Admission requirements
Students should be proficient in Python or R. In addition, students are advised to complete an introductory course in methodology and statistics.
Description
This course equips students with the skills to design and carry out rigorous and transparent research. Students learn to develop appropriate data analysis plans for research questions, select statistical models that match the data, and create meaningful visualizations. In addition, they will learn how to generate synthetic data. The course also emphasizes critical reflection on how research results are interpreted, how the strength of evidence should be weighed, and how (questionable) research practices can shape scientific conclusions. Finally, the course also discusses the principles of open science and explores different publication practices, helping students understand how transparent and responsible research can improve the credibility and cumulative progress of science.
Course objectives
By the end of the course, students can:
Create a suitable data analysis plan to tackle a research question
Selecting an appropriate model that fits the data types and assumptions
Create insightful visualizations for various data types and patterns
Write code to generate synthetic data and perform analyses on them
Reflect critically on the interpretation of research results and accurately weigh the strength of evidence
Recognize and appraise research practices as appropriate or inappropriate, and explain the motivations behind using them
Evaluate the effects of questionable research practices on research outcomes
Distinguish the concepts of reproducibility, replicability, and robustness
Explain the importance and different facets of open science
Distinguish between different publication practices and their respective merits
Schedule
Teaching method
Ten two-hour lectures and associated two-hour workgroup sessions. In addition, students will work on two written assignments.
In the first assignment, students generate synthetic data, select an appropriate analysis method to answer a particular research question, simulate the impact of Questionable Research Practices, and present the results using suitable data visualization techniques. In the second assignment, students evaluate the reproducibility, replicability and robustness of a particular finding.
In preparation for the two assignments, students need to reach certain milestones, which focus on a particular aspect of the assignment.
Assesment method
The course grade is the weighted average of:
A closed-book multiple choice exam covering the theoretical knowledge discussed in the lectures and work group sessions (50%)
An assignment grade (50%), with both assignments having an equal weight.
Assessment requirements:
Reaching the milestones is a requirement in order to receive a grade for the assignment, and students will receive feedback on what they handed in during the following workgroup. This will in turn allow students to improve on the assignment they eventually hand in.
Not meeting the milestones for a given assignment or failing to hand in an assignment in a timely fashion, will result in a 1 for the respective assignment.
Policy on generative AI:
The use of generative tools is not allowed during the exam. Generative AI may be used for specific aspects of the assignments. The assignment instructions describe exactly how generative AI can and cannot be used. In any case, transparent reporting of generative AI use is required.
To verify ownership of the assignments, we will organize (oral) evaluations which partly determine the grade for the respective assignments.
Resit, review & feedback
Resit opportunities:
Students have the opportunity to retake the exam. If, after the resit, the theory grade is (still) below 5.5, the student needs to retake the theory part of the course (i.e., the lectures).
There is a resit opportunity for both assignments. The maximum grade for a resit assignment is 6. If the overall assignment grade is below 5.5 (after a potential resit), students need to retake the practical part of the course (i.e., the assignments).
Review and feedback:
Feedback on the assignments is given during one of the workgroup sessions.
Review of the exam takes place within 10 working days after publication of the exam results and before the second exam moment takes place.
Reading list
Course material includes slides, exercises, and articles that will be made available via the online course platform.
Registration
Contact
For substantive questions, contact the lecturers (listed in the right information bar). For questions about enrolment, admission, etc., contact the Education Administration Office: education-office@liacs.leidenuniv.nl