1 Syllabus
This course spans from late september to december and is split into the following sessions, listed in the schedule, which will be covered in order:
- Probability and stochastic variables
- Outcome types and measuring effects
- Law of Large Numbers
- Data wrangling
- Workshop: Formulating a research question
- Hypothesis testing
- Linear regression
- Logistic regression
- Time-to-event analysis
- Repeated measures
- Power calculations
- Workshop: Prediction vs. explanatory models
- Validation of continuous prediction models
- Workshop: From statistical analysis to clinical decision-making
- Introduction to meta-analysis
1.1 Learning outcome and objectives
1.1.1 Knowledge
Students will:
- Understand uncertainty, probability, and core biostatistical concepts
- Recognize major study designs and distinguish between explanatory, exploratory, and predictive studies
- Explain random and non-random variation
- Understand the limitations and possibilities of statistical tools
- Apply biostatistics to problems in medicine with industrial specialization
1.1.2 Skills
Students will be able to:
- Read and interpret software documentation
- Select and apply appropriate visualization tools for health data
- Formulate scientific statistical problems and apply biostatistical methods
- Manipulate, visualize, and analyze complex and large datasets
- Communicate statistical results in a clinical context using relevant literature and databases
- Collaborate effectively in interdisciplinary project groups
1.1.3 Competencies
Students will:
- Quantify clinical and health-related problems using biostatistical methods
- Integrate uncertainty and clinical relevance in decision-making
- Translate data analysis into clinical decision support
- Critically evaluate statistical approaches and participate in scientific discussions
Broken down into specific objectives for each session, we’ve designed the workshop to enable you to do the following:
Tangibly, during the workshop you will:
- List concrete tasks and steps
1.2 All literature for the course:
Session 1:
note this is not a small amount of home-work!
Read:
Session 2:
Chapter 1 in the Medical Statistic Compendium (see Moodle)
Session 3:
Chapter 2 in the Medical Statistic Compendium (see Moodle)
Session 4:
Mandatory:
- data viz guide of the Royal Statistical Society
- Chapters 1-4: Why we visualise data; Principles and elements of visualisations; Choosing a visualisation type; Styling for accessibility
- astrazeneca blog post
- data.europa.eu blog post on Honest Charts
- Section 17.3
Extra - not mandatory:
Session 5:
Chapter 3 in the Medical Statistic Compendium (see Moodle)
Session 6:
See zip file on Moodle
Session 7:
TBD - see Moodle.
Session 8:
Chapter 4 in the Medical Statistic Compendium (see Moodle)
Session 9:
TBD - see Moodle for announcement.
Session 10:
TBD - see Moodle for announcement.
Session 11:
- Chapter 3.3.2 (pages 87—-93) in Introduction to statistical learning with R 2nd edition (click “Download ISL with R”)
- Section 17.3
Session 12:
- Todays dataset (Epilepsy Clinical Trial)
- Chapter 4.6 (pages 164—-171) in Introduction to statistical learning with R 2nd edition (click “Download ISL with R”)
Session 13:
TBD - see Moodle for announcement.
Session 14:
TBD - see Moodle for announcement.
Session 15:
- Marginal effects chatpter 3
- Marginal effects chatpter 5
- You can skip section 5.4 Uncertainty and 5.5 Test
Session 16:
TBD - see Moodle for announcement.
Session 17:
TBD - see Moodle for announcement.
Session 18:
Obligatory:
- Steyerberg & Vergouwe, 2014 NB: read only “An ABCD for model validation”
if you join the lecture, no need to read:
Session 19:
Session 20:
TBD - see Moodle for announcement.
Session 21:
TBD - see Moodle for announcement.