Sample Size Calculator for Cure Rates

Advanced Statistical Parameter Configuration

1. Cure Rate Parameters

Expected Cure Rate ($P_1$)

Example: 0.85 (85%)

Expected Cure Rate ($P_0$)

Example: 0.65 (65%)

Non-Inferiority Margin

Example: 0.00 for superiority

2. Power & Significance

Significance Level ($\alpha$)

Example: 0.05 (5%)

Statistical Power ($1-\beta$)

Example: 0.80 (80%)

Hypothesis Test Type

Directional significance

3. Design & Adjustments

Allocation Ratio ($n_2 / n_1$)

Example: 1.0 for equal groups

Anticipated Dropout Rate (%)

Example: 10.0% loss rate

Cluster Design Effect (Deff)

Example: 1.0 for RCTs

Formula Used

The sample size calculation for comparing two independent cure rates is derived using normal approximation for binomial proportions. The core formula for standard group sizes is expressed as:

$$n_1 = \frac{\left( Z_{1-\alpha/2}\sqrt{\left(1+\frac{1}{r}\right)\bar{p}(1-\bar{p})} + Z_{1-\beta}\sqrt{\frac{p_1(1-p_1)}{r} + p_0(1-p_0)} \right)^2}{(p_1 - p_0 - \delta)^2}$$

Where $p_1$ and $p_0$ represent expected cure rates, $\bar{p}$ is the weighted pooled proportion, $r$ is the allocation ratio, and $Z$ values correspond to critical normal distribution quantiles.

How to Use This Calculator

Enter Cure Rates: Input your expected treatment cure rate ($P_1$) and control cure rate ($P_0$).
Set Parameters: Define your significance level ($\alpha$) and statistical power ($1-\beta$).
Configure Adjustments: Adjust allocation ratios, expected participant dropout rates, and cluster design effects.
Submit: Click the calculate button to review required group sizes instantly displayed at the top.

Understanding Cure Rate Sample Size Planning

Planning statistical sample sizes for clinical cure rate trials is fundamental to successful medical research. In clinical trials, establishing whether a novel therapeutic intervention achieves superior or non-inferior cure rates compared to standard treatments requires precise statistical rigor. Inadequate sample sizes lead to underpowered trials prone to Type II errors, whereas excessively large cohorts waste valuable healthcare resources and expose patients needlessly.

Key Considerations in Statistical Design

Investigators must carefully estimate baseline cure rates using prior literature or pilot studies. Furthermore, accounting for participant attrition through dropout adjustments ensures that the final evaluated cohort maintains adequate statistical power. When working with clustered sampling designs, applying a design effect multiplier is necessary to adjust standard error inflation accurately.

Frequently Asked Questions

Why is statistical power important?

Statistical power ensures that a study has a high probability of detecting a true therapeutic effect when one genuinely exists, usually set at 80% or 90%.

How does the dropout rate affect sample size?

Anticipated dropouts inflate the initial recruitment target so that the final analyzed dataset meets the minimum required statistical threshold.

What is the difference between one-sided and two-sided tests?

Two-sided tests check for differences in either direction, whereas one-sided tests evaluate superiority or non-inferiority in one specific directional hypothesis.