Student rights and obligations (login required)
Linköping University common rules and regulations (in Swedish)
Data Mining and Statistical Learning, 15 credits
Data Mining and Statistical Learning, 15 hp
732A33
Main field of study
StatisticsCourse level
Second cycleCourse type
Single subject and programme courseECV = Elective / Compulsory / Voluntary
| Course offered for | Semester | Weeks | Language | Campus | ECV | N.B. | |
|---|---|---|---|---|---|---|---|
| Single subject course (Full-time, Day-time) | Autumn 2014 | 201444-201403 | English | Linköping | CANCELLED | ||
Main field of study
StatisticsCourse level
Second cycleAdvancement level
A1XEntry requirements
For acceptance to the course, the student must have a bachelor’s degree with a total of at least 90 ECTS credits (1.5 years of full-time studies) in mathematics, applied mathematics, statistics, and computer science. The undergraduate courses in mathematics should include both calculus and linear algebra. Basic undergraduate courses in statistics and computer science are also required. Documented knowledge of English equivalent to Engelska B/Engelska 6. internationally recognized test, e.g. TOEFL (minimum scores: Paper based 575 + TWE-score 4.5, and internet based 90), IELTS, academic (minimum score Overall band 6.5 and no band under 5.5), or equivalent.Intended learning outcomes
The course lays the foundation for professional work and research in which large amounts of data are explored, modified, modelled and assessed to uncover previously unknown patterns and trends.
Having completed the course, the student should be able to:
- account for the principles of statistical modeling, in particular for the analysis of large data sets
- utilize tools in SAS environment to explore large and complex data sets, derive data-based models, assess their outcomes and use such models for forecasting
- compare the performance of statistical and data mining models in order to select the most appropriate model in a given context
Course content
- basic concepts in statistical learning, in particular supervised learning,
- model selection strategies involving the use of training sets, validation sets, and test sets and model selection by cross-validation.
- linear regression technique and regression shrinkage methods
- spline smoothers and kernel smoothers,
- decision trees and classification methods, such as discriminant analysis and logistic regression,
- neural networks, support vector machines, and generalized additive models
- ensemble methods, including bagging and boosting.
- Bayesian approach in data mining
Teaching and working methods
The teaching comprises lectures, seminars, and computer exercises. Lectures are devoted to presentations of theories, concepts and methods. Computer exercises provide practical experience of data analysis in SAS environment (as a rule) or in other enviroments (in exceptional cases). The seminars comprise student presentations and discussions of computer assignments.
Language of instruction: English.
Examination
Written reports on the computer assignments. Obligatory attendance of the seminars. One final written examination.
Grades
ECTS, ECOther information
Planning and implementation of a course must take its starting point in the wording of the syllabus. The course evaluation included in each course must therefore take up the question how well the course agrees with the syllabus. The course is carried out in such a way that both men´s and women´s experience and knowledge is made visible and developed.Department
Institutionen för datavetenskapNo examination details is to be found.
Course literature is preliminary.
There is no course literature available for this course in studieinfo.
This tab contains public material from the course room in Lisam. The information published here is not legally binding, such material can be found under the other tabs on this page.
There are no files available for this course.