Report on experiments

Page Summary

• Treatment campaigns are considered new campaigns and do not copy metrics from control campaigns.

• Control and treatment campaigns accrue and retain their metrics separately throughout an experiment, even after promotion or graduation.

• After promotion, changes from the treatment campaign are copied to the control campaign, but metrics remain associated with their original campaigns.

• Experiment campaigns and base campaigns can be differentiated in search queries using campaign.experiment_type.

To evaluate how campaign changes and ad exposure affect performance, query experiment and lift measurement reporting resources in the Google Ads API.

The Google Ads API supports two ways to report on standard A/B experiments:

• Direct experiment reporting: Query the experiment resource for metrics. This option provides metrics for control and treatment arms in a single response, along with statistical comparison data such as uplift and p-values. Direct experiment reporting is the only way to report on intra-campaign experiments.
• Campaign reporting: Query the campaign resource for metrics by using the campaign.experiment_type field to distinguish between base and experiment campaigns. This option is available only for experiments that use separate control and treatment campaigns, such as system-managed experiments.

For standard experiments, this guide focuses primarily on direct experiment reporting, which supports all reportable experiment types. For lift measurement studies, see the Lift reporting guide or the summary sections on this page for Brand Lift, Conversion Lift (including A/B + Conversion Lift), and Search Lift.

Direct experiment reporting

To retrieve performance metrics and statistical comparisons between your control and treatment arms in a single response across all supported Google Ads API versions (v23 and later), query the experiment resource directly.

Metrics and statistical significance

For core metrics such as clicks, impressions, cost, conversions, and conversion value, the experiment resource provides both treatment metrics (for example, metrics.clicks) and control metrics (for example, metrics.control_clicks) in the same row.

The experiment resource also provides fields to help you evaluate the statistical significance of any difference between the arms:

• metrics.*_p_value: The probability of observing results at least as extreme as the measured difference if the experiment has no actual effect on the metric. A lower p-value indicates higher statistical significance.
• metrics.*_point_estimate: The estimated percentage lift (positive or negative) in the given metric for the treatment arm compared to the control arm. Together with the metrics.*_margin_of_error field, this value defines a confidence interval with a prescribed confidence level for the estimated difference. The estimated quantity is (treatment / control) - 1, and the point estimate is the center of the confidence interval.
• metrics.*_margin_of_error: The radius of the confidence interval, which is centered at the metrics.*_point_estimate value. The API calculates this margin for a prescribed confidence level that depends on the experiment type.

The following core metric fields are supported on the experiment resource, including a treatment group value, a control group value, and the stat fields listed previously:

• clicks
• impressions
• cost_micros
• conversions
• cost_per_conversion
• conversion_value
• conversion_value_per_cost

For conversions, specifically, the statistical fields are available through the following absolute_change fields, rather than as relative values:

• metrics.conversions_absolute_change_p_value: The p-value for the null hypothesis that the experiment has no effect on conversions absolute change. Ranges from 0 to 1.
• metrics.conversions_absolute_change_point_estimate: The point estimate when estimating the experiment's effect on conversions absolute change.
• metrics.conversions_absolute_change_margin_of_error: The margin of error when estimating the experiment's effect on conversions absolute change.

For assistance constructing valid queries to the experiment resource, use the Google Ads Query Builder tool.

Example query

The following Google Ads Query Language (GAQL) query retrieves key metrics for an experiment:

SELECT
  experiment.experiment_id,
  experiment.name,
  experiment.type,
  metrics.clicks,
  metrics.control_clicks,
  metrics.clicks_point_estimate,
  metrics.clicks_margin_of_error,
  metrics.clicks_p_value,
  metrics.conversions,
  metrics.control_conversions,
  metrics.conversions_absolute_change_point_estimate,
  metrics.conversions_absolute_change_margin_of_error,
  metrics.conversions_absolute_change_p_value
FROM experiment
WHERE experiment.experiment_id = EXPERIMENT_ID

Replace the following:

• EXPERIMENT_ID: the integer ID of the experiment (experiment.experiment_id).

Interpret results

Use the p-value, point estimate, and margin of error fields to determine whether your experiment has yielded statistically significant results. For example, if the metrics.conversions_absolute_change_p_value metric is less than your chosen threshold (such as 0.05 for 95% confidence) and the metrics.conversions_absolute_change_point_estimate metric minus the metrics.conversions_absolute_change_margin_of_error metric is greater than zero, the treatment arm is performing significantly better than the control arm in terms of conversions.

The following code example demonstrates how to evaluate results based on p-value and lift estimates:

Java

private void evaluateExperiment(
    GoogleAdsClient googleAdsClient, long customerId, GoogleAdsRow row) {
  Metrics metrics = row.getMetrics();
  String experimentResourceName = row.getExperiment().getResourceName();

  // 1. Evaluate conversion success as a primary success signal if available.
  // - Point Estimate: Represents the estimated average lift or difference in conversions.
  // - Margin of Error: Outlines the confidence interval bounds. Note that the margin_of_error
  //   provided by the API is calculated for a preset confidence level which is set based on the
  //   experiment type.
  // - Lower Bound: (Point Estimate - Margin of Error). If this value is above 0,
  //   we have statistical significance that performance has improved.
  double convPValue = metrics.getConversionsAbsoluteChangePValue();
  double convLift = metrics.getConversionsAbsoluteChangePointEstimate();
  double convError = metrics.getConversionsAbsoluteChangeMarginOfError();
  double convLowerBound = convLift - convError;

  if (convPValue <= P_VALUE_THRESHOLD) {
    if (convLowerBound > 0) {
      System.out.printf(
          "Significant Success: Conversions increased. Even at the lower bound, the lift is %.2f."
              + " Promoting changes.%n",
          convLowerBound);
      promoteExperiment(googleAdsClient, customerId, experimentResourceName);
      return;
    } else if ((convLift + convError) < 0) {
      System.out.printf(
          "Significant Decline: Even the upper bound (%.2f) is below zero. Ending experiment.%n",
          convLift + convError);
      endExperiment(googleAdsClient, customerId, experimentResourceName);
      return;
    }
  }

  // 2. Fall back to evaluating click metrics if conversions are inconclusive.
  double clickPValue = metrics.getClicksPValue();
  double clickLift = metrics.getClicksPointEstimate();
  double clickError = metrics.getClicksMarginOfError();
  double clickLowerBound = clickLift - clickError;

  if (clickPValue <= P_VALUE_THRESHOLD && clickLowerBound > 0) {
    System.out.printf("Click volume is significantly up (+%.1f%%).%n", clickLift * 100);

    // Graduation is only supported for separate campaign experiments, not
    // intra-campaign experiments where there is no separate treatment campaign.
    ExperimentType experimentType = row.getExperiment().getType();
    if (experimentType != ExperimentType.ADOPT_BROAD_MATCH_KEYWORDS
        && experimentType != ExperimentType.ADOPT_AI_MAX) {
      System.out.println("Graduating treatment campaign for further manual analysis.");
      graduateExperiment(googleAdsClient, customerId, experimentResourceName);
    } else {
      System.out.println(
          "Intra-campaign trial detected: graduation is not supported. Continuing to run the"
              + " experiment to gather more conversion data.");
    }
  } else {
    // 3. Print status if no action was taken.
    System.out.printf(
        "Inconclusive: No significant lift in Conversions (p=%.2f) or Clicks (p=%.2f). Current"
            + " estimated lift: %.2f +/- %.2f. Allowing the experiment to continue running.%n",
        convPValue, clickPValue, convLift, convError);
  }
}
EvaluateAndUpdateExperiment.java
      

C#

private static void EvaluateExperiment(GoogleAdsClient client, long customerId, GoogleAdsRow row)
{
    // This function evaluates performance metrics and immediately takes action
    // to update the experiment's status (promote, end, or graduate) if
    // statistical significance thresholds are met.
    var metrics = row.Metrics;
    string experimentResourceName = row.Experiment.ResourceName;

    bool hasConvMetrics = metrics.HasConversionsAbsoluteChangePValue
        && metrics.HasConversionsAbsoluteChangePointEstimate
        && metrics.HasConversionsAbsoluteChangeMarginOfError;

    bool hasClickMetrics = metrics.HasClicksPValue
        && metrics.HasClicksPointEstimate
        && metrics.HasClicksMarginOfError;

    // 1. Evaluate conversion success as a primary success signal if available.
    // - Point Estimate: Represents the estimated average lift or difference in conversions.
    // - Margin of Error: Outlines the confidence interval bounds. Note that the margin_of_error
    //   provided by the API is calculated for a preset confidence level which is set based on
    //   the experiment type.
    // - Lower Bound: (Point Estimate - Margin of Error). If this value is above 0,
    //   we have statistical significance that performance has improved.
    if (hasConvMetrics)
    {
        double convPValue = metrics.ConversionsAbsoluteChangePValue;
        double convLift = metrics.ConversionsAbsoluteChangePointEstimate;
        double convError = metrics.ConversionsAbsoluteChangeMarginOfError;
        double convLowerBound = convLift - convError;

        if (convPValue <= P_VALUE_THRESHOLD)
        {
            if (convLowerBound > 0)
            {
                Console.WriteLine(
                    $"Significant Success: Conversions increased. Even at the lower" +
                    $" bound, the lift is {convLowerBound:F2}. Promoting changes.");
                PromoteExperiment(client, customerId, experimentResourceName);
                return;
            }
            else if ((convLift + convError) < 0)
            {
                Console.WriteLine(
                    $"Significant Decline: Even the upper bound ({convLift + convError:F2}) " +
                    $"is below zero. Ending experiment.");
                EndExperiment(client, customerId, experimentResourceName);
                return;
            }
        }
    }

    // 2. Evaluate click volume as a secondary signal.
    // This is helpful as an early indicator or for lower-volume accounts.
    if (hasClickMetrics)
    {
        double clickPValue = metrics.ClicksPValue;
        double clickLift = metrics.ClicksPointEstimate;
        double clickError = metrics.ClicksMarginOfError;
        double clickLowerBound = clickLift - clickError;

        if (clickPValue <= P_VALUE_THRESHOLD && clickLowerBound > 0)
        {
            // We have a directional winner: high confidence in more traffic,
            // but not enough data to confirm conversion impact yet.
            Console.WriteLine(
                $"Click volume is significantly up (+{clickLift * 100:F1}%).");

            // Graduation is only supported for separate campaign experiments, not
            // intra-campaign experiments where there is no separate treatment campaign.
            if (row.Experiment.Type != ExperimentType.AdoptBroadMatchKeywords
                && row.Experiment.Type != ExperimentType.AdoptAiMax)
            {
                Console.WriteLine("Graduating treatment campaign for further manual analysis.");
                GraduateExperiment(client, customerId, experimentResourceName);
            }
            else
            {
                Console.WriteLine(
                    "Intra-campaign trial detected: graduation is not supported. " +
                    "Continuing to run the experiment to gather more conversion data.");
            }
            return;
        }
    }

    // 3. Print status if no action was taken.
    if (hasConvMetrics || hasClickMetrics)
    {
        string convStatus = hasConvMetrics
            ? $"Conversions (p={metrics.ConversionsAbsoluteChangePValue:F2}, " +
              $"lift={metrics.ConversionsAbsoluteChangePointEstimate:F2} +/- " +
              $"{metrics.ConversionsAbsoluteChangeMarginOfError:F2})"
            : "Conversions (not populated)";

        string clickStatus = hasClickMetrics
            ? $"Clicks (p={metrics.ClicksPValue:F2}, " +
              $"lift={metrics.ClicksPointEstimate:F2} +/- " +
              $"{metrics.ClicksMarginOfError:F2})"
            : "Clicks (not populated)";

        Console.WriteLine(
            $"Inconclusive: No significant action taken. {convStatus}, {clickStatus}. " +
            "Allowing the experiment to continue running.");
    }
    else
    {
        Console.WriteLine(
            "Conversion and click performance metrics are not yet populated. " +
            "Allowing the experiment to continue running.");
    }
}
EvaluateAndUpdateExperiment.cs
      

PHP

This example is not yet available in PHP; you can take a look at the other languages.
    

Python

def evaluate_experiment(
    client: GoogleAdsClient, customer_id: str, row: GoogleAdsRow
) -> None:
    """Evaluates the performance of the experiment and updates it accordingly
    (for example, promotes, ends, or graduates).

    Checks conversion and click metrics against statistical significance thresholds
    to determine the appropriate action to take on the experiment.

    Args:
        client: an initialized GoogleAdsClient instance.
        customer_id: a client customer ID.
        row: a GoogleAdsRow containing the experiment and metrics.
    """
    # This function evaluates performance metrics and immediately takes action
    # to update the experiment's status (promote, end, or graduate) if
    # statistical significance thresholds are met.
    metrics = row.metrics
    experiment_resource_name = row.experiment.resource_name

    has_conv_metrics = (
        "conversions_absolute_change_p_value" in metrics
        and "conversions_absolute_change_point_estimate" in metrics
        and "conversions_absolute_change_margin_of_error" in metrics
    )
    has_click_metrics = (
        "clicks_p_value" in metrics
        and "clicks_point_estimate" in metrics
        and "clicks_margin_of_error" in metrics
    )

    # 1. Evaluate conversion success as a primary success signal if available.
    # - Point Estimate: Represents the estimated average lift or difference in conversions.
    # - Margin of Error: Outlines the confidence interval bounds. Note that the margin_of_error provided by the API is calculated for a preset confidence level which is set based on the experiment type.
    # - Lower Bound: (Point Estimate - Margin of Error). If this value is above 0,
    #   we have statistical significance that performance has improved.
    if has_conv_metrics:
        conv_p_value = metrics.conversions_absolute_change_p_value
        conv_lift = metrics.conversions_absolute_change_point_estimate
        conv_error = metrics.conversions_absolute_change_margin_of_error
        conv_lower_bound = conv_lift - conv_error

        if conv_p_value <= P_VALUE_THRESHOLD:
            if conv_lower_bound > 0:
                print(
                    "Significant Success: Conversions increased. Even at the lower"
                    f" bound, the lift is {conv_lower_bound:.2f}. Promoting"
                    " changes."
                )
                promote_experiment(
                    client, customer_id, experiment_resource_name
                )
                return
            elif (conv_lift + conv_error) < 0:
                print(
                    "Significant Decline: Even the upper bound"
                    f" ({conv_lift + conv_error:.2f}) is below zero. Ending"
                    " experiment."
                )
                end_experiment(client, customer_id, experiment_resource_name)
                return

        # 2. Evaluate click volume as a secondary signal.
        # This is helpful as an early indicator or for lower-volume accounts.
        click_p_value = metrics.clicks_p_value
        click_lift = metrics.clicks_point_estimate
        click_error = metrics.clicks_margin_of_error
        click_lower_bound = click_lift - click_error

        if click_p_value <= P_VALUE_THRESHOLD and click_lower_bound > 0:
            # We have a directional winner: high confidence in more traffic,
            # but not enough data to confirm conversion impact yet.
            print(f"Click volume is significantly up (+{click_lift*100:.1f}%).")

            # Graduation is only supported for separate campaign experiments, not
            # intra-campaign experiments where there is no separate treatment campaign.
            experiment_type_name = row.experiment.type_.name
            if (
                experiment_type_name != "ADOPT_BROAD_MATCH_KEYWORDS"
                and experiment_type_name != "ADOPT_AI_MAX"
            ):
                print(
                    "Graduating treatment campaign for further manual analysis."
                )
                graduate_experiment(
                    client, customer_id, experiment_resource_name
                )
            else:
                print(
                    "Intra-campaign trial detected: graduation is not supported. "
                    "Continuing to run the experiment to gather more conversion data."
                )
            return

    # 3. Print status if no action was taken.
    if has_conv_metrics or has_click_metrics:
        conv_status = (
            f"Conversions (p={metrics.conversions_absolute_change_p_value:.2f}, "
            f"lift={metrics.conversions_absolute_change_point_estimate:.2f} +/- "
            f"{metrics.conversions_absolute_change_margin_of_error:.2f})"
            if has_conv_metrics
            else "Conversions (not populated)"
        )
        click_status = (
            f"Clicks (p={metrics.clicks_p_value:.2f}, "
            f"lift={metrics.clicks_point_estimate:.2f} +/- "
            f"{metrics.clicks_margin_of_error:.2f})"
            if has_click_metrics
            else "Clicks (not populated)"
        )
        print(
            f"Inconclusive: No significant action taken. {conv_status}, {click_status}."
            " Allowing the experiment to continue running."
        )
    else:
        print(
            "Conversion and click performance metrics are not yet populated. "
            "Allowing the experiment to continue running."
        )
evaluate_and_update_experiment.py
      

Ruby

def evaluate_experiment(client, customer_id, row)
  # This function evaluates performance metrics and immediately takes action
  # to update the experiment's status (promote, end, or graduate) if
  # statistical significance thresholds are met.
  metrics = row.metrics
  experiment_resource_name = row.experiment.resource_name

  has_conv_metrics = !metrics.nil? &&
                     metrics.has_conversions_absolute_change_p_value? &&
                     metrics.has_conversions_absolute_change_point_estimate? &&
                     metrics.has_conversions_absolute_change_margin_of_error?
  has_click_metrics = !metrics.nil? &&
                      metrics.has_clicks_p_value? &&
                      metrics.has_clicks_point_estimate? &&
                      metrics.has_clicks_margin_of_error?

  # 1. Evaluate conversion success as a primary success signal if available.
  # - Point Estimate: Represents the estimated average lift or difference in conversions.
  # - Margin of Error: Outlines the confidence interval bounds. Note that the margin_of_error
  #   provided by the API is calculated for a preset confidence level which is set based on the experiment type.
  # - Lower Bound: (Point Estimate - Margin of Error). If this value is above 0,
  #   we have statistical significance that performance has improved.
  if has_conv_metrics
    conv_p_value = metrics.conversions_absolute_change_p_value
    conv_lift = metrics.conversions_absolute_change_point_estimate
    conv_error = metrics.conversions_absolute_change_margin_of_error
    conv_lower_bound = conv_lift - conv_error

    if conv_p_value <= P_VALUE_THRESHOLD
      if conv_lower_bound > 0
        puts sprintf(
          "Significant Success: Conversions increased. Even at the lower " \
          "bound, the lift is %.2f. Promoting changes.",
          conv_lower_bound,
        )
        promote_experiment(client, customer_id, experiment_resource_name)
        return
      elsif (conv_lift + conv_error) < 0
        puts sprintf(
          "Significant Decline: Even the upper bound (%.2f) is below zero. " \
          "Ending experiment.",
          conv_lift + conv_error,
        )
        end_experiment(client, customer_id, experiment_resource_name)
        return
      end
    end
  end

  # 2. Evaluate click volume as a secondary signal.
  # This is helpful as an early indicator or for lower-volume accounts.
  if has_click_metrics
    click_p_value = metrics.clicks_p_value
    click_lift = metrics.clicks_point_estimate
    click_error = metrics.clicks_margin_of_error
    click_lower_bound = click_lift - click_error

    if click_p_value <= P_VALUE_THRESHOLD && click_lower_bound > 0
      # We have a directional winner: high confidence in more traffic,
      # but not enough data to confirm conversion impact yet.
      puts sprintf("Click volume is significantly up (+%.1f%%).", click_lift * 100)

      # Graduation is only supported for separate campaign experiments, not
      # intra-campaign experiments where there is no separate treatment campaign.
      experiment_type = row.experiment.type
      if experiment_type != :ADOPT_BROAD_MATCH_KEYWORDS && experiment_type != :ADOPT_AI_MAX
        puts "Graduating treatment campaign for further manual analysis."
        graduate_experiment(client, customer_id, experiment_resource_name)
      else
        puts "Intra-campaign trial detected: graduation is not supported. " \
             "Continuing to run the experiment to gather more conversion data."
      end
      return
    end
  end

  # 3. Print status if no action was taken.
  if has_conv_metrics || has_click_metrics
    conv_status = if has_conv_metrics
      sprintf(
        "Conversions (p=%.2f, lift=%.2f +/- %.2f)",
        metrics.conversions_absolute_change_p_value,
        metrics.conversions_absolute_change_point_estimate,
        metrics.conversions_absolute_change_margin_of_error,
      )
    else
      "Conversions (not populated)"
    end

    click_status = if has_click_metrics
      sprintf(
        "Clicks (p=%.2f, lift=%.2f +/- %.2f)",
        metrics.clicks_p_value,
        metrics.clicks_point_estimate,
        metrics.clicks_margin_of_error,
      )
    else
      "Clicks (not populated)"
    end

    puts "Inconclusive: No significant action taken. #{conv_status}, #{click_status}. " \
         "Allowing the experiment to continue running."
  else
    puts "Conversion and click performance metrics are not yet populated. " \
         "Allowing the experiment to continue running."
  end
end
evaluate_and_update_experiment.rb
      

Perl

This example is not yet available in Perl; you can take a look at the other languages.
    

curl

Note: While a direct REST code sample for this step isn't provided here, you can achieve this using a manual REST request.

Refer to the Google Ads API REST interface documentation and the method-specific reference pages. You will need to construct the JSON payload based on the proto definitions.

Key Resources:

• Using REST
• REST Interface Structure
• JSON Field Mappings
• Consult the REST API Reference for the specific service and method.

Benefits over campaign reporting

Direct experiment reporting offers several advantages over querying campaign reports separately:

• Centralized metrics: Retrieves metrics for control and treatment arms in a single row.
• Statistical confidence data: Provides calculated p-values, point estimates, and margins of error.
• Efficiency: Eliminates the need to manually join or compare results from multiple reports.
• Intra-campaign support: Supports control-versus-treatment comparisons for intra-campaign experiments, where traffic splits within a single campaign.

Campaign reporting

Across all supported Google Ads API versions (v23 and later), for experiments that create separate treatment campaigns (for example, SEARCH_CUSTOM), you can query the campaign resource and use the campaign.experiment_type field to identify BASE (control) and EXPERIMENT (treatment) campaigns. This approach is useful when you need to segment metrics at a more granular level (such as by ad group or keyword) or view campaign metadata that is not available on the experiment resource. However, campaign reporting requires you to perform performance comparisons and statistical calculations manually.

You cannot use campaign-level reporting to compare arms for intra-campaign experiments, because the traffic split happens internally within a single campaign. Querying the campaign resource for an intra-campaign experiment returns only aggregated totals.

Brand Lift reporting

In Google Ads API v25 and later, evaluate how your ad campaigns influence brand perception by querying the read-only (OUTPUT_ONLY) LiftMeasurementFlight, LiftMeasurementConfig, and Brand Lift breakdown resources (LiftMeasurementAgeRange, LiftMeasurementCampaign, LiftMeasurementDevice, LiftMeasurementGender, and LiftMeasurementVideo). In Google Ads API v27 and later, you can also select the lift_guidance field (lift_guidance.outcome and lift_guidance.guidance_message) for row-level statistical interpretation.

For survey response reportability thresholds, empty-response (results: []) diagnostics, outcome interpretation, and GAQL query examples, see Brand Lift reporting in the Lift reporting guide.

Conversion Lift reporting

In Google Ads API v25 and later, Conversion Lift reporting measures the incremental impact of your ads on conversions, conversion value, cost per incremental conversion (iCPA), and incremental return on ad spend (iROAS) by comparing an exposed group against an unexposed holdback group across daily cumulative evaluation snapshots (segments.conversion_lift_start_date and segments.conversion_lift_end_date) on the LiftMeasurementConfig resource. In Google Ads API v26 and later, you can also discover linked configurations and campaigns through the campaign.lift_measurement_config and lift_measurement_config.campaigns fields, and in Google Ads API v27 and later, select lift_measurement_config.lift_guidance for row-level statistical interpretation.

For study and flight discovery, cumulative snapshot date ranges, conversion action scopes (SELECTED versus ALL), dimensional breakdowns, reportability thresholds, and GAQL query examples, see Conversion Lift reporting in the Lift reporting guide.

A/B + Conversion Lift reporting

In Google Ads API v25 and later, A/B + Conversion Lift studies combine a two-arm experiment (discovered through the ExperimentArm resource and the experiment.lift_measurement_config field) with holdback measurement on the LiftMeasurementConfig resource. Include the segments.experiment_arm segment and the Bayesian winner score metrics (metrics.*_winner_score) to evaluate per-arm causal lift and head-to-head winner probabilities.

For experiment arm discovery, per-arm and combined-arm queries, winner score interpretation, and multi-study batch queries, see A/B + Conversion Lift reporting in the Lift reporting guide.

Search Lift reporting

In Google Ads API v26 and later, Search Lift reporting measures the incremental increase in organic search query volume across Google Search and YouTube driven by your ad campaigns. Query the SearchLiftKeywordBundle resource for configured keyword bundles and the LiftMeasurementConfig resource (with lift_measurement_config.lift_guidance in Google Ads API v27 and later) for relative and normalized incremental search metrics.

For Search Lift segmentation rules, metric definitions, and GAQL query examples, see Search Lift reporting in the Lift reporting guide.

Best practices

The following best practices apply to standard A/B experiments (such as campaign and intra-campaign experiments). Lift measurement studies (Brand Lift, Conversion Lift, and Search Lift) use study-specific configurations and report 90% one-sided confidence bounds (*_p90_lower_bound and *_p90_upper_bound, which together form an 80% two-sided confidence interval with p_value <= 0.10) rather than a 95% confidence threshold. See the Lift reporting guide for lift study thresholds and interpretation.

• Select an appropriate confidence level: Setting a lower p-value threshold can provide directional guidance faster, especially with lower budgets or conversion volumes. A 95% confidence level (p_value <= 0.05) is the academic standard and provides higher precision over a longer timeframe.
• Run experiments for long enough: Run experiments for at least 4 weeks to account for weekly performance cycles, conversion delays, and learning periods.
• Give time for ramp-up: For campaigns that use automated bidding or test new features, disregard the first 1–2 weeks of data so that bidding models and traffic levels can recalibrate to the split.
• Use 50/50 splits: A 50/50 traffic split is generally the fastest way to achieve statistically significant results.
• Schedule in advance: Set your experiment start date 3–7 days in the future to allow time for ad review and approval processes.

Important: You can only run one standard A/B experiment per campaign at any given time.