A/B Test Feasibility Calculator

Know if your test can find the truth.

Estimate the sample, traffic and time your landing-page test needs to detect a worthwhile improvement—before weeks of inconclusive data make the decision harder.

Freeto use
No sign-upor email gate
Privateruns in your browser

Built for landing-page lead generation

01

Describe the test you want to run

Start with an average month. Use visitors who could genuinely see either page—not every session in analytics.

Your traffic and conversion
The number of people who reach the page you want to test in an average month. Counting page views can overstate the sample because one person may visit more than once.Use unique visitors or users, not page views
The share of page visitors who can be assigned cleanly to either version. Excluding bots, staff, known customers and repeat exposure makes the estimate more realistic.%Remove bots, staff, repeat exposure and excluded audiences
The percentage of eligible visitors who complete the one action you care about, such as submitting a qualified enquiry. Use a recent stable period.%Conversions ÷ eligible visitors on the current page
Improvement worth detectingThe smallest win that would justify changing the page. A smaller target needs a much larger sample.
%A 20% lift turns 6% into 7.2%
Your decision window
Your practical deadline. The calculator compares the statistically required duration with how long the decision is still useful.weeksHow long the business can wait before acting
A short period to confirm allocation, event tracking and page behaviour before the official sample begins. These visitors are not counted in the result.daysTime to verify tracking before counting the sample
Advanced statistical settings

The defaults are the standard choice for most marketing tests.

A 50/50 split produces an answer fastest. An uneven split can reduce risk but needs more total traffic.%50% current page · 50% challenger
How strongly the result must rule out random noise. At 95% confidence, the tolerated false-positive rate is 5% before other testing issues are considered.%95% is the common default
The chance that the test detects the improvement if that improvement is real. Higher power reduces missed wins but requires more visitors.%80% is standard; 90% needs more traffic
Question the test must answerTwo-sided tests can detect a meaningful win or loss and are safer by default. One-sided tests need less traffic but should only be chosen before launch when a loss would not be treated as a finding.Choose this before the test starts
Can this test produce a useful answer?

We’ll calculate the sample, duration, detectable lift and the safest next move.

The thinking behind the forecast

A test is only useful if it can change a decision.

Sample size is not a universal traffic threshold. It changes with your starting conversion rate, the smallest win worth detecting, the risk of a false winner, the risk of missing a real winner and how traffic is divided.

01 · SIGNAL

Minimum detectable effect

The smallest change the experiment is designed to distinguish from noise. Asking the test to detect tiny lifts dramatically increases the required sample.

02 · CERTAINTY

Confidence and power

Confidence limits false winners. Power limits missed real winners. The 95% confidence and 80% power defaults are a common planning balance.

03 · REALITY

Traffic plus time

The model converts the sample into calendar time using eligible traffic, then adds a launch check and a two-week observation guardrail.

Experiment notes

Plan the decision before watching the result.

Statistical settings cannot rescue weak tracking, changing rules or a test that was too small from the beginning.

What is a meaningful improvement?

It is the smallest conversion-rate increase that would make the winning page worth implementing. Set it from commercial value and implementation effort, not from the lift you hope to see. Smaller improvements need much larger samples.

What is the difference between relative lift and percentage points?

Relative lift describes the improvement compared with the current rate. Moving from 5% to 6% is a 20% relative lift but a one percentage-point increase. The calculator supports both and shows the resulting challenger target.

Why does the calculator recommend at least two weeks?

A test that fills its sample in a few days can still overrepresent particular weekdays, campaign conditions or sales patterns. Two complete weeks are a practical minimum guardrail for most lead-generation landing pages, though highly seasonal or considered purchases may need longer.

Can I stop when the testing tool shows 95% confidence?

Not safely if that was not the stopping rule planned in advance. Repeatedly checking and stopping on a favourable result increases the chance of a false winner. Complete the planned sample and observation window, or use a properly configured sequential method.

Should I use a one-sided or two-sided test?

Use a two-sided test by default because a challenger can perform meaningfully better or worse. A one-sided test needs less traffic but should only be chosen before launch when the decision genuinely cares about improvement in one direction and the downside is handled separately.

What if my landing page does not have enough traffic?

Test a larger proposition or journey change, choose a higher-volume behaviour as the primary metric, aggregate a genuinely comparable audience, or use structured qualitative research and a time-based or holdout design. Do not keep an underpowered test running indefinitely and call the direction a result.

Does this guarantee the test will be valid?

No. The calculation addresses sample size under a two-proportion normal approximation. Validity also depends on clean assignment, reliable tracking, stable traffic, no interference between groups, a precommitted metric and stopping rule, and a test experience that remains consistent.

Is my data stored?

No. The calculator runs in your browser. A shareable result puts the values in the link itself, so only create or send one when you are comfortable sharing those assumptions.

When the answer is “do not A/B test”

Build a learning plan that fits your traffic.

We Know Growth can connect customer research, analytics, page strategy and experiment design so your team learns without waiting months for a result the site could never support.