Explains the design of a controlled experiment
Units are assigned at random to control and treatment, one factor differs, and the metric, sample size and stopping rule are fixed before the start.
Can AI do this?
Not tested yet
No AI benchmark covers this knobit yet. New results are announced in the Can AI Do the Job? newsletter.
What it looks like in practice
Expected result: Units are assigned at random to control and treatment, one factor differs, and the metric, sample size and stopping rule are fixed before the start.
How it is assessed: Answers a written question on the controlled experiment design correctly
Related knobits
Builds on
- K-1802 Explains the concepts of a hypothesis and a counter-example
- Q-1801 Defines the concepts of sample and population
Needed for
- E-1803 Estimates price elasticity from experiment results
- E-2101 Formulates a testable hypothesis for an experiment
- E-2102 Designs the assignment of units in an experiment
- E-3102 Derives a design change from observed drop-off
All 6 knobits of Perform scientific research.
Source: ESCO knowledge concept 'research design' (ESCO v1.2.1); knowledge the ESCO skill 'perform scientific research' applies in DO process activities P3.6, P5.7, P7.6, P8.4; CRISP-DM 1.0; Kohavi, Tang and Xu, Trustworthy Online Controlled Experiments (2020); not checked against a reference text