Peeking at live numbers during a festive window
Looking at an A/B test every morning through a sale period does not make the result arrive sooner. It makes the stopping rule honest or dishonest.
Journal
Journal
Field notes on A/B test analytics: assignment hygiene, metric choice, and the decisions Malaysian teams actually have to make.
These pieces are written for people who already run experiments. They are not productivity essays.
Choosing a primary metric when checkout is not the whole story
Why a homepage test in Malaysian retail often needs a metric closer to the hypothesis than a site-wide conversion rate.
A non-significant result is still a decision
Holding the control is a legitimate close-out for an A/B test. Treating ‘not significant’ as a reason to keep the treatment live is how clutter accumulates.
Guardrails that belong on the brief, not on Friday’s curiosity
How to choose a short list of guardrail metrics for an A/B test so a checkout lift cannot hide a refund problem.
Do not read the p-value until the assignment file is boring
Why Page Grove Base treats daily variant counts as the first page of an A/B test readout, before anyone discusses significance.