A Bayesian analysis of the multinomial probit model with fully identified parameters

By Robert E. McCulloch, Nicholas G. Polson, Peter E. Rossi. 2000

307 citations recorded by the source corpus.

Subfields: Finance, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/15221e32e87168ac83af34006c85d929437bae4b

How researchers see this paper

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

In Finance

In Statistics and Probability

Citations in the corpus

K-state switching models with time-varying transition distributions—Does loan growth signal stronger effects of variables on inflation? (2015, background): “…alternatives (IIA), is readily exploitable in models in which the state or classification indicator is known (Hausman and Wise 1978, Albert and Chib 1993, Nobile 1998, McCulloch et al. 2000), because the outcome probabilities do not need to be evaluated to obtain an inference on the parameters.”
Incorporating pro-environmental preferences towards green automobile technologies through a Bayesian hybrid choice model (2013, methodology): “HCM Bayesian estimation with a probit kernel is straightforward because the properties of the normal distribution allow us to exploit data augmentation techniques, basically because the utility function follows a normal distribution (Albert and Chib 1993, McCulloch et al. 2000).”
Retrieving Unobserved Consideration Sets from Household Panel Data (2005, methodology): “At the core of our approach is a multivariate probit model (MVP, Edwards and Allenby, 2003) for consideration, compounded with a multinomial probit (MNP, McCulloch and Rossi, 1994; McCulloch et al., 2000) model for brand choice, given consideration.”
Estimating Housing Demand With an Application to Explaining Racial Segregation in Cities (2005, methodology): “In most previous work that estimated discrete choice models (e.g., Berry et al. 1995; McCulloch et al. 2000), the random coefficients are typically assumed to be independently and normally distributed, conditional on demographics.”
Bayesian inference in a sample selection model (2011, background): “The advantage of the current model formulation is that a prior is placed directly on the identified parameters; see Li (1998) and McCulloch et al. (2000), who proposed this strategy before.”
Bayesian analysis of stochastic volatility models with fat-tails and correlated errors (2004, methodology): “As observed by McCulloch et al. (2000), one can use a normal prior for and an inverse gamma for .”
MCMC Estimation of Restricted Covariance Matrices (2009, methodology): “Advances have been made in imposing a constraint on a single diagonal element of the covariance matrix as in MNP models (McCulloch, Polson, and Rossi 2000; Nobile 2000; Imai and van Dyk 2005), treatment models (Munkin and Trivedi 2003; Chib 2007), and incidental truncation models (Chib, Greenberg,…”