Built for music and programming teams deciding what to keep, increase, reduce or watch in rotation.
Airplay Live measures how songs hold listeners as rotation builds. But for that signal to be useful, it should also stand up independently of the score itself.
A real signal should repeat. Known biases should disappear after correction. Clear differences should show up, and where no difference exists, the data should stay quiet.
Two Halves, One Answer
It could be noise. Noise would not repeat.
Split-half test · … songs · plays split at random
Split-half agreement (r)
The Big 80s0.39
Box UK0.02
r = 0.39 across … songs
Each dot is one song, scored independently from two non-overlapping halves of its plays. The Big 80s shows repeatable song-to-song differences across … songs; Box UK shows almost none.Airplay Live database · Random non-overlapping play halves
Off the Clock
The hour a song airs should not decide its score.
Schedule bias test · before and after baseline correction
Before baseline correction, tune-outs partly follow the schedule. Once corrected, the relationship with time of day all but disappears: Dance UK drops from 0.38 to 0.00, Box UK from 0.15 to 0.00.Dance UK + Box UK · Before vs. after baseline correction · Airplay Live database
When It Says No
A meter that finds a difference everywhere finds nothing.
Genre-pair test · three stations · POP Score difference · 95% CI
Three genre contrasts sit clearly away from zero, while two stay on it. The meter does not produce similarly large differences across every comparison.5 genre-pair comparisons · 3 stations · 95% confidence intervals · Airplay Live database
One Ballad Every Hour
A test where every radio person already knows the answer.
Off-format test · hourly ballads vs. catalog
Hourly ballads form a clearly lower score cluster. The 34 qualifying ballads average about 8 points below the rest of the catalog, and their median sits lower as well.Dance stream · 548 songs · 34 ballads · Frozen archive Schedule fixed · No smoothing · End-of-hour tune-out matched rest of day
A Window With Nothing In It
Same test, run 999 times on windows with no song behind them.
Clock-window control · Dance UK · 999 runs, no real content
Each run is a made-up three-minute “song” placed at a different time each day. Out of 999 runs, only 6 came close to what real songs show.Dance UK · 999 clock windows · 3 minutes each · No real content
Reference stations are shown for demonstration only. No partnership or endorsement implied.
