japan (2014, methodology): “Given these facts, we focus on the following six key attributes in this study: (1) purchase price premium, (2) fuel cost reduction (percentage) as compared with gasoline vehicles, (3) driving range on full battery, (4) emissions reduction (percentage) compared with gasoline vehicles, (5) alternative”
EM algorithms for nonparametric estimation of mixing distributions (2008, methodology): “…which we could have, but did not, code around.7 A Halton sequence of 10,000 points was created in the standard way (Halton 1960, as described by Bhat 2001 and Train 2003, Section 9.3.3), using the seven primes between 2 and 17, inclusive, for the 7 dimensions.8 Run time with 10,000 Halton…”
Can scale and coefficient heterogeneity be separated in random coefficients models? (2012, methodology): “2 (Doornik, 2001), using 500 Halton draws (cf. Halton, 1960; Bhat, 2001).”
Discrete Choice Experiments: A Guide to Model Specification, Estimation and Software (2017, background): “For example, in the context of mixed logit estimation, 100 Halton draws have been found to be more accurate than 1000 pseudo-random draws [48, 49].”
Joint Analysis of Injury Severity of Drivers in Two-Vehicle Crashes Accommodating Seat Belt Use Endogeneity (2013, methodology): “In this paper, we adopt the most commonly used GHK (GewekeHajivassiliou-Keane) simulator (see Geweke, 1991, Hajivassiliou and McFadden, 1998, and Keane, 1994), but by enhancing it through the use of Halton draws rather than pseudo-random draws (see Bhat, 2011 and Bhat et al., 2010 for extensive disc”
Consumers' willingness to pay for renewable and nuclear energy: A comparative analysis between the US and Japan (2015, methodology): “Bhat (2001) found that 100 Halton sequence draws are efficient for simulating an ML model with over 1,000 random draws. global warming.”
BIOGEME: a free package for the estimation of discrete choice models (2003, methodology): “Train, 1997, Bhat, 2001, Ben-Akiva et al., 2002) combine dierent model structures”
A joint econometric framework for modeling crash counts by severity (2018, background): “…Halton sequence to approximate this integral in the likelihood function and maximize the logarithm of the resulting simulated likelihood function across individuals (see Bhat 2001; Eluru, Bhat, and Hensher 2008; Yasmin and Eluru 2013 for examples of Quasi-Monte Carlo approaches in literature).”
Incorporating Discontinuous Preferences into the Analysis of Discrete Choice Experiments (2008, background): “For further details on Halton sequences see Bhat (2001) and Train (2003).”