Bayesian Estimation of Linear Sum Assignment Problems
Essays in Honor of Cheng Hsiao
ISBN: 978-1-78973-958-9, eISBN: 978-1-78973-957-2
Publication date: 15 April 2020
Abstract
The authors propose an Markov Chain Monte Carlo (MCMC) method for estimating a class of linear sum assignment problems (LSAP; the discrete case of the optimal transport problems). Prominent examples include multi-item auctions and mergers in industrial organizations. This contribution is to decompose the joint likelihood of the allocation and prices by exploiting the primal and dual linear programming formulation of the underlying LSAP. Our decomposition, coupled with the data augmentation technique, leads to an MCMC sampler without a repeated model-solving phase.
Keywords
Acknowledgements
Acknowledgments
We thank Hashem Pesaran, Dek Terrell, and the conference participants of Advance in Econometrics in honor of Prof. Cheng Hsiao for helpful comments. Our special thank goes to Sha Yang for her valuable input to this chapter.
Citation
Hsieh, Y.-W. and Shum, M. (2020), "Bayesian Estimation of Linear Sum Assignment Problems", Li, T., Pesaran, M.H. and Terrell, D. (Ed.) Essays in Honor of Cheng Hsiao (Advances in Econometrics, Vol. 41), Emerald Publishing Limited, Leeds, pp. 323-339. https://doi.org/10.1108/S0731-905320200000041011
Publisher
:Emerald Publishing Limited
Copyright © 2020 Emerald Publishing Limited