|
所在平台: Coursera |
课程主页: https://www.coursera.org/learn/mcmc-bayesian-statistics
课程评论：没有评论
课程名称：贝叶斯统计：技术与模型 课程概述： 本课程是贝叶斯统计两门课程系列中的第二门，旨在介绍贝叶斯统计的基本原理。它在课程“贝叶斯统计：从概念到数据分析”的基础上展开，后者通过使用简单的共轭模型介绍贝叶斯方法。现实世界的数据往往需要更复杂的模型来得出现实的结论。该课程的目标是扩展我们的“贝叶斯工具箱”，引入更一般的模型以及拟合它们的计算技术。特别地，我们将介绍马尔科夫链蒙特卡洛（MCMC）方法，这些方法允许从没有解析解的后验分布中进行采样。我们将使用开源且免费提供的软件R（假定有一定经验，例如完成之前的R课程）和JAGS（无需经验）。课程将教授如何构建、拟合、评估和比较贝叶斯统计模型，以回答涉及连续、二元和计数数据的科学问题。该课程结合了讲座视频、计算机演示、阅读材料、练习和讨论板，为学员创造了一个积极的学习体验。讲座提供了一些基本的数学发展、统计建模过程解释以及统计学家常用的基本建模技术。计算机演示提供了具体的实用操作指导。完成本课程后，学员将获得一系列可针对自身数据定制的贝叶斯分析工具。 课程大纲： 1. 统计建模与蒙特卡洛估计 描述：统计建模、贝叶斯建模、蒙特卡洛估计 2. 马尔科夫链蒙特卡洛（MCMC） 描述：Metropolis-Hastings方法、Gibbs抽样、收敛性评估 3. 常见统计模型 描述：线性回归、方差分析（ANOVA）、逻辑回归、多因素方差分析 4. 计数数据和层次建模 描述：泊松回归、层次建模 5. 总结项目 描述：同行评审的数据分析项目
Name:Statistical modeling and Monte Carlo estimation
Description:Statistical modeling, Bayesian modeling, Monte Carlo estimation
Name:Markov chain Monte Carlo (MCMC)
Description:Metropolis-Hastings, Gibbs sampling, assessing convergence
Name:Common statistical models
Description:Linear regression, ANOVA, logistic regression, multiple factor ANOVA
Name:Count data and hierarchical modeling
Description:Poisson regression, hierarchical modeling
Name:Capstone project
Description:Peer-reviewed data analysis project
This is the second of a two-course sequence introducing the fundamentals of Bayesian statistics. It builds on the course Bayesian Statistics: From Concept to Data Analysis, which introduces Bayesian methods through use of simple conjugate models. Real-world data often require more sophisticated models to reach realistic conclusions. This course aims to expand our “Bayesian toolbox” with more general models, and computational techniques to fit them. In particular, we will introduce Markov chain Monte Carlo (MCMC) methods, which allow sampling from posterior distributions that have no analytical solution. We will use the open-source, freely available software R (some experience is assumed, e.g., completing the previous course in R) and JAGS (no experience required). We will learn how to construct, fit, assess, and compare Bayesian statistical models to answer scientific questions involving continuous, binary, and count data. This course combines lecture videos, computer demonstrations, readings, exercises, and discussion boards to create an active learning experience. The lectures provide some of the basic mathematical development, explanations of the statistical modeling process, and a few basic modeling techniques commonly used by statisticians. Computer demonstrations provide concrete, practical walkthroughs. Completion of this course will give you access to a wide range of Bayesian analytical tools, customizable to your data.
