Bayesian Analysis

Bayesian inference is a method of statistical inference in which Bayes’ theorem is used to update the probability for a hypothesis as more evidence or information becomes available. Bayesian inference is an important technique in statistics, especially in mathematical statistics.
Bayesian analysis is the most underestimated but highly power analytical tool. There is no way to get the nuts and bolts of Bayesian other than getting involved in the ugly maths of it. We have made your life easier by teaching the complex maths through simple rows and columns structure. By the end of this module you will be able to understand the following –
Familiarize with the ideas of MLE and Bayesian approach taking a Coin Toss example.
•One Dimensional Data is Normally distributed N (μ , σ2) . Estimate μ and σ using MLE
•One Dimensional Data is Normally distributed N (μ , σ2) . σ is known, estimate μ using Bayesian Analysis
•One Dimensional Data is Normally distributed N (μ , σ2) . Both μ and σ are unknown. Set up Gibbs Sampler.
•Generates sample from Posterior for μ and σ as per Gibbs Sampling method
•Generates sample from Posterior for μ and σ as per Metropolis-Hastings Sampling method

If this is not sufficient we have also covered Variable Selection through Spike and Slab Priors
Not only Regression, this module also covers Bayesian Structure Time series and its 3 most important components – Spike and Slab Regression, Kalam Filtering and Markov Chain Monte Carlo (MCMC)