STAT 4010 - Bayesian Learning

Assessment and Grading 

There are three main assessment components, plus a bonus component. 

• • •  a (out of 100) is the average score of approximately eight assignments with the lowest two scores dropped; 

    • m (out of 100) is the score of mid-term exam; 

    • f (out of 100) is the score of final exam; and

    • b (out of 2) is the bonus points, which will be given to students who actively participate in class.

The total score t (out of 100) is given by 

t = min{100, 0.3a + 0.2max(m,f ) + 0.5f + b}

If min(t, f ) < 30, the final letter grade will be handled on a case-by-case basis. Otherwise, your letter grade will be in the A range if t ≥ 85, at least in the B range if t ≥ 65, at least in the C range if t ≥ 55.

Important note: For the most updated information, please always refer to the course outline announced by the course instructor in Blackboard, which shall prevail the above information if there is any discrepancy.

In-class Materials

Click (S4010/2025Spring/L) to download all in-class notes and recordings (if any). 

• Lecture 1 (9 Jan): Introduction of Bayesian philosophy, posterior calculation 

• Lecture 2 (16 Jan): Example of posterior calculation, why flat prior fails, noninformative prior

• Lecture 3 (23 Jan): Proofs of invariant priors, conjugate priors, informative priors, weakly informative priors  

• Lecture 4 (6 Feb): Exponential family mixture conjugate prior, Bayesian estimators, decision theory (luck simulation)

• Lecture 5 (13 Feb): Bayes estimator, weighted posterior mean, posterior quantile, admissibility, uniqueness of BE

• Lecture 6 (20 Feb): Admissible estimators, minimax estimators, proof of Chapter 3 

• Lecture 7 (27 Feb): Proof of Theorem 3.7, Bayesian testing, Bayse factor 

• Lecture 8 (13 Mar): Three problems of Bayesian testing, region estimation, highest posterior density 

• Lecture 9 (20 Mar): Asymptotic theory for Bayesian analysis, classical and MC methods for posterior computation   

• Lecture 10 (27 Mar): MH algorithm and examples 

• Lecture 11 (3 Apr): Convergence diagnosis for MCMC, Gibbs, MH-within-Gibbs

• Lecture 12 (10 Apr): Multiple linear regression, BF, BIC and AIC, spike-and-slab prior, LASSO

• Lecture 13 (17 Apr): Missing data mechiansim, full Bayesian approach, EM, MI, emprical Bayes

Remark:  In-class notes and recordings (if any) will be uploaded within one week after the lecture. 

Quizzes 

Click (S4010/2025Spring/Q) to download all quizzes.

• • Quiz 1: calculation of posterior 

  • Quiz 2: calculation of prior 

  • Quiz 3: Bayes estimator 

Final Exam

• • Date: 29 April (Tue) 

  • Start Time: 9:30 am

  • Duration: 3 hours

  • Location: LSB G25--G27 (Computer Lab)

  • Scope: Chapters 1--10

  • Instruction: Please read the first page of the real question paper. Some highlights are listed below: 

    • • Read the instructions carefully before doing the exam. 

      • Complete the exam on your own.

      • Internet access and any form of generative AI are not allowed during the exam. 

      • Formulas and hints (if any) are provided after the last question. 

      • Only two pieces of A4-sized, double-sided, self-prepared cheat sheets are allowed.

  • Mock: 

    • • Quick review exercise for each chapter. (Recording from 2021 Spring)

      • Mock 1: 2024 Spring F

      • Mock 1: 2023 Spring F

      • Mock 2: 2022 Spring F 

      • Mock 3: 2021 Spring F

      • Mock 4: 2019 Fall F

  • Real exam structure overview: Please refer to the Blackboard announcement.