← All workshopsRead Making a Fair Comparison by Assignment

Causal Inference and Experiments

Compare randomly assigned groups

BOTIE

Average each group and subtract control from treatment.
Ready to test
0 passed · 0 failed · 2 not run

An empty floor. Start with the information your machine needs.

Received result

Your answer will arrive here.

Examples, experiments and workspace controls
Live values

Connect a tool's inputs to see what it produces. You can try a branch before connecting it to Result.

Try your own inputs

Use a copy of the example to try your own data. Keep the problem's assumptions in mind, and predict the effect of a change before checking the output. You can also add another branch to compare two ways of doing the calculation.

Start at an output arrow, then click or drag to an input. Drag empty space to pan. Delete removes a selection. Ctrl/Cmd+Z undoes a change.
Context for this challenge

Average each group and subtract control from treatment.

Botie recorded outcomes after random schedule assignment under the lesson's independent-unit design. The comparison starts with the assignment procedure.

Calculate each assigned group's mean and subtract the control mean from the treatment mean.

Examples and results
Assigned treatment outcomes
  1. 06
  2. 18
  3. 27
Assigned control outcomes
  1. 04
  2. 15
  3. 26
Required result
2
Assigned treatment outcomes
  1. 02
  2. 14
Assigned control outcomes
  1. 01
  2. 15
Required result
0
Try a fresh construction

This clears this draft, including its undo history. Earlier successful attempts stay recorded. Build again without opening hints to record an independent attempt.

Stuck? Inspect a worked construction

The tools below form one possible solution. You can assemble it, follow its signals, and undo that change to return to your own construction.

Assumptions and test precision

This estimates an average assignment effect under the design assumptions, with finite-sample uncertainty. Numerical tests allow a difference of 0.001. Lists and structures must also have the right shape.

The assigned groups have different sample sizes

This check uses the pieces from “Estimate the difference between assigned groups”.

BOTIE

A randomised pilot records completed tasks per person. Three people were assigned the new interface and four the existing interface. Calculate the difference in their sample means, new interface minus existing interface.
Assigned treatment outcomes
  1. 04
  2. 17
  3. 27
Assigned control outcomes
  1. 03
  2. 14
  3. 25
  4. 38

Use a number, text, or an array matching the requested result. For a matrix, put each row in brackets. Saving your prediction runs your current construction on these inputs and checks the earlier examples too.

Build a construction in the workspace above first. This case will test those pieces.

Which facts about assignment and units must accompany this numerical contrast?

A causal interpretation is supported by the experimental design, not by subtraction alone.

This estimates an average assignment effect under the design assumptions, with finite-sample uncertainty.

Work through the Python challenges →
Continue the courseComparing Treatments in the Same Population →
← Separating a Useful Prediction From a Causal Claim