Understanding Report Metrics in Convert

THIS ARTICLE WILL HELP YOU

• Identify the core performance metrics in every Convert report

• Judge when a result is reliable (and when it isn’t)

• Monitor test progress and sample health in real time

• Recognise warning icons before acting on a false winner

• Pick the statistical engine that fits your traffic and risk profile

• Apply a rapid “ship-or-wait” checklist to every experiment

Performance Metrics

• Visitors – Unique people bucketed into each variation.
  Example: 5 000 visitors on Variation A means 5 000 different individuals saw that version.

• Conversions – Goal completions counted once per visitor per experiment (unique). Repeat conversions by the same visitor do not increase the conversion count. This applies to purchase/sale goals as well.
  Example: If a visitor buys three times during the same experiment, Convert counts 1 conversion for that visitor.

• Conversion Rate – Conversions ÷ Visitors.
  Example: 100 / 1 000 = 10 % conversion rate.

• Total Conversions – If multiple conversions per visitor are allowed, this is the aggregate count.
  Example: 50 visitors × 2 purchases each = 100 total conversions.

• Revenue (when enabled) – Sum of transaction amounts tracked for the variation. By default, only the first transaction per visitor per experiment is recorded; you can optionally send subsequent order amounts for revenue accumulation (see note below). 

• Revenue per Visitor (RPV) – Revenue ÷ Visitors. In Convert, RPV is based on each visitor’s first recorded order unless you explicitly allow multiple transactions for revenue accumulation (conversion count remains unique). 

• Average Products Per Visitor (APPV) – Average number of items ordered per visitor in your experiment. In Convert, APPV uses the product count of each visitor’s first recorded order (unless you enable revenue accumulation), divided by total visitors in the variation.
  

  Formula (default):

  APPV=∑(products_cnt of first order per unique visitor) / Visitors

  To populate APPV you must pass the product count when tracking revenue (products_cnt in pushRevenue).

• Improvement – Percentage lift or loss v. baseline.
  Example: Control 10 % → Var A 12 % ⇒ +20 % improvement (not +2 %).

How APPV & RPV are populated (implementation notes)

• Manual / GA-based revenue tracking:

  • Manual JS:
    
    

  <script>
    window._conv_q = window._conv_q || [];
    window._conv_q.push(["pushRevenue", revenue, products_cnt, goal_id]);
    // Optional to accumulate revenue from repeat purchases:
    // window._conv_q.push(["pushRevenue", revenue, products_cnt, goal_id, "force_multiple"]);
  </script>

   

  • products_cnt is required to surface APPV.

  • force_multiple adds repeat-order amounts to revenue totals (conversion stays unique).

• Why your analytics tool might not match Convert:
  • Other tools may count all orders per user; Convert’s default is first order per visitor for conversion and per-visitor metrics. Expect differences unless you align counting logic.

Statistical Confidence Indicators

Frequentist

• Confidence – Certainty that the observed difference is real. Wait for 95 %+ before deciding.

• Statistical Significance – Flag showing whether confidence ≥ your preset threshold.

• P-value – Probability of seeing the data if the variants were identical. < 0.05 is conventionally “significant”.

• Confidence Interval – Range containing the true lift.
  Example: +15 % [+10 %, +20 %].

Bayesian

• Chance to Win – Probability a variation is best. Most teams ship at 95 %+.

• Expected Loss – Average % conversion you might forfeit if you pick this variant and it is not actually the best.

• Credible Interval – Bayesian version of the confidence interval (interpretation is the same).

Test Progress Indicators

• Sample Size – Visitors collected vs. required.
  Example: 5 000 / 10 000 visitors (50 %).

• Statistical Power – Probability the test will detect a true effect. Aim for ≥ 80 %.

• Minimum Detectable Effect (MDE) – Smallest lift your current traffic can reliably spot.

• Test Duration – Elapsed runtime; keep every test live for at least one full business cycle (7-14 days for most sites).

Warning Icons

• ⚠️ Low Sample Size – Fewer than ~5 000 visitors per variation. Let the test run.

• ⚠️ Not Yet Significant – Results still within the margin of error. Collect more data.

• ✅ Test Complete – All sample, power, and confidence criteria satisfied; safe to implement the winner.

Choosing Your Statistical Method