方法对比

	带缺失数据的Metropolis-Hastings算法	Metropolis-Hastings算法
领域	贝叶斯	贝叶斯
方法族	Bayesian methods	Bayesian methods
起源年份	1953 / 1987	1953
提出者	Metropolis et al. (1953); missing-data extension formalised by Tanner & Wong (1987)	Metropolis et al. (1953); generalised by Hastings (1970)
类型	MCMC sampler with latent-variable augmentation	Markov chain Monte Carlo sampler
开创性文献	Tanner, M. A. & Wong, W. H. (1987). The calculation of posterior distributions by data augmentation. Journal of the American Statistical Association, 82(398), 528-540.	Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. (1953). Equation of state calculations by fast computing machines. The Journal of Chemical Physics, 21(6), 1087–1092.
别名	MH with missing data, Metropolis-Hastings data augmentation, MCMC missing data imputation, MH data-augmentation sampler	MH algorithm, M-H algorithm, Metropolis algorithm, Metropolis-Hastings sampler
相关	6	5
摘要	Metropolis-Hastings with missing data treats unobserved values as latent variables and samples them jointly with model parameters inside a single MCMC chain. By augmenting the target distribution to include both parameters and missing values, the algorithm yields properly calibrated posterior inference without discarding incomplete cases or requiring a separate imputation step.	The Metropolis-Hastings (MH) algorithm is a general-purpose Markov chain Monte Carlo (MCMC) method for drawing samples from any probability distribution whose density can be evaluated up to a normalising constant. Introduced by Metropolis, Rosenbluth, Rosenbluth, Teller, and Teller (1953) in computational physics and generalised by Hastings (1970) to asymmetric proposal distributions, it is the foundational algorithm from which nearly all subsequent MCMC samplers — Gibbs sampling, Hamiltonian Monte Carlo, slice sampling — are derived or can be viewed as special cases.