方法对比

	共轭先验分析	Bayesian Regression	经验贝叶斯	马尔可夫链蒙特卡洛 (MCMC)
领域	贝叶斯	贝叶斯	贝叶斯	贝叶斯
方法族	Bayesian methods	Bayesian methods	Bayesian methods	Bayesian methods
起源年份	1961	—	—	—
提出者	Raiffa & Schlaifer (1961); DeGroot (1970)	—	Herbert Robbins (1956); Bradley Efron & Carl Morris (1973)	—
类型	Closed-form Bayesian model	Bayesian linear model	Empirical Bayes estimator	Posterior sampling algorithm
开创性文献	Raiffa, H. & Schlaifer, R. (1961). Applied Statistical Decision Theory. Harvard University Press. ISBN: 978-0-87584-017-8	Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A. & Rubin, D. B. (2013). Bayesian Data Analysis (3rd ed.). CRC Press. ISBN: 978-1439840955	Robbins, H. (1956). An empirical Bayes approach to statistics. In J. Neyman (Ed.), Proceedings of the Third Berkeley Symposium on Mathematical Statistics and Probability, Vol. 1 (pp. 157–164). University of California Press.	Gelman, A., Carlin, J. B., Stern, H. S., Dunson, D. B., Vehtari, A. & Rubin, D. B. (2013). Bayesian Data Analysis (3rd ed.). CRC Press. ISBN: 978-1439840955
别名	conjugate priors, conjugate Bayesian updating, closed-form posterior analysis, Beta-Binomial model	bayesian linear regression, probabilistic regression, bayesian regresyon	EB, empirical Bayes estimation, marginal likelihood estimation, James-Stein shrinkage	markov chain monte carlo, MCMC sampling, MCMC (Markov Zinciri Monte Carlo)
相关	3	2	4	3
摘要	Conjugate prior analysis is a class of Bayesian inference methods in which the prior distribution and the likelihood belong to a matched family — called a conjugate pair — so that the posterior distribution has exactly the same functional form as the prior and can be derived in closed form. Introduced systematically by Raiffa and Schlaifer (1961) and consolidated by DeGroot (1970), conjugate analysis is the pedagogic backbone of introductory Bayesian statistics and a practical tool whenever analytical tractability is required.	Bayesian regression is a probabilistic version of linear regression that treats the model parameters as uncertain quantities. Instead of returning a single best-fit estimate, it combines prior knowledge with the observed data to produce a full posterior probability distribution for each parameter, from which credible intervals and predictions are read off.	Empirical Bayes (EB) is an estimation strategy, introduced by Herbert Robbins in 1956 and developed into practical shrinkage estimators by Bradley Efron and Carl Morris in 1973, in which the hyperparameters of the prior distribution are estimated from the observed data via the marginal likelihood rather than specified in advance. The resulting posterior retains a Bayesian structure but substitutes data-driven hyperparameters for subjective ones, bridging frequentist shrinkage and full Bayesian inference.	Markov Chain Monte Carlo (MCMC) is a family of computational algorithms for sampling from complex probability distributions, most commonly the posterior distributions that arise in Bayesian inference. Rather than computing posteriors analytically — which is rarely possible for realistic models — MCMC constructs a Markov chain whose stationary distribution is the target posterior and draws dependent samples from it, enabling full probabilistic inference for virtually any model.