split
split copied to clipboard
Q: Variant consistently strong in the first week, but drops of to no change in the 2nd. Normal?
Hi there,
we've been using the split gem for a while, but we've seen this behavior a couple of times and wonder if it's normal:
We run an A/B test where the new variant is very strong (~4-6% better than control) in the first week (with 100k+ participants), even shows up as 90%+ confidence in the dashboard, but then in the 2nd week (we usually try to run experiment for at least 2 weeks) it just drops off to no real change against the control.
Is this normal? Could we have done something wrong with the setup? Thanks!
Curious to see this issue, because we've noticed this behavior as well!