LogoLogo
HomeThe PlatformBlogSchedule a demo
  • Getting Started
    • Welcome to AdLibertas
  • The Platform
    • How it works
    • User-Level Audience Reporting
      • Creating Reports
        • Creating a New User Report
        • Creating Advanced User-Level Reports
        • Advanced Audience Builder
        • Custom Event Metrics
      • Report Layout
        • Report Module: Audience Filtering
        • Chart Type Module: Absolute vs. Relative Reports
        • Daily Totals, Per User, Cumulative Totals
        • Lifecycle Reports
        • Forecasting Module
        • Statistics Module
        • Measuring Confidence
      • Advanced Reporting Methods
        • User Measurement & Calculation Details
        • Date Ranges: Define Audience vs. Create Report
        • Exclude GAID tracking opt-outs
        • Scheduled Reports: Keep Updated & Rolling
        • Reporting on a Firebase AB test
        • Understanding “Audience Restraints”
        • Adding user time to your reports
    • Consolidated Revenue Reporting
      • Reporting Discrepancies
      • Reporting Availability & Timezones
      • Ad Network Re-Repost; Also: Revenue Reconciliation Accuracy
      • Consolidated Reporting vs. Consolidated Inventory Reporting
      • Reporting Table – Column Descriptions Common Metrics (Calculated Fields)
      • Facebook Reporting
      • Consolidated Ad Revenue with multiple mediators
    • Business Analytics
      • Analytics Layout
      • Understanding the "Explore Data" button
      • The Data Table
      • Asking a Question
      • Saving a Question
      • Creating a custom dimension
      • Setting up a pulse
    • Custom Dashboards
      • Custom Dashboard Filters
      • Combining data into a single chart
    • Direct SQL Access
    • Exporting Data
      • Ad Network Reports
      • Chart Reports
      • Custom API connections
      • Downloading & Scheduling Data Reports
      • Deprecated: Line Item Change Log
    • General
      • Change your Username & Password
      • Adding Users to your Account
      • Sharing Collaborative Links
      • AdLibertas Cost
  • Data Integrations
    • Connecting in 3 steps
    • Ad Impression-Level Revenue Connections
      • AppLovin Max User Revenue API
      • ironSource Ad Revenue Measurement Integration
      • Impression level tracking with Admob Mediation
      • Collecting MoPub Impression-Level Data as a Firebase Event
    • Ad Network & Store Connections
      • Adding Ad Network Credentials
      • How does App Store Reporting work?
      • Adding access to Google Play
      • Adding Sub User to App Store Connect
      • Getting the most from Ad Network Reports
    • Analytics Connections
      • Data Set Status
      • Connect AdLibertas to Firebase
      • Connecting AdLibertas to BigQuery
      • Firebase Install Counts in Audience Reporting
      • Setting User Campaigns in Firebase
      • Why use revenue to determine Firebase AB test winners?
      • Firebase Best Practices: keeping Google BigQuery Costs Down
    • Custom Integrations
      • Sending Events via Webhooks to AdLibertas
      • Impression level tracking with Admob Mediation
      • Connecting AdLibertas to BigQuery
      • Importing a custom data set
    • IAP Connections
      • Tracking IAP & Subscriptions in Firebase and BigQuery
      • RevenueCat Integration: WebHooks
      • RevenueCat: Setting Universal Identifiers
    • MMP Connections
      • Connecting Adjust
      • Connecting AppsFlyer
      • Connecting Kochava
  • FAQs
    • General
      • Why does AdLibertas need credentials?
    • Audience Reporting
      • Why doesn't my daily active user count match Firebase?
      • Why doesn’t my retention rate match?
      • Why aren't my install rates matching?
      • Why doesn't my relative user count match retention?
      • What is the probability projected LTV becomes actual LTV?
      • Why doesn’t Firebase and AdLibertas revenue match?
    • Reporting
      • What is “non_mopub” revenue
      • How do customers use AdLibertas?
  • Privacy & Security
    • Privacy & Security Details
Powered by GitBook
On this page
  • How to include confidence in AdLibertas reporting
  • Understanding the outcome.
  • Best practices for using confidence in your reporting
  1. The Platform
  2. User-Level Audience Reporting
  3. Report Layout

Measuring Confidence

Measuring confidence in your LTV reports

PreviousStatistics ModuleNextAdvanced Reporting Methods

Last updated 2 years ago

Confidence measures the percentage a random sample of your test audience will show as, or greater difference than the mean of the baseline.

When you set a baseline in your report, AdLibertas will calculate the statistical significance (p-value) of your comparison audiences. The confidence (1 – p) percentage returned is the likelihood a random sample will show as, or greater difference than the mean.

How to include confidence in AdLibertas reporting

When creating a with more than one , you’ll be able to select a baseline. That baseline is used as the calculation for your comparison. All other audiences or variants will be compared to the baseline.

How confidence is calculated.

is determined by calculating the of a . is calculated as (1—p-value).

Understanding the outcome.

Confidence returns the likelihood a randomly selected sample of users, one user from A and one from B, will have an outcome as, or greater, than the displayed mean.

Best practices for using confidence in your reporting

Also – like mean values– a small number of users will distort your confidence levels, so be sure to keep in mind the number of users at the end of the experiment.

Most scientists and statisticians often strive for in experiments but you’ll find a range that works for your purposes. An AB test with <50% confidence isn’t necessarily a failure, it is just less than half of the users in the experiment will fall closer together than the mean value.

Looking for more tips, read our article on

95%+ confidence levels
setting up an effective framework for AB tests.
report
audience
Statistical significance
p-value
one-tailed test
Confidence