an immediate fast slump on 5th Nov.
So if the "slump" occurred on the very day lockdown started, lockdown cannot have been responsible for it.
It does seem a bit sensitive, I was surprised by the suddenness of the correction.
Yet not sufficiently surprised to question whether it was caused by lockdown?
Yet not sufficiently surprised to question whether it was caused by lockdown?
Correct, in explanation,I posited that the Tier 3 in northern England in mid October may have been taking effect before the 5th Nov, with national lockdown as the final nail. It seems plausible.
the site appears to be using self-reported symptoms.
That is a strength as well. It avoids the government's PCR based test system, putting it outside politics. It is interesting to observe the consistency between two very different schemes, that consistency imbues greater faith in both systems.
I would add also that the curve is for the country as a whole, and there will be geographic variation in time baked into it.
The first peak in early November could well have been dominated by cases in the North (which reached a peak then declined before lockdown could have had an effect) while the second rise looks to be dominated by the populous South East.
You might be right there. Quite strict T3 arrangements were imposed in the north West in mid October . Perhaps all these in conjunction caused the sudden peak around the time of national lockdown Nov 5. I cannot be sure; there was a lot going on. It is not as cut and dried as it looks.
The point I was trying to make is that when trying to understand a mathematical curve
I know , that is why I added it takes nature time to react. Time is the factor behind all that calculus. But I am not looking at a function, although it looks surprisingly like a function's output. I am looking at the superposition of some exponential function (natural virus behaviour) with the effects of law making layered in, and the individual choices of 70 individual million people as well. Hence I am not trying to understand a mathematical curve, it would be fruitless.
I am pointing at 2 or 3 obvious and dramatic features in the path the virus took, and correlating as best I can those abrupt features to obvious, large legal changes. And they seem to fit. It may be chance, but I don't buy that. It is likely that such all encompassing legal constraints on behaviour would alter virus transmission, it's not proof I seek, but mere confirmation. And that is what I saw. Perhaps I should say as a title: Sorry to break this: all encompassing legal constraints on behaviour alter virus transmission rates, but it's not snappy!
