Courses / Scientific reasoning and experimental design / Design evidence that can change your mind / Design and challenge an intervention study Build and defend your work Design and challenge an intervention study Investigate whether a proposed study or process improvement produces a meaningful benefit. Use contrasting captures from at least two experiments, then specify a new investigation whose result could contradict your favored explanation. Deliver a protocol and a qualified conclusion; this workbench does not execute a real human study or certify its causal validity.
Choose an audience, investigate alternatives, copy evidence from your experiments, and produce an artifact. You can open this project at any time. Reports, numerical transfer checks and human review are separate outcomes.
Your project workspace Choose the kind of work you want to produce School investigation College investigation Workplace application Choose two safe paper-based study or sorting methods. Draft a protocol with balanced assignment, one primary outcome, a prediction for each explanation and a calibration check. Use model captures to show one misleading comparison and its repair; do not recruit people or collect personal data merely to complete this workbench.
1. Collect and compare evidence Required experiment sources:
Include every source above and at least one pair with different inputs from the same experiment. Explain confounding changes yourself; the presence check does not judge your interpretation.
Open an experiment and change an input or capture a trial to make evidence available here.
2. Write and revise your report Question, outcome and competing explanations State a concrete intervention, the population or process, one primary measurable outcome, and at least two explanations. Predict a result that would distinguish them before inspecting it.
Assignment and measurement controls Specify group balance or pairing, order handling, instrument calibration and what stays fixed. Identify a plausible remaining confounder or carryover effect.
Contrasting experiment evidence Compare at least two saved captures, changing one cause at a time where possible. Show intermediate arithmetic and explain what the contrast identifies and what it cannot identify.
Analysis and false-alarm plan Name the primary outcome, exploratory outcomes, uncertainty approach and any multiple-test correction. Explain why repeated analysis is not independent replication.
Decision and falsification Give a bounded conclusion, an inconclusive condition and a new test that could reverse it. Separate synthetic model evidence from any real observations and note permissions needed for future participant research.
Your artifact: code, analysis, prototype or decision brief This field stores up to 12,000 characters of inert text. Code runs only through the explicit bounded editor in the relevant lessons; project attachments never execute.
Load a text artifact Review your work against the rubric The protocol makes the intervention, outcome and comparison explicit. Controls address at least one observed bias and acknowledge a remaining threat. Captures and calculations support the claimed comparison without claiming real-world calibration. The analysis plan distinguishes primary, exploratory and replicated evidence. The conclusion can be revised by a specified contrary result; a numeric match is not a research qualification. 14 evidence requirements remain Capture evidence from fair comparisons. Capture evidence from calibration and repeatability. Capture evidence from noise and sample size. Capture evidence from paired and order effects. Capture evidence from factorial interactions. Capture evidence from discriminating hypotheses. Capture evidence from many tests false alarms. Include two different input configurations from the same experiment to compare. Write your question, outcome and competing explanations. Write your assignment and measurement controls. Write your contrasting experiment evidence. Write your analysis and false-alarm plan. Write your decision and falsification. Add your project artifact: code, analysis, prototype or decision brief. Record my report Download report and evidence Editing the report or evidence returns it to draft. Recording verifies field presence and input comparisons, not correctness of your reasoning or code.
3. Check transfer to unfamiliar cases These authored cases use different numbers or conditions from the lesson practice. They are public local checks, not secure certification. Each case permits three submissions. Opening, first responses and attempt counts survive imports; no reset creates fresh evidence.
Case science-project-composition Open case science-project-composition Case science-project-interaction Open case science-project-interaction Case science-project-false-alarms Open case science-project-false-alarms
Return to the course · My Work and backups
