CRO Glossary
Clear definitions of conversion rate optimization and A/B testing terminology. Your comprehensive reference for understanding CRO concepts.
A/B Testing
A controlled experiment where two versions of a webpage or element are compared by randomly showing each version to different visitors and measuring which performs better on a defined conversion metric.
Example:
Testing two different homepage headlines to see which drives more sign-ups.
Bounce Rate
The percentage of visitors who leave your website after viewing only one page, without taking any action or navigating to other pages. A high bounce rate often indicates poor relevance or usability issues.
Example:
If 100 visitors land on your page and 65 leave without clicking anything, your bounce rate is 65%.
Chi-Squared Test
A statistical test used to determine if there is a significant difference between expected and observed frequencies in categorical data. In CRO, it's commonly used to analyze A/B test results for conversion rates.
Example:
Testing whether the difference between a 5% control conversion rate and a 5.5% variant conversion rate is statistically significant.
Conversion Funnel
The journey visitors take from initial awareness to completing a desired action, visualized as a funnel because typically fewer users complete each subsequent step. Understanding drop-off points is crucial for optimization.
Example:
Homepage → Product Page → Cart → Checkout → Purchase, where 100 start but only 3 complete the purchase.
Conversion Rate
The percentage of visitors who complete a desired action out of the total number of visitors. Calculated as (conversions ÷ total visitors) × 100. This is the primary metric most CRO efforts aim to improve.
Example:
If 50 out of 1,000 visitors make a purchase, the conversion rate is 5%.
LEARN MORE
Hypothesis
A specific, testable prediction about how a change to your website will impact a conversion metric. Good hypotheses are based on data, user research, and psychological principles rather than assumptions.
Example:
If we add customer testimonials above the fold, then sign-up rate will increase by at least 10% because it builds trust with new visitors.
Minimum Detectable Effect (MDE)
The smallest improvement in conversion rate that you want your test to be able to detect reliably. A smaller MDE requires larger sample sizes. Setting realistic MDEs is crucial for efficient testing.
Example:
Setting MDE at 10% means you want to detect improvements of 10% or greater (e.g., 5% → 5.5%).
P-Value
The probability that the observed difference between variations occurred by chance alone, assuming there is no real difference. A p-value less than 0.05 (5%) is typically considered statistically significant.
Example:
A p-value of 0.03 means there's a 3% probability the results are due to random chance.
Sample Size
The number of visitors each variation in your A/B test needs to reach statistical significance. Proper sample size calculation before testing ensures reliable results and prevents stopping tests prematurely.
Example:
To detect a 15% improvement at 95% confidence, you might need 10,000 visitors per variation.
Statistical Significance
A measure of confidence that the difference observed in your test represents a real effect rather than random variation. Typically achieved when p-value is less than 0.05 (95% confidence level).
Example:
Your test is statistically significant at 95% confidence, meaning you can be 95% confident the variant truly performs better.