Week 5

Lecture

• Lecture #8: Metropolis-Hastings and Gibbs
  • Lecture Video
  • Lecture Notes
  • Lecture Summary
• Lecture #9: Latent Variable Models and MLE
  • Lecture Video
  • Lecture Notes

Activities

• In-Class Exercise #8: Metropolis-Hastings and Gibbs Sampling
• In-Class Exercise #8: Solutions
• In-Class Exercise #9: Expectation Maximization
• Homework #4
• Homework #4 Solutions

Reading

Applications and Broader Impact:

1. Item Response Theory for assessing students and questions (pt. 1)
2. Simultaneous Discovery, Estimation and Prediction Analysis of Complex Traits Using a Bayesian Mixture Model
3. Parkinson’s Disease Subtypes in the Oxford Parkinson Disease Centre (OPDC) Discovery Cohort
4. One Size Doesn’t Fit All: Using Factor Analysis to Gather Validity Evidence When Using Surveys in Your Research

MCMC Diagnostics:

1. (Introductory) Markov Chain Monte Carlo (MCMC) Diagnostics
2. (In-Depth) Convergence diagnostics for Markov chain Monte Carlo
3. (Opinion) On the Bogosity of MCMC Diagnostics

More on Thinning:

1. (Thinning is bad!) On Thinning of Chains in MCMC
2. (Thinning can be good!) Statistically efficient thinning of a Markov chain sampler

More on Chain Length:

1. (The longer the better? Not always) Unbiased Markov chain Monte Carlo with couplings

Latent Variable Models:

1. (Introductory) Build, Compute, Critique, Repeat: Data Analysis with Latent Variable Models
2. (Introductory) Theory and Use of the EM Algorithm