180,000 visitors. The biggest sample we've published.
Eight days, 180,023 randomized Instagram visitors, 2,648 orders. At this scale the error bars vanish: escaped traffic converted +40% better (z = 8.7) and produced +42% more revenue per visitor, outlier-trimmed on both arms.
This performance-apparel brand runs serious paid Meta volume, which made it the largest randomized sample in the portfolio: 180,023 Instagram visitors split across the two arms in eight days.
Escaped visitors checked out at 1.72% vs 1.23% for the webview control — +40% at z = 8.7, a result you could re-run a thousand times and never see flip. Per-visitor revenue was $1.36 vs $0.96 (+42%) with whale orders trimmed from both arms.
Scale is the point of this study. Every objection to a small test — luck, seasonality, one big order — is off the table at 180K visitors. The webview tax showed up here at almost exactly the rate it shows up across the rest of the portfolio.
After the test: The brand rolled escape out to 100% of Instagram traffic at the end of the window.
| Arm | Visitors | Orders | CVR | Rev / visitor |
|---|---|---|---|---|
| A · escaped | 88,143 | 1,518 | 1.72% | $1.36 |
| B · control | 91,880 | 1,130 | 1.23% | $0.96 |
Brand anonymized. Revenue trimmed by the standard outlier rule on both arms (two orders totaling $13,104 removed from the escaped arm, one $11,201 order from control); conversion counts untouched.
Run this exact test on your traffic.
One script tag, 60-second install. Randomized 50/50 from the first visitor — in 7–14 days this page is your data.