Clinical Trial Simulator | mysimulator.uk

Clinical Trial

Patients per group 30

Dose 50 mg

Drug potency (true effect) 0.50

p-value

–

Significant? (α=0.05)

–

Effect size, 95% CI

–

Treatment responders

–

Placebo responders

–

How it works

Every patient is randomly assigned to the treatment or placebo arm. Placebo patients still improve a little from natural variation and expectation (the placebo effect); treatment patients get that same baseline plus a dose-dependent drug effect from a sigmoid dose-response curve. Sphere height is each patient's improvement score; colour marks whether they responded (green), showed no meaningful change (grey) or got worse (red).

effect(dose) = potency · σ((dose − ED50) / slope)
score = placebo_noise + effect(dose) + patient_noise
t = (x̄₁ − x̄₂) / √(s₁²/n₁ + s₂²/n₂)   (Welch's t-test)

Patients per group — sample size. A larger trial shrinks the confidence interval and makes a small true effect easier to detect (statistical power).
Dose — how much drug each treatment patient receives; the dose-response curve means low doses barely beat placebo while high doses saturate near the drug's ceiling effect.
Drug potency — the maximum true effect size the drug can reach at saturating dose; set it to 0 to simulate a drug that is no better than placebo and watch p-value hover around chance.
p-value / 95% CI — the probability of seeing a difference this large (or larger) by chance alone if the drug had no real effect; the effect-size confidence interval shows the plausible range for the true treatment benefit.

Real-world relevance: this randomize → dose → measure → test loop is the backbone of every Phase II/III drug trial — the reason sample size calculations and pre-registered significance thresholds exist is to keep random noise from being mistaken for a real medical benefit.

TreatmentPlacebo

Responded No significant change Worsened

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.