Emnebeskrivelse PGR109

This course introduces theoretical principles of probability and statistics with a focus on practical applications in data science. Topics include but are not limited to: permutations and combinations, frequentist vs. subjectivist probability, parametric vs. non-parametric statistics, probability distributions, Bayesian inference, null hypothesis significance testing, confidence intervals, effect sizes, point estimation, linear regression, multiple regression and logistic regression.

Knowledge

The student ...

• understands the key theoretical principles in probability and statistics
• understands key technologies, tools, platforms, libraries, packages and / or modules for conducting statistics in data science domains
• has deep understanding required to discuss important technical issues in designing, conducting and evaluating statistical procedures in data science applications

Skills

The student ...

• knows the skills to analyze the different principles and techniques for descriptive as well as inferential statistics
• is able to select and apply the appropriate statistical principles, methods, tools and techniques for a given dataset
• is able to design, implement, evaluate and document statistics in a data science project

General competence

The student ...

• can discuss theoretical aspects of and practical challenges in probability and statistics
• can reflect upon the different tools for conducting statistics in data science
• can critically assess statistical principles, methods, tools and techniques applied on a given dataset
• can communicate the role of probability and statistics in data science applications

Bachelor of Data Science

Lectures, exercises and exam.

Participation in lectures and exercises - 48 hours

Self study 80 - hours

Independent preparation for presentation / discussion in class - 12 hours

Independent practice / lab work / practical work individually or in groups - 48 hours

Execution of and preparation for the exam - 12 hours

Recommended use of time in total - 200 hours

Python and / or R

Coursework requirements: These consist of one or more assignments/activities that must be collectively approved. Assignments supported by some datasets that will be given. The students will have to submit solutions along with the analysis and present their results in a written format.

Individual qualification: G / IG (approved / not approved)

Execution: Individual

Verifiable (right of appeal): No

Coursework requirements are to be handed in or conducted in accordance with information given by the lecturer and carried out within the duration of the course, as well as registered as approved/not approved at least two weeks before the exam/exam period.

Approved coursework requirements grant students permission to take exams. Unapproved coursework requirements result in the student’s withdrawal from the exam.

Exam type: Individual written examination

Duration: 3 hours

Grading scale: Norwegian grading system using the grades pass or fail

Weighting: Passing of overall assessment

Support materials : No Books are allowed, but a Calculator is allowed

Resit exam: Same exam type as the ordinary exam with a new assignment.