Bayesian Analysis of Random Coefficient Logit Models Using Aggregate Data

2008 ◽  
Author(s):  
Renna Jiang ◽  
Puneet Manchanda ◽  
Peter E. Rossi
Keyword(s):  
Bayesian Analysis ◽  
Aggregate Data ◽  
Random Coefficient ◽  
Logit Models ◽  
Random Coefficient Logit

Bayesian analysis of random coefficient logit models using aggregate data

2009 ◽  
Vol 149 (2) ◽  
pp. 136-148 ◽  
Author(s):  
Renna Jiang ◽  
Puneet Manchanda ◽  
Peter E. Rossi
Keyword(s):  
Bayesian Analysis ◽  
Aggregate Data ◽  
Random Coefficient ◽  
Logit Models ◽  
Random Coefficient Logit

scholarly journals Monte Carlo Simulation in Random Coefficient Logit Models Involving Large Sums

2013 ◽  
Vol 1 (1) ◽  
pp. 85-108
Author(s):  
Zsolt Sándor
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Monte Carlo Methods ◽  
Mean Squared Error ◽  
Mixed Logit ◽  
Random Coefficient ◽  
Consumer Information ◽  
Logit Models ◽  
Quasi Monte Carlo ◽  
Random Coefficient Logit

Abstract We study Monte Carlo simulation in some recent versions of random coefficient logit models that contain large sums of expressions involving multivariate integrals. Such large sums occur in the random coefficient logit with demographic characteristics, the random coefficient logit with limited consumer information and the design of choice experiments for the panel mixed logit. We show that certain quasi-Monte Carlo methods, that is, so-called (t, m, s)-nets, provide improved performance over pseudo-Monte Carlo methods in terms of bias, standard deviation and root mean squared error.

Simulated Maximum Likelihood Estimator for the Random Coefficient Logit Model Using Aggregate Data

2009 ◽  
Vol 46 (4) ◽  
pp. 531-542 ◽  
Author(s):  
Sungho Park ◽  
Sachin Gupta
Keyword(s):  
Maximum Likelihood ◽  
Logit Model ◽  
Regime Switching ◽  
Control Function ◽  
Sampling Error ◽  
Estimation Method ◽  
Aggregate Data ◽  
Random Coefficient ◽  
Simulated Maximum Likelihood ◽  
Random Coefficient Logit

The authors propose a simulated maximum likelihood estimation method for the random coefficient logit model using aggregate data, accounting for heterogeneity and endogeneity. The method allows for two sources of randomness in observed market shares: unobserved product characteristics and sampling error. Because of the latter, the method is suitable when sample sizes underlying the shares are finite. In contrast, Berry, Levinsohn and Pakes's commonly used approach assumes that observed shares have no sampling error. The method can be viewed as a generalization of Villas-Boas and Winer's approach and is closely related to Petrin and Train's “control function” approach. The authors show that the proposed method provides unbiased and efficient estimates of demand parameters. They also obtain endogeneity test statistics as a by-product, including the direction of endogeneity bias. The model can be extended to incorporate Markov regime-switching dynamics in parameters and is open to other extensions based on maximum likelihood. The benefits of the proposed approach are achieved by assuming normality of the unobserved demand attributes, an assumption that imposes constraints on the types of pricing behaviors that are accommodated. However, the authors find in simulations that demand estimates are fairly robust to violations of these assumptions.

Bayesian analysis in random coefficient m-group regression

1987 ◽  
Vol 5 (2) ◽  
pp. 135-142 ◽  
Author(s):  
William G. Fortney ◽  
Robert B. Miller
Keyword(s):  
Bayesian Analysis ◽  
Random Coefficient ◽  
Group Regression
Sign in / Sign up

Export Citation Format

Share Document