Contemporary Statistics with Applications (22/23)

Faculteit Science and Engineering
Jaar 2022/23
Vakcode WMMA015-05
Vaknaam Contemporary Statistics with Applications (22/23)
Niveau(s) master
Voertaal Engels
Periode semester I a

Uitgebreide vaknaam Contemporary Statistics with Applications (tweejaarlijks 2022/2023)
Leerdoelen At the end of the course, the student is able to:
1. analyse data with (penalized) linear regression models, e.g. Lasso and Ridge regression.
2. apply linear classification methods to data, e.g. to perform a linear discriminant analysis (LDA).
3. to implement and to apply cross-validation for model selection, randomization tests for hypothesis testing and Bootstrapping for variance estimation.
4. to implement and to apply the Expectation-Maximization (EM) algorithm to incomplete data, e.g. Gaussian mixture models.
5. to implement and to apply a principal component analysis (PCA) for dimension reduction.
6. to derive the mathematical properties of the discussed statistical methods.
Omschrijving This course unit covers a selection of important contemporary statistical modelling techniques for statistical data analyses. The statistical methods will be motivated by applications and/or data examples, before the underlying theoretical concepts will be explained. In practical exercises the methods will be applied to data and the results will be interpreted. The topics of the course include: Penalized linear regression models (e.g. Ridge/Lasso regression), linear classification methods (e.g. LDA), principal component analysis (PCA), Gaussian and other mixture models, the Expectation-Maximisation (EM) algorithm, Cubic splines and Gaussian Process regression, Bootstrap procedures and permutation tests, and hidden Markov models (HMMs).
Uren per week
Onderwijsvorm Hoorcollege (LC), Opdracht (ASM), Werkcollege (T)
(Weekly twice two-hour lectures and one two-hour practical. The practical will be held in a computer lab and involves programming in R.)
Toetsvorm Opdracht (AST), Verslag (R)
(Assessment takes place through three homework assignments and a research project and report according to the formula: Final grade = max{PR,0.7 x PR + 0.3 x HW} where HW is the average of the three homework assignment grades and PR is the project report grade. The pass mark is: Final grade = 5.5 or higher)
Vaksoort master
Coördinator prof. dr. M.A. Grzegorczyk
Docent(en) prof. dr. M.A. Grzegorczyk
Verplichte literatuur
Titel Auteur ISBN Prijs
Recommended: The Elements of Statistical Learning (2009)

Hastie, Tibshirani, Friedman 978-0-387-84857-0
Entreevoorwaarden The course unit assumes prior knowledge acquired from the two course units Probability Theory and Statistics (from the Mathematics BSc programme).
Opmerkingen This course was registered last year with course code WICSA-10
Opgenomen in
Opleiding Jaar Periode Type
MSc Applied Mathematics: Computational Mathematics  (Computational Mathematics: Guided choice) - semester I a keuzegroep
MSc Applied Mathematics: Systems and Control  (Systems and Control: Guided choice) - semester I a keuzegroep
MSc Applied mathematics  (Specialisatie: Computational Mathematics) - semester I a keuzegroep
MSc Applied mathematics  (Specialisatie: Systems and Optimization) - semester I a keuzegroep
MSc Applied mathematics  (Specialisatie: Statistics and Data Science) - semester I a verplicht
MSc Computing Science: Data Science and Systems Complexity  (Guided choice course units) - semester I a keuze
MSc Courses for Exchange Students: AI - Computing Science - Mathematics - semester I a
MSc Mathematics: Science, Business and Policy  (Science, Business and Policy: Statistics and Big Data) - semester I a keuzegroep
MSc Mathematics: Statistics and Big Data  (MSc Mathematics: Statistics and Big Data) - semester I a verplicht
Tweejaarlijkse vakken  (Even jaren) - semester I a -