Sample Size Calculator
A/B test sample size calculator. Enter your baseline conversion rate and minimum detectable lift to see the visitors ...
What Sample Size Calculator does
An A/B test sample size calculator that tells you how many visitors each variant needs to detect a meaningful lift. Enter your baseline conversion rate and the minimum detectable effect you care about, and the tool outputs the required sample size per variant, the total visitors across all variants, and an estimated test duration based on your daily traffic. It also shows statistical power options, significance levels, and a comparison with a bandit approach that claims to reach a winner with roughly 40% fewer impressions. A simple chart visualizes how smaller minimum detectable effects require dramatically more traffic at your chosen baseline rate.
How to use the TrafficLoopback Sample Size Calculator
- 1
Input your baseline conversion rate in the control variant field
- 2
Set the minimum detectable effect, the smallest lift you want to be able to detect
- 3
Choose your desired statistical power and significance level from the dropdowns
- 4
Enter your daily visitors per variant to get an estimated test duration
Best for
Marketers and product teams running A/B tests who need to calculate required sample size before launching, especially those with limited traffic who want to compare standard testing against bandit alternatives.
Limitations
- Results are estimates based on input parameters
- Test duration depends on actual daily visitor volume which may vary
- Bandit alternative provides a conservative 40% impression reduction estimate
Sample Size Calculator FAQ
- What does minimum detectable effect mean in this calculator?
- The minimum detectable effect is the smallest relative lift you care about detecting. A smaller MDE requires much larger sample sizes, while a larger MDE needs fewer visitors but may miss subtle improvements.
- How is test duration estimated?
- Test duration is calculated by dividing the required sample size by your daily visitors per variant. The tool uses your input daily traffic number to estimate how many days the test would run.
- Can this calculator be used for tests with more than two variants?
- Yes, the tool allows you to select the number of variants from 2 up to 6, adjusting the total sample size requirements accordingly.
- What is the difference between the standard A/B test and the bandit alternative?
- A standard A/B test splits traffic evenly and waits for statistical significance, while a bandit algorithm dynamically shifts traffic toward better-performing variants, potentially reaching a winner with 30-50% fewer impressions according to the tool's estimate.
More Sample Size Calculator tools
Similar tools
Based on shared tags