3 day periodicity appearing quite robust now.
Again I have no idea why this is. Given only a slight increase in the number of tests today I can only guess that the worst parts of the UK all report on the same day (London?).
The model predicts 1447 cases tommorow but based on this 3 day periodicity I'm expecting a drop.
FYI the model does not account for this 3 day periodicity but it doesn't need to, it's a short term fluctuation that I don't care about that much with regards to the modelling. But if we do see a drop tommorow, that's why.
Originally Posted by: Quantum