Clinical Trials · ANCOVA-2A

Sample Size for Baseline-Adjusted ANCOVA

Calculate the required sample size for a parallel two-arm trial with one baseline measurement and one primary follow-up analysed using ANCOVA adjusted for baseline.

1. Planning setup

Primary outcome name

Optional. Used only in the protocol-ready wording and calculation summary.

2. Information obtained from previous study / literature

Expected common SD at final follow-up σ

Enter the expected standard deviation of the continuous primary outcome at the final follow-up assessment.

Expected correlation between baseline and final follow-up outcome ρ

Enter the expected correlation between baseline and final follow-up values of the same primary outcome. Use estimates from prior studies, pilot data, or a clinically comparable population.

3. Information decided by the researcher

Minimum clinically important difference between groups Δ

Enter the smallest absolute between-group difference at final follow-up that the study should be able to detect.

Test direction

Two-sided One-sided

Two-sided testing is generally appropriate for superiority trials unless a one-sided hypothesis is fully justified before the study begins.

Significance level α

Use the total two-sided alpha level when two-sided testing is selected.

Power

Anticipated dropout/non-response (%)

Inflate the recruitment target for participants expected not to contribute a final primary-outcome measurement.

4. Results

Enter the RCT planning assumptions and select Calculate.

Analysis sample-size summary

Item	Per arm	Total

Sensitivity analysis

Correlation, ρ	ANCOVA-adjusted analysable sample per arm	Recruitment target per arm	Total recruitment target

Higher baseline-to-follow-up correlation results in a greater precision gain from ANCOVA and a smaller required sample size. Select the final correlation assumption using credible prior evidence rather than choosing the value that gives the smallest sample size.

Suggested sample-size wording

Formula, assumptions, limitations, and methodological note

Example clinical scenario

A randomized trial compares 12-week systolic blood pressure between a new antihypertensive treatment and usual care while adjusting for baseline systolic blood pressure.

Formula and methodological note

Use this calculator for individually randomised, two-arm, parallel-group superiority trials with equal 1:1 allocation, one continuous primary outcome measured once at baseline and once at the primary follow-up, and a planned ANCOVA or equivalent linear-regression primary analysis adjusted for baseline outcome value.

For one baseline measurement and multiple follow-ups with an average treatment effect as the primary hypothesis, use the baseline-adjusted repeated-measures ANCOVA calculator.

This calculator uses a two-arm ANCOVA sample-size approach for a continuous outcome. The sample-size reduction is based on the squared correlation between baseline and follow-up outcome values.

The calculation assumes equal 1:1 randomisation.
The planned primary analysis must be ANCOVA or equivalent linear regression adjusting for baseline outcome.
The calculation is not intended for analysis of change scores.
The final analysis should not switch to an unadjusted test merely because the sample size was calculated using ANCOVA.
Additional prognostic covariates may further improve precision but are not included in this calculator.
For repeated post-baseline measurements, cluster randomisation, crossover design, non-inferiority, or unequal allocation, use an appropriate dedicated calculator.

Two-sided testing: Z critical = Z(1 - α / 2)

One-sided testing: Z critical = Z(1 - α)

Unadjusted per-arm sample size = 2 × (Z critical + Z power)² × σ² / Δ²

ANCOVA-adjusted analysable sample size per arm = ceiling[unadjusted per-arm sample size × (1 - ρ²) + 1]

Recruitment target per arm = ceiling[ANCOVA-adjusted analysable sample size per arm / (1 - L)]

Total recruitment target = 2 × recruitment target per arm

Method references

Borm GF, Fransen J, Lemmens WAJG. A simple sample size formula for analysis of covariance in randomized clinical trials. Journal of Clinical Epidemiology. 2007;60:1234–1238. doi:10.1016/j.jclinepi.2007.02.006.

Suggested citation

Yaacob, Najib Majdi. “Sample Size for a Two-Arm RCT with Baseline-Adjusted ANCOVA (ANCOVA-2A).” Web calculator. NajibMY, 2026. Accessed July 29, 2026. https://najibmy.netlify.app/tools/sample-size/clinical-complex-study-designs/rct-continuous-ancova/.