Course ObjectiveIn this course the student will get acquainted with the most common
experimental designs and regression models, nonparametric tests and
bootstrap methods will be discussed. On completion of this course the
student should be able to:
- design experiments and analyse the results according to the design,
- analyse data using the common ANOVA designs,
- analyse data using linear regression or a generalized linear
- perform basic nonparametric tests,
- perform bootstrap and permutation tests.
Course ContentRegression models try to explain or predict a dependent variable using
measured independent variables. Statistical methods are needed if there
is random variation in the dependent variables. We will discuss multiple
linear regression, analyses of variance (ANOVA), lasso, generalized
linear regression models. All methods will be illustrated with practical
examples. Especially in the case of ANOVA it is necessary that the study
is well designed in order to draw sound conclusions from an experiment
or survey. In this course a few well known designs (completely
randomized, randomized block etc.) and the associated analyses of
variance are discussed. The remainder of the course is be dedicated to
non-parametric testing methods and bootstrap methods: Wilcoxon test for
(one and two samples), Kolmogorov-Smirnov test (two samples), rank
correlation tests, permutation and bootstrap tests. All analyses are
carried out by using the statistical package R.
Teaching MethodsLectures, discussions of the assignments.
Method of AssessmentSeveral practical assignments during the course and the final assignment
at the end. The final grade is based on the written reports of all these
Entry RequirementsIntroductory statistics.
Literature- Slides of the lectures, R manual.
Introductory books on statistics (containing the prerequisite knowledge
for this course) are for example
- Statistical reasoning for everyday life, by J.O. Bennett, W. Briggs,
- Elementary Statistics, by Mario Triola (12th edition, Pearson New
- Probability and Statistics for Computer Scientists by Michael Baron
(2nd edition, 2014 CRC Press).
For more background on the topics in this course, the following books
(emphasis on the implementation in R) are recommended:
- Linear models with R, by J.J. Faraway;
- Extending the linear model with R, by J.J. Faraway.
Target AudiencemAI, mCS
Additional InformationAll assignments are to be solved using the statistical package R
Recommended background knowledgeA basic course in statistics of the same level as Statistical Methods
(FEW_XB_40013), basic knowledge of the statistical software R and its
application to data analysis.
|Language of Tuition||English|
|Faculty||Faculty of Science|
|Course Coordinator||dr. E.N. Belitser|
|Examiner||dr. E.N. Belitser|
dr. E.N. Belitser
You need to register for this course yourself
Last-minute registration is available for this course.
|Teaching Methods||Lecture, Practical|
This course is also available as: