AtlasSession 3L7: Systematic errorsp.65–66
Decision flowcharts
- Study designs primer
- What is systematic error
- Selection bias
- Missing data
- Decision flowcharts
Fig. 1
Classifying an exclusion: the L7 p.65 flowchart chained into p.66 (p.66 read with RC8’s logic)
Fig. 1: decision flowchart “Does leaving people out make the comparison unfair?”. Case: Rabbits with a swollen joint. Rabbits with a swollen knee joint are left out of both groups before any implant is put in. Question: Were they left out before treatment started, or for a reason unrelated to the treatment? Answers: 1 Yes, 2 No.
- Case
- Rabbits with a swollen joint
- Question
- before treatment / unrelated?
- Your answers
- none yet
- How it’s going
- — (answer the first question to see how it’s going)
- Score
- 0/4 (no cases finished yet)
Decision Flowchart Walker · First look
Level 1 · First look · Lecture 7 · p.65–66
Use yes/no questions to decide what kind of problem an exclusion causes.
Walk any exclusion through the p.65 and corrected p.66 flowcharts to land on generalisability, selection bias, missing data or deviations.
Race analogy (the step you are on)
Barring injured runners from every heat before the start is fair; deleting one team's slow finishers isn't.
Barring injured runners from every heat before the start is fair; deleting one team’s slow finishers afterwards isn’t. One question sorts them: when, and why, were they left out? Case: Rabbits with a swollen joint. Your answers: none yet.