Lesson 3 · Observational Designs · Step 6 of 6
Choosing and reading an observational design
The design follows from the question, the outcome and the clock. Descriptive questions point to surveillance and cross-sectional surveys. Rare outcomes and urgent outbreaks point to case-control studies. Questions about timing point to cohorts, retrospective ones when records already exist. Reading a study well means checking the decisions made before any result: how controls were chosen, whether a matched design got a matched analysis, how much of the cohort was lost, whether a snapshot is described with causal verbs, and what nobody measured.
Also covered: choosing a design · appraising observational studies · residual confounding · triangulation
Alongside this step
- Slides and transcript — the whole video
- Read the chapter — Observational Designs
Check yourself
5 questions, marked as you go. Nothing is recorded as a grade and nothing is locked behind it — if a question catches you out, that is the useful part.
Lesson 3 · 6 steps
Research Designs · lesson 3 of 5