Curriculum placement
Algebra 2. This describes the skill, not a learner estimate.
Testing a difference by randomization
Use randomization simulations to compare treatments and assess observed differences
Problem types
- Is the treatment difference significant?
Builds on
- Checking a chance model by simulation
- Studies, experiments, and samples
- A procedure that gives each outcome a fair chance · Useful idea
A fair random shuffle of group labels is the procedure a randomization test repeats.
- Comparing center, spread, and shape · Useful idea
The difference in centers between two groups is the statistic that a randomization test compares with chance.
- Comparing two data distributions · Earlier idea
Comparing two groups by their means in units of spread extends to asking whether a difference could arise by chance in a randomization test.
Leads to
- Reading a statistical report critically · See it applied
A significant randomization test from random assignment supports a causal claim, which is what a critique of a report asks whether the design justifies.
- Association is not causation · See it applied
A significant randomization test from random assignment supports a causal conclusion.
Related skills
- A distribution built from frequencies · Related idea
The results of reshuffled data form an empirical distribution against which the observed result is compared.
- Checking a model against evidence · Related idea
Asking whether a model's pattern could come from chance uses the same logic as a randomization test.
- A margin of error from simulated samples · Shared foundations
- Margin of error and what a sample supports · Shared foundations
Open the interactive map to explore lessons and skill connections.