Data Analysis: Statistical Learning and Visualization
Dataanalys: statistisk inlärning och visualisering

FMSF86, 6.0 credits, G2 (First Cycle)

Valid for: 2024/25
Faculty: Faculty of Engineering LTH
Decided by: PLED I
Date of Decision: 2024-04-16
Effective: 2024-05-08

General Information

Main field: Technology Depth of study relative to the degree requirements: First cycle, in-depth level of the course cannot be classified
Mandatory for: I2
Language of instruction: The course will be given in English

Aim

The course begins with an overview of basic data wrangling and visualisation. With a focus on the student's ability to identify and illustrate important features of the data.

Then important methods in statistical learning are introduced. Emphasis is given supervised and unsupervised learning. Issues arising from fitting and evaluating multiple models as well as the methods relationship to linear regression are discussed. Computer based labs and projects form an important part of the learning activities.

Learning outcomes

Knowledge and understanding
For a passing grade the student must

• Describe different ways of aggregating, summarising and visualising data.
• Explain the principles of supervised and unsupervised learning.
• Explain the importance of evaluating models based on their predictive ability.

Competences and skills
For a passing grade the student must

• be able to wrangle, present and visualise data to highlight important features in a complex data material.
• be able to use common methods for supervised and unsupervised learning.
• be able to draw conclusions regarding a data material, based on results from classification and regression methods.
• be able to use common method for evaluation of predictive ability on out-of-sample data.
• present statistical analysis and conclusions a written report.

Judgement and approach
For a passing grade the student must

• Reflect over the limitations of the chosen model and method, as well as alternative solutions.
• Reflect over the possible issues with fitting multiple models to the same data material.

Contents

• Basic methods for data handling and common visualisation methods for data
• Methods for unsupervised and supervised learning such as: clustering; hierarchical clustering; and regression and decision tree methods for classification and regression problems.
• Methods for model selection and validation such as: bootstrap, split of data into training and test, and cross-validation.

Examination details

Grading scale: UG - (U, G) - (Fail, Pass)
Assessment:

Passing grade on all written lab reports and attendance on at least one scheduled lab per lab report.

The examiner, in consultation with Disability Support Services, may deviate from the regular form of examination in order to provide a permanently disabled student with a form of examination equivalent to that of a student without a disability.

Modules
Code: 0123. Name: Computer Lab 1.
Credits: 2.0. Grading scale: UG - (U, G). Assessment: Reporting of the lab. The module includes: Data handling and visualisation.
Code: 0223. Name: Computer Lab 2.
Credits: 2.0. Grading scale: UG - (U, G). Assessment: Reporting of the lab. The module includes: Continuous prediction (regression).
Code: 0323. Name: Computer Lab 3.
Credits: 2.0. Grading scale: UG - (U, G). Assessment: Reporting of the lab. The module includes: Classification.

Admission

Admission requirements:

• At least 4.5 credits (hp) in Mathematical Statistics (FMSF20, FMSF50, FMSF70, FMSF75, FMSF80 or equivalent) OR both one course in Calculus in Several Variables and one course in Linear Algebra.
• (FMAA20 Linear Algebra with Introduction to Computer Tools or FMAA21 Linear Algebra with Numerical Applications or FMAB20 Linear Algebra or FMAB22 Linear Algebra) and (FMAB30 Calculus in Several Variables or FMAB35 Calculus in Several Variables)

Reading list

• Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani: An Introduction to Statistical Learning with Applications in R. Springer, 2021, ISBN: 978-1071614174. Either the book for Python or R. Available on https://www.statlearning.com.
• Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, Jonathan Taylor: An introduction to statistical learning with applications in Python. Springer, 2023, ISBN: 3031387465. Either the book for Python or R. Available on https://www.statlearning.com.
  https://www.statlearning.com
• Vanderplas, Jacob T: Python data science handbook : essential tools for working with data. O'Reilly, 2022, ISBN: 1098121228. Side reading.
• Hadley Wickham, Mine Cetinkaya-Rundel, Garrett Grolemund: R for Data Science, 2nd Edition. O'Reilly Media, 2023, ISBN: 1492097403. Side reading. Available at https://r4ds.hadley.nz.
  https://r4ds.hadley.nz

Contact

Course coordinator: Linda Hartman, linda.hartman@matstat.lu.se
Director of studies: Johan Lindström, studierektor@matstat.lu.se
Course administrator: Susann Nordqvist, expedition@matstat.lu.se
Course homepage: https://www.maths.lu.se/utbildning/civilingenjoersutbildning/matematisk-statistik-paa-civilingenjoersprogram/

Further information