Latest
measurement
media buying
Check an experiment’s assignment counts before reading its uplift
An experiment can produce an attractive uplift while its assignment counts contradict the intended split. A reproducible illustrative example with editable inputs and explicit limits.
Isaac Turner
2 min read
measurement
media buying
·2 min read
Put a Wilson interval beside a small retention estimate
measurement
media buying
·2 min read
Show how a UTC event crosses a reporting-day boundary
measurement
media buying
·2 min read
Reconcile gross purchases and refunds without moving the cohort
measurement
media buying
·2 min read
Find repeated purchase records before reporting revenue
measurement
media buying
·2 min read
Separate payer concentration from average revenue per payer
measurement
media buying
·2 min read
Hold segment weights fixed when a blended retention rate moves
measurement
media buying
·2 min read
Bound a conversion share when some outcomes are unknown
measurement
media buying
·2 min read
Remove immature installs from a D7 retention denominator
measurement
media buying
·2 min read
Measure how much an event table changed after the first snapshot
measurement
media buying
·2 min read
Spot a repeated revenue total after a one-to-many join
measurement
media buying
·2 min read