Skip to main content
loser

General: Big Navigation A/B Test With 8 Confounded UI Changes

Hypothesis

If we test a similar change on our any pages as rejected, we should be cautious

NavigationLanding PageE-commerceindustry_leakwalmartgloballoser

Test Results

Key Learning

Problem: Users arriving at the general can't efficiently find what they're looking for, increasing bounce rates.

What was tried: rejected this UI change (Nov 9, 2023). Rejection suggests the change underperformed the control

Why it failed: Navigation changes are risky because they disrupt established muscle memory. Test with new visitors separately.

How to Apply This to Your Site

This test showed that general: big navigation a/b test with 8 confounded ui changes hurt conversions. The change was tested on a landing page page in the e-commerce industry. Avoid replicating this exact approach — instead, consider testing the opposite direction or a more subtle variation.

Before you test: Consider that navigation tests typically require adequate traffic to reach statistical significance. Run your test for at least 2 full business cycles to account for weekly traffic patterns.

What Was Tested

ran a larger redesign experiment of their navigation. If I observed correctly after triple checking, it was a leap variation with at least 8 changes grouped together. Unfortunately, as of this month it seems that the experiment has stopped with no sight of the variation - hinting at a rejection for whatever reason. In retrospect, I do have some ideas along with my personal and mixed bets on these UI changes. All in all, I suspect a possible confounding situation with some negative changes cancelling out the positive.

Methodology

Confidence Level
70%

Build On These Learnings

Save your own experiments, spot winning patterns across your test history, and stop repeating what's already been tried.

Related Experiments

Explore More Experiments