Statistical Inference for Intractable Count Distributions
Resumen
Markov chain Monte Carlo (MCMC) is routinely used to perform Bayesian inference for a wide range of complex models (see [1]). However, in Bayesian models with intractable normalising distributions — where the normalising constant lacks a closed-form expression — standard MCMC methods face significant challenges, with no definitive solution. To illustrate this, consider a posterior density of the usual form: [...]
Descargas
Citas
S. Brooks, A. Gelman, G. Jones, and X. Meng, eds. Handbook of Markov chain Monte Carlo. Chapman & Hall/CRC Handbooks of Modern Statistical Methods. Boca Raton: CRC Press, 2011. isbn: 9781420079425. doi: 10.1201/b10905.
L. M. Carvalho, W. J. Silva, and G. A. Moreira. “Adaptive truncation of infinite sums: applications to Statistics”. In: arXiv preprint arXiv:2202.06121 (Feb. 2022).
G. Shmueli, T. P. Minka, J. B. Kadane, S. Borle, and P. Boatwright. “A useful distribution for fitting discrete data: revival of the Conway–Maxwell–Poisson distribution”. In: Journal of the Royal Statistical Society: Series C (Applied Statistics) 54.1 (Jan. 2005), pp. 127–142. doi: 10.1111/j.1467-9876.2005.00474.x.
