omni_clinical_trial_sample_size
Calculate required patient sample size per treatment arm for randomized controlled trials using statistical power, alpha, effect size, and dropout rate.
Instructions
Clinical Trial Sample Size & Statistical Power Calculator. Calculate required patient sample size per treatment arm for superiority randomized controlled trials (RCTs) based on statistical power, alpha, and effect size. Discipline: BIOTECH. Governing mathematical model / formula: N_arm = 2 · (Z_α/2 + Z_β)² · p̄(1 - p̄) / (p₁ - p₂)².
USAGE GUIDELINES:
WHEN TO USE: Invoke for deterministic calculation of required_sample_size_per_arm (Sample Size Per Treatment Arm), total_evaluable_trial_n (Total Evaluable Patients (2 Arms)), total_recruitment_enrollment (Target Enrollment (With Dropout Buffer)), absolute_treatment_effect_delta (Target Effect Size (Absolute Delta)) using control_group_event_rate_p1 (Control Group Response Rate (p₁ in %) in %), experimental_event_rate_p2 (Experimental Group Target Rate (p₂ in %) in %), type_1_error_alpha_pct (Significance Level α (Two-Tailed %) in % (α=0.05)), statistical_power_pct (Statistical Power (1 - β %) in % (Power)), anticipated_dropout_rate_pct (Anticipated Patient Dropout Rate (%) in %). Guarantees exact machine floating-point precision, eliminating LLM arithmetic mistakes and formula hallucinations.
WHEN NOT TO USE: Do not use for qualitative evaluations or unquantified reasoning. All input parameters must be valid numerical values.
DISAMBIGUATION & BOUNDARIES:
Use this dedicated specialist tool for 'Clinical Trial Sample Size & Statistical Power Calculator' rather than generic dispatchers like omni_universal_query.
For multi-calculation chained jobs, use 'omni_batch_calculate'.
To inspect schema fields, see 'omni_describe_solver'.
BEHAVIOR & SAFETY:
Pure deterministic computation with machine floating-point precision.
Read-only, idempotent, and stateless. Zero side effects or persistent state mutations.
Input validation: All arguments are validated against physical and domain bounds. Out-of-bounds inputs return a safe diagnostic error status without throwing runtime exceptions.
RETURNS:
Structured JSON object containing:
status (string): "success" on valid execution or "error" if validation fails
calculator (string): "clinical-trial-sample-size"
category (string): "biotech"
name (string): "Clinical Trial Sample Size & Statistical Power Calculator"
formula (string): Governing mathematical formula string
inputs (object): Echoed input parameter dictionary with applied defaults
metrics (object): Dictionary of computed outputs:
metrics.required_sample_size_per_arm (Sample Size Per Treatment Arm): Formatted display string (e.g. '138 Patients / Arm')
metrics.total_evaluable_trial_n (Total Evaluable Patients (2 Arms)): Formatted display string (e.g. '276 Patients')
metrics.total_recruitment_enrollment (Target Enrollment (With Dropout Buffer)): Formatted display string (e.g. '326 Total Recruits')
metrics.absolute_treatment_effect_delta (Target Effect Size (Absolute Delta)): Formatted display string (e.g. '+15.0% Difference')
execution_time_ms (number): Latency in milliseconds.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "omni_clinical_trial_sample_size"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| statistical_power_pct | No | Statistical Power (1 - β %) (% (Power)). Probability of detecting a true difference (typically 80% or 90%). Default: 80. Min: 70. Max: 99. | |
| type_1_error_alpha_pct | No | Significance Level α (Two-Tailed %) (% (α=0.05)). Standard medical threshold is α = 0.05 (Z = 1.96). Default: 5. Min: 1. Max: 10. | |
| experimental_event_rate_p2 | No | Experimental Group Target Rate (p₂ in %) (%). Clinically meaningful target response rate for new drug. Default: 35. Min: 2. Max: 99. | |
| control_group_event_rate_p1 | No | Control Group Response Rate (p₁ in %) (%). Expected baseline response rate or historical control. Default: 20. Min: 1. Max: 90. | |
| anticipated_dropout_rate_pct | No | Anticipated Patient Dropout Rate (%) (%). Patients lost to follow-up over trial duration. Default: 15. Min: 0. Max: 40. |