Control Condition Designer AI Prompt

Design the appropriate control condition(s) for my experiment.

Treatment / intervention: {{treatment}}
Outcome of interest: {{outcome}}
Study population: {{population}}

The choice of control condition is one of the most consequential design decisions in an experiment — it determines what your results actually mean.

1. Types of control conditions:

   No-treatment control:
   - Participants receive nothing
   - What it controls for: the natural trajectory of the outcome over time
   - What it does NOT control for: expectancy effects, attention effects, placebo response, demand characteristics
   - Appropriate when: you want to know if treatment outperforms doing nothing at all

   Waitlist control:
   - Participants are told they will receive treatment later
   - Controls for: passive time effects
   - Does not control for: expectancy, attention
   - Appropriate when: it is unethical to permanently withhold treatment; participants need a reason to stay in the study

   Active control (treatment as usual):
   - Participants receive the current standard of care or typical practice
   - Controls for: expectancy, attention, non-specific treatment effects
   - Appropriate when: you want to know if your treatment outperforms what is already available

   Placebo control:
   - Participants receive an inert treatment designed to be indistinguishable from the active treatment
   - Controls for: expectancy, placebo response, non-specific effects
   - Appropriate when: the active treatment has a specific mechanism you want to isolate
   - Requires: a credible placebo that participants cannot distinguish from treatment

   Active component control:
   - A version of the treatment with one component removed
   - Appropriate when: you want to test whether a specific component is the active ingredient

2. For my specific experiment:
   - Which control type is most appropriate? Why?
   - What does each plausible control condition tell me vs what it leaves confounded?
   - Are multiple control arms warranted to answer more than one question?

3. Blinding considerations:
   - Can participants be blinded to their condition? If not, how will expectancy effects be minimized?
   - Can assessors be blinded? Can analysts be blinded?
   - What are the risks of unblinding (participants guessing their condition)?

4. Ethical considerations:
   - Is it ethical to withhold treatment from the control group?
   - What happens to control participants after the study ends?

Return: recommended control condition(s), rationale, what each controls for and does not, and a blinding plan.