A School of Emergent Priorities poster attempts to repeat the coffee-cart queue's celebrated ranking indicator on a second campus queue, and traces the original finding to a shared academic-year rhythm.
A new poster repeats the coffee-cart queue's leading-indicator finding on the printer queue, and traces the original correlation to the academic calendar
Two years ago, a School of Continuous Improvement poster reported that coffee-cart queue length led the University’s global-ranking trajectory by two quarters, peaking at r = 0.78. A new poster from the School of Emergent Priorities repeats the exercise on a different queue, and gets a different answer.
Dr Petra Umbile and Dr Marek Solheim tracked queue depth at six shared printers for twenty-one months, then ran the same cross-correlation the original study used against the University’s ranking-movement series. Applying the same seasonal adjustment to the original coffee-cart figures brought its own celebrated correlation down from r = 0.78 to a non-significant r = 0.14.
We went looking for a second queue that behaved like the first one. What we found was how much of the first result the calendar had been doing on its own.
— Dr Umbile, Postdoctoral Fellow in the School of Emergent Priorities
The University treats the audit as proof that a well-liked figure earns a second look as readily as an unfamiliar one, regardless of where it was first reported.
“A correlation that only shows up once is still on the record,” said Dr Solheim, Lecturer in the School of Emergent Priorities. “It just isn’t the closed loop anyone was hoping to build on it.”
The full poster is available from the University’s research repository under an open licence, doi:10.5555/slop.gb7aki.