Observational study designs: risk factors vs prediction rules
7 important questions on Observational study designs: risk factors vs prediction rules
Observational study design
What are the two different aims of a cohort study?
- Aim one, explain what the association is between a set of main determinant(s) and the outcome of interest
- Can also be used to analyse which set of predictors tell us something about the likelihood of the occurrence of interest in the future
What for design is used for prediction models
- Higher grades + faster learning
- Never study anything twice
- 100% sure, 100% understanding
Mention 7 steps to develop a prediction model
- Problem definition and data inspection
- Coding of predictors
- Model specification
- Model estimation
- Model performance
- Model validation
- Model presentation
The development of a prediction model
- Pre-selection of potential predictors
- Literature/ previous research
- Expert opinion
- Collect data in longitudinal study
- Cohort
- Registry data
- Selection of predictors statistically
- Forward selection
- Backward selection
- Begin met zo'n groot mogelijk model (alle determinanten erin) Verwijder de minst sterke voorspeller uit het model, blijf dit herhalen
How do you test the quality of the models?
- Multiple linear regression -> R(2)
- Classification tables
- Hosmer-Lemeshow test
- C-statistic (AUC)
Three concepts of validity within prediction models
- Validation: to determine to what extent the predictions/ models is feasible or optimistic
- Internal validation: validate in the setting/ patients used to make the model
- External validation: validate in a new setting / new patients
The question on the page originate from the summary of the following study material:
- A unique study and practice tool
- Never study anything twice again
- Get the grades you hope for
- 100% sure, 100% understanding
![Trustpilot Logo](/images/design_2020/lp/clp-trustpilot-en.png)