A/B Testing Screen Resolution (Monthly) Calculator
Estimate whether your monthly traffic for a screen resolution can support an A/B test and how long the test may need to run.
Overview
Use this calculator to estimate the sample size and time needed to run an A/B test for visitors on a particular screen resolution. Enter your total monthly traffic, the resolution's share of that traffic, your current conversion rate, and the smallest conversion improvement you want the test to detect.
How it works
The calculator first estimates the visitors available for the chosen screen resolution each month. It then uses a standard two-proportion A/B test sample-size calculation based on your baseline conversion rate, minimum detectable effect, confidence level, and power. The total required sample is split equally between control and variant, then divided by eligible monthly traffic to estimate the test length.
How to use this calculator
- 1Enter your average total website visitors per month.
- 2Add the percentage of visitors using the screen resolution you are targeting.
- 3Enter the current conversion rate for that resolution.
- 4Set the smallest conversion-rate improvement that would be meaningful.
- 5Choose your confidence level and statistical power.
- 6Review the required traffic per variation and estimated test duration.
Example Calculation
Total monthly website visitors
100000
Screen resolution traffic share
25%
Baseline conversion rate
5%
Minimum detectable effect
1%
Confidence level
1.96
Statistical power
0.84
Visitors needed per variation
8,149 visitors
With 100,000 monthly visitors and 25% using the chosen resolution, about 25,000 eligible visitors are available each month. Detecting an increase from 5% to 6% requires about 8,147 visitors per variation, or roughly 0.7 months of traffic.
Frequently asked questions
What is a screen resolution A/B test?
It is an experiment that compares two page, design, or experience variations only among visitors using a selected screen resolution or resolution segment.
Why does screen resolution share affect test duration?
Only visitors in the selected resolution segment can enter the test. A smaller segment means fewer eligible visitors each month and usually a longer test.
What is the minimum detectable effect?
It is the smallest absolute conversion-rate change you want the test to reliably detect. For example, moving from 5% to 6% is a 1 percentage-point effect.
What confidence level should I use for an A/B test?
A 95% confidence level is a common planning choice. Higher confidence requires more traffic because the test needs stronger evidence before identifying a difference.
What does statistical power mean?
Power is the chance that the test detects the chosen minimum effect when that effect truly exists. Higher power reduces missed effects but increases the required sample size.
Should I stop the test as soon as one variation looks better?
It is generally better to plan the sample size and test duration in advance, then evaluate results after the planned data has been collected. Early results can fluctuate substantially.
Explore Related Calculators
Assumptions and warnings
Assumptions
- Visitors are split evenly between the control and variant, with 50% assigned to each.
- Monthly traffic and the selected screen resolution's share remain broadly stable during the test.
- The calculation uses a two-sided comparison of two conversion rates.
- The minimum detectable effect is an absolute change in percentage points, not a relative percentage increase.
- Results are planning estimates and do not account for multiple tests, traffic-quality changes, or experiment exclusions.