A/B Testing
Test variations of your pages and find what converts best for your store.
Creating a Test
- Go to A/B Tests in the sidebar
- Click Create Test
- Enter the URL of the page you want to test
- Use the visual editor to make changes to your variant
- Set your traffic allocation (e.g., 50/50 split)
- Define your goal (clicks, purchases, etc.)
- Start the test
Visual Editor
The visual editor lets you make changes without code:
- Change text content
- Modify colors and styles
- Hide or show elements
- Swap images
Reading Results
Test results show:
- Visitors - Number of visitors in each variant
- Conversions - Goal completions per variant
- Conversion Rate - Percentage of visitors who converted
- Lift - Improvement over the control
- Confidence - Statistical certainty of the result
When to Declare a Winner
We recommend declaring a winner when:
- Confidence level reaches 95% or higher
- You have at least 100 conversions per variant
- The test has run for at least 7 days (to account for weekly patterns)
Test Limits
- Starter: No A/B testing
- Growth: 3 concurrent tests
- Pro: 10 concurrent tests
Advanced StatisticsComing Soon
Soon, Zolvio will include:
- Bayesian statistics for probability-based decisions
- Auto-winner detection when confidence thresholds are met
- Advanced device and audience segmentation
Important
Don't stop tests too early. Statistical significance requires sufficient sample size. Running tests for at least one full week helps account for day-of-week variations.