Login for PhD students/staff at UCPH      Login for others
Statistical methods for the SCIENCE (SmS)
Provider: Faculty of Science

Activity no.: 5542-24-07-21 
Enrollment deadline: 20/10/2024
PlaceDepartment of Mathematical Sciences
Universitetsparken 5, 2100 København Ø
Date and time30.10.2024, at: 08:30 - 08.11.2024, at: 16:30
Regular seats50
Activity Prices:
  - Deltager/Participant from SCIENCE0.00 kr.
  - Deltager/Participant Others3,000.00 kr.
ECTS credits2.50
Contact personBo Markussen    E-mail address: bomar@math.ku.dk
Enrolment Handling/Course OrganiserBo Markussen    E-mail address: bomar@math.ku.dk
Written languageEnglish
Teaching languageEnglish
Semester/BlockBlock 1 ¤ Block 2 ¤ Block 3 ¤ Block 4
Block noteTeaching on 5 full days within two consecutive weeks: October 30 + 31 and November 6 +7 + 8.
Exam requirementsTo pass the student must participate in at least 4 of the 5 course days
Exam formContinuous assessment
Grading scalePassed / Not passed
Censorship formOne internal examiner.
Course workload
Course workload categoryHours
Theory exercises20.00
Lectures20.00
Preparation25.00
Sum65.00
Content
Toolbox course on statistical methodology with focus on choice of statistical models, practical implementation using statistical software, and presentation and interpretation of results. For the practical implementation, we use the state-of-the approach for data analysis in R including data wrangling and visualization via the tidyverse package. The course covers the most common statistical models used in the empirical sciences. Specifically, the following topics are taught: data types, data visualization, table-of-counts, categorical regression, linear and multilinear regression, analysis of variance, random effects, hypothesis testing and statistical power, correction for multiple testing, estimated marginal means and confidence intervals, and design of experiments.

Formel requirements
There are no formal requirements. However, recommended prerequisite is some introductory statistics course during the participant’s bachelor or master studies, or the PhD school Fundamentals II course.

Learning outcome
The students are introduced to statistical models commonly used in the empirical sciences for univariate end-points. The statistical methodology is discussed with emphasis on how models are used and interpreted, and the students are trained to do the statistical analyses using the statistical software R.

After course completion, the students should be able to:

Knowledge:
• Understand elements of frequentist statistics including estimation, confidence intervals, hypothesis tests, model validation.
• Understand data types and organization in tidy data.
• Understand assumptions for statistical analyses.
• Understand concepts of fixed and random effects.
• Understand solutions to the multiple testing problem.

Skills:
• Identify the data types in a particular dataset, and choose an adequate statistical model.
• Make high quality visualizations of data.
• Report results via the estimated-marginal-means technology.
• Use R to perform the statistical analysis via the RStudio interface.
• Use relevant R packages. In particular, tidyverse, emmeans, and lme4.

Competences:
• Formulate scientific questions in terms of statistical hypothesis.
• Conduct statistical analysis using the discussed models.
• Interpret the results of a statistical analysis.
• Critically reflect over the results, conclusions and limitations of a statistical analysis.
• Judge when to seek help from a skilled statistician.

Literature
• Chester Ismay, Albert Y. Kim: “Statistical Inference via Data Science: A ModernDive into R and the Tidyverse”, CRC Press, The R Series, 2019. Book is also available online at www.moderndive.com.
• Supplementary material on random effects and estimated marginal means.
• Software R and RStudio is free and may be downloaded from www.r-project.org and www.posit.co.

Teaching and learning methods
Lectures and exercises including use of computers. In the first half of the course days focus will be on lectures, and in the second half on individual coursework with exercises. Participants must bring their own laptops with R and RStudio installed.

Search
Click the search button to search Courses.


Course calendar
See which courses you can attend and when
JanFebMarApr
MayJunJulAug
SepOctNovDec



Publication of new courses
All planned PhD courses at the PhD School are visible in the course catalogue. Courses are published regularly.