Which change earned the improvement?

Which intervention caused the observed improvement?

Make your own investigation

Create a factorial comparison with identical cases across configurations. Report interactions and uncertainty across cases.

Keep each case paired. Compute retrieval and review effects plus interaction = both − retrieval − review + baseline.

Case cards

Cut these cards apart. Use the original example first, then let a partner supply a changed case. Keep sealed/final cards with the teacher until the learner commits a rule.

Case 1

Case: A

Baseline: 0.4

Retrieval only: 0.6

Review only: 0.5

Both: 0.9

My prediction and reason:

Case 2

Case: B

Baseline: 0.5

Retrieval only: 0.7

Review only: 0.6

Both: 0.75

My prediction and reason:

Case 3

Case: C

Baseline: 0.2

Retrieval only: 0.3

Review only: 0.4

Both: 0.7

My prediction and reason:

Case 4

Case: D

Baseline: 0.7

Retrieval only: 0.75

Review only: 0.8

Both: 0.82

My prediction and reason:

What this cannot establish

Case variation is not automatically independent sampling. Identify the population before interpreting uncertainty.