Filtering by Segment

The segment filter on the Results page lets you view your experiment results through a narrower lens. Instead of looking at all visitors together, you can filter down to a specific device type, country, browser, or custom segment — and see how the experiment performed for just that group. This is one of the most useful tools for understanding why your results look the way they do.

Where to find the segment filter

The segment filter appears as a dropdown near the top of the Results page, typically above the variation performance table. Click the dropdown to expand it and see all available segment dimensions. Select any segment value to filter the entire Results page — summary cards, variation table, metric sections, and time series chart — to show data for only that segment.

To return to the full results, select All visitors from the dropdown.

Available segments

The following segments are automatically available for all experiments:

Device type — Desktop, Mobile, Tablet. Filter to see how results differ between screen sizes and interaction modes.
Country — any country that had visitors during the experiment. Filter to see results for a specific geographic market.
Browser — Chrome, Firefox, Safari, Edge, Opera, Samsung Internet. Filter to see if results vary by browser.
Platform— the visitor's operating system (macOS, Windows, iOS, Android, Linux). Filter to see OS-level differences.
Language— the visitor's browser language. Filter to see results for English speakers vs French speakers, etc.
User type — New or Returning. Filter to see whether the experiment worked differently for first-time vs repeat visitors.

In addition to these automatic segments, any custom segments you have sent via avsb.track.segment() will also appear in the filter dropdown, organized under the segment key name.

How filtering works

When you select a segment filter, A vs B recalculates all the results metrics — visitor counts, conversions, conversion rates, winning probability — using only the data from visitors who belong to that segment. The variation assignments remain the same; you are simply looking at a subset of the enrolled visitors.

Because you are now looking at fewer visitors, the credible intervals will widen and the winning probability may drop. This is expected — the smaller the sample, the less certainty. For segment analysis to be meaningful, you typically need a few hundred visitors within the segment per variation.

Common use cases

Mobile vs desktop comparison

Your overall results show a modest lift, but you suspect the experiment worked better on mobile. Filter to Mobile and then to Desktop to compare. If mobile shows a strong win and desktop shows no improvement, you have a mobile-specific result — and you might decide to roll out the change mobile-only first.

Geographic differences

You are running a global experiment but your largest market is the US. Filter by Country = United States to see how the experiment is performing for your biggest segment. If the US result looks good but international results are neutral, you can proceed confidently for US traffic while giving the experiment more time for the international segment.

New vs returning visitors

Filter by User Type = New to see how first-time visitors responded to your experiment. Then filter by Returning. If the experiment produced different results for each group, that information can guide your personalization strategy — maybe the winning variation is great for new visitors but the control is better for returning ones.

Custom segment analysis

If you sent custom segment data like subscription plan or user tier, filter by those to understand whether premium users responded differently from free users. This kind of segment analysis often reveals insights that the aggregate result hides.

Treat segment filtering as exploratory analysis rather than definitive proof. When you filter to a segment, you are running many implicit comparisons — one per segment — which increases the risk of finding a "significant" result by chance. Use segment filters to generate hypotheses, then validate those hypotheses with dedicated experiments targeting those specific segments.

Active filters appear in the URL. Date range writes itself as ?from=YYYY-MM-DD&to=YYYY-MM-DD; each segment selection writes a repeated ?segment=key:value param. Multiple values for the same key combine with OR — selecting country: US and country: UK shows visitors from either country. Different keys combine with AND — adding device: mobile on top narrows to mobile visitors from the US or UK.

You can bookmark a sliced view, share it with a teammate, or paste the link into Slack — opening it restores the same filters on load. Date presets like "Last 7 days" write the absolute dates, not the preset name. A link shared on a Tuesday for "Last 7 days" will still show the same Tuesday-to-prior-Tuesday window when opened on Friday — the link reproduces the exact view, not a rolling window.

The baseline variation and the statistical engine are not part of the shared link — they're per-viewer rendering preferences. The recipient sees their own baseline / engine choice for the same sliced data.