P\'olygamma Data Augmentation to address Non-conjugacy in the Bayesian Estimation of Mixed Multinomial Logit Models

• Tác giả: Prateek Bansal, Michel Bierlaire, Ricardo A Daziano, Rico Krueger, Taha H Rashidi
• Ngôn ngữ: eng
• Ký hiệu phân loại: 003.75 Nonlinear systems
• Thông tin xuất bản: 2019
• Bộ sưu tập: Metadata
• ID: 162812

Tóm tắt

Comment: arXiv admin note: text overlap with arXiv:1904.03647The standard Gibbs sampler of Mixed Multinomial Logit (MMNL) models involves sampling from conditional densities of utility parameters using Metropolis-Hastings (MH) algorithm due to unavailability of conjugate prior for logit kernel. To address this non-conjugacy concern, we propose the application of P\'olygamma data augmentation (PG-DA) technique for the MMNL estimation. The posterior estimates of the augmented and the default Gibbs sampler are similar for two-alternative scenario (binary choice), but we encounter empirical identification issues in the case of more alternatives ($J \geq 3$).