Design of Experiments
0/98 solvedEach question is graded on a single answer: a check that this chapter's methods work, not a test of the reasoning behind them.
Your answer
About these 98 questions
Potential outcomes and why randomisation identifies a causal effect; control, blinding and placebo; blocking and the exact variance reduction it buys, including Latin squares; factorial designs and why varying one factor at a time is strictly worse; replication, pseudoreplication and sizing an experiment for power; and what can and cannot be recovered from observational data, including Simpson's paradox. This set covers the chapter Design of Experiments in Statistics: 34 easy, 39 medium and 25 hard questions, each graded instantly with a hint and a full step-by-step solution. Progress is saved in this browser only.
- Randomisation, and why it works — 20 questions
- Blocking: removing variation before it becomes noise — 20 questions
- Factorial designs — 20 questions
- Replication and the size of an experiment — 18 questions
- When you cannot randomise — 20 questions
For work on paper there is a printable problem set with separate worked solutions.