Module also offered within study programmes:
General information:
Name:
Advanced statistical modelling and data analysis
Course of study:
2019/2020
Code:
ZSDA-3-0040-s
Faculty of:
Szkoła Doktorska AGH
Study level:
Third-cycle studies
Specialty:
-
Field of study:
Szkoła Doktorska AGH
Semester:
0
Profile of education:
Academic (A)
Lecture language:
English
Form and type of study:
Full-time studies
Course homepage:
 
Responsible teacher:
dr hab. inż. Baranowski Jerzy (jb@agh.edu.pl)
Dyscypliny:
Moduł multidyscyplinarny
Module summary

The goal of the course is to familiarize PhD students with advanced computational models used in Bayesian statistics. The main focus is on Hamiltonian Monte Carlo methods and their implementation in Stan

Description of learning outcomes for module
MLO code Student after module completion has the knowledge/ knows how to/is able to Connections with FLO Method of learning outcomes verification (form of completion)
Social competence: is able to
M_K001 Student knows how to critically asses and communicate scientific results. SDA3A_K01 Activity during classes
Skills: he can
M_U001 Student is able to critically analyze a scientific paper and present it contents to others with a special focus on statistical results. SDA3A_U05, SDA3A_U01, SDA3A_U04 Activity during classes
Knowledge: he knows and understands
M_W001 Student knows advanced methodologies of statistical modelling in the Bayesian paradigm SDA3A_W03, SDA3A_W01 Activity during classes
M_W002 Student knows about Hamiltonian Monte Carlo methods and their difference from the classical MCMC. SDA3A_W03, SDA3A_W01 Activity during classes
Number of hours for each form of classes:
Sum (hours)
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
18 9 0 0 0 0 9 0 0 0 0 0
FLO matrix in relation to forms of classes
MLO code Student after module completion has the knowledge/ knows how to/is able to Form of classes
Lecture
Audit. classes
Lab. classes
Project classes
Conv. seminar
Seminar classes
Pract. classes
Zaj. terenowe
Zaj. warsztatowe
Prace kontr. przejść.
Lektorat
Social competence
M_K001 Student knows how to critically asses and communicate scientific results. - - - - - + - - - - -
Skills
M_U001 Student is able to critically analyze a scientific paper and present it contents to others with a special focus on statistical results. - - - - - + - - - - -
Knowledge
M_W001 Student knows advanced methodologies of statistical modelling in the Bayesian paradigm + - - - - + - - - - -
M_W002 Student knows about Hamiltonian Monte Carlo methods and their difference from the classical MCMC. - - - - - - - - - - -
Student workload (ECTS credits balance)
Student activity form Student workload
Summary student workload 54 h
Module ECTS credits 3 ECTS
Udział w zajęciach dydaktycznych/praktyka 18 h
Preparation for classes 18 h
Realization of independently performed tasks 18 h
Module content
Lectures (9h):
  1. Main concepts of Bayesian data analysis
  2. Monte Carlo Methods
  3. Using Stan in data analysis
Seminar classes (9h):
Presentation and discussion of statistics applications

PhD Students are assigned research papers, which they study and present them to the gropup. Topics are dis

Additional information
Teaching methods and techniques:
  • Lectures: The content of the lecture is presented in the form of a multimedia presentation in combination with a classic blackboard lecture enriched with shows related to the presented issues.
  • Seminar classes: Multimedia presentation and discussion
Warunki i sposób zaliczenia poszczególnych form zajęć, w tym zasady zaliczeń poprawkowych, a także warunki dopuszczenia do egzaminu:

Lectures – attendance
Seminars – the quality of presentation, and understanding and presentation of the concepts in the assigned papers.

Participation rules in classes:
  • Lectures:
    – Attendance is mandatory: Yes
    – Participation rules in classes: Students participate in classes learning the next teaching content according to the subject syllabus. Students should keep asking questions and clarifying doubts. Audiovisual registration of the lecture requires the teacher's consent.
  • Seminar classes:
    – Attendance is mandatory: Yes
    – Participation rules in classes: Students participate in seminars and participate in discussion
Method of calculating the final grade:

The grade will be established mostly on the discussion participation and the presentation of the assigned papers.

Sposób i tryb wyrównywania zaległości powstałych wskutek nieobecności studenta na zajęciach:

Individually determined with the lecturer based on length and reasons of absence.

Prerequisites and additional requirements:

Basics of statistics, knowledge or either R or Python.

Recommended literature and teaching resources:
  1. Edwin Thompson Jaynes. Probability Theory: The Logic of Science. Cambridge University Press, (2003).
  2. Devinderjit Sivia, John Skilling. Data Analysis: A Bayesian Tutorial. Oxford University Press; 2 edition, (2006)
  3. Gelman, Carlin, Stern, Dunson, Vehtari & Rubin, Bayesian Data Analysis, 3rd ed, 2013
  4. Richard McElreath (2016). Statistical Rethinking: A Bayesian Course with Examples in R and Stan CRC Press.
  5. Michael Betancourt (2017), A Conceptual Introduction to Hamiltonian Monte Carlo, https://arxiv.org/abs/1701.02434
  6. Betancourt, Michael; Byrne, Simon; Livingstone, Sam; Girolami, Mark. The geometric foundations of Hamiltonian Monte Carlo. Bernoulli 23 (2017), no. 4A, 2257—2298. doi:10.3150/16-BEJ810. https://projecteuclid.org/euclid.bj/1494316818
  7. Stan https://mc-stan.org
Scientific publications of module course instructors related to the topic of the module:
  1. Bania, P., Baranowski, J.
    Approximation of optimal filter for Ornstein–Uhlenbeck process with quantised discrete-time observation
    (2018) International Journal of Control,
  2. Baranowski, J., Bania, P., Prasad, I., Cong, T.
    Bayesian fault detection and isolation using Field Kalman Filter
    (2017) Eurasip Journal on Advances in Signal Processing,
  3. Bania, P., Baranowski, J.
    Bayesian estimator of a faulty state: Logarithmic odds approach
    (2017) 2017 22nd International Conference on Methods and Models in Automation and Robotics, MMAR 2017,
  4. Stief, A., Ottewill, J.R., Orkisz, M., Baranowski, J.
    Two stage data fusion of acoustic, electric and vibration signals for diagnosing faults in induction motors
    (2017) Elektronika ir Elektrotechnika,
  5. Bania, P., Baranowski, J.
    Field Kalman Filter and its approximation
    (2016) 2016 IEEE 55th Conference on Decision and Control, CDC 2016,
  6. Chilinski, J., Bauer, W., Baranowski, J.
    Bayesian analysis of EEG signal frequency components
    (2016) 2016 21st International Conference on Methods and Models in Automation and Robotics, MMAR 2016,
Additional information:

-