COVID-19

Covid-19 discussion, bring your own statistics
Post Reply
User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Fri Jan 01, 2021 4:16 pm

Another day, another 50,000 new covids in the UK. Well, not 50,000: 53,285. And not the UK: England and Scotland. Northern Ireland and Wales haven't reported anything today so there's probably about 4,000 cases missing.

613 deaths taking the total to 74125, and that's only England because none of NI, Scotland, and Wales report today. So there could be 50-100 deaths missing and since it's nearly the weekend it'll probably be Tuesday before we've caught up there.
molto tricky

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Fri Jan 01, 2021 5:25 pm

Meanwhile, Italy has 22,211 new covids today but when 14.1% of the day's swabs are positive it's probably the case that this is somewhat of an underestimate. The 7-day average is about 12% and rising while the UK is at about 11% and rising.
molto tricky

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Fri Jan 01, 2021 7:11 pm

James Annan has added the effect of the vaccination program to his model in terms of a reduction of the IFR over the next few months:

https://twitter.com/jamesannan/status/1 ... 6747096064

He hasn't explicitly accounted for the immunity itself "which will have relatively little effect on transmission over this time scale". The model suggests we will be through to herd immunity soon anyway unless there's a very strong lockdown.
molto tricky

KAJ
Clardic Fug
Posts: 197
Joined: Thu Nov 14, 2019 5:05 pm
Location: UK

Re: COVID-19

Post by KAJ » Fri Jan 01, 2021 7:20 pm

KAJ wrote:
Thu Dec 31, 2020 5:48 pm
I'm not convinced, see below. Models don't fit well, but there really isn't much evidence (even visual) of a consistent increase.
By date of death (last 5 zero weighted, day-of-week doesn't help fit)
<snip>

By date of publication
<snip>

That has to change soon, look at
Patients in mechanical ventilation beds, where the R-sq is 99%
<snip>
Well that didn't take long!
Deaths by date of death
OK, the fit isn't very good ( ~ 40%) but I think the evidence for an upwards trend is becoming clear, even zero-weighting the last 5 points.
DateDeaths.png
DateDeaths.png (10.39 KiB) Viewed 540 times

Code: Select all

At 30/12 fit = 566.7 with doubling time = 34.2 days. That time halving in 13.3 days 

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)     6.14114    0.01460 420.644  < 2e-16 ***
poly(date, 2)1  0.46396    0.10199   4.549  0.00012 ***
poly(date, 2)2  0.17702    0.09885   1.791  0.08544 .  
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.06549 on 25 degrees of freedom
Multiple R-squared:  0.464,	Adjusted R-squared:  0.4212 

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Fri Jan 01, 2021 9:01 pm

sTeamTraen wrote:
Thu Dec 24, 2020 4:31 pm
bob sterman wrote:
Thu Dec 24, 2020 2:46 pm
plodder wrote:
Thu Dec 24, 2020 2:34 pm
It’s gone.

https://mobile.twitter.com/TiceRichard/ ... 2773159936
Maybe it has - but I wouldn't believe a word that guy Richard Tice says. He's the Brexit Party chair - known as "Farage's sidekick" and is one of these folk who thinks most cases are PCR false positives.
I think the point here is that the government's handling of this has been so incompetent that even a conspiracist tw.t like Tice can make hay and a lto of sensible people will be nodding along. Apart from one brief moment in that clip where he lets slips that the real point of his story is to show that there is no problem in London ("because they've taken the Nightingale down, so that proves it") and so everyone should get back in the pub immediately, it could equally well have been made by a principled opposition party to show that the whole idea of the Nightingales was flawed from day one because there are no doctors or nurses to staff them. For example, Tice has fooled the otherwise admirable Gary Neville into thinking it was about resources.

Indeed, the same question could have been asked back when the government was about to order 30,000 ventilators or however many it was; it turns out that you can't just get a bloke from Kwik-Fit, or even a regular nurse, to just stand by it and press button B when it goes "beep".
... the Nightingale hospital built in London’s ExCeL centre is expected to take Covid patients next week, for the first time since the spring.

Not that there will be anyone to staff them.
molto tricky

KAJ
Clardic Fug
Posts: 197
Joined: Thu Nov 14, 2019 5:05 pm
Location: UK

Re: COVID-19

Post by KAJ » Sat Jan 02, 2021 4:09 pm

Today's coronavirus.data.gov.uk data is out. Cases by specimen date (excluding Christmas Day = 14,150) shows almost pure exponential growth with doubling time = 14.7 days (with day of week factor), R-sq ~95%
SpecCases.png
SpecCases.png (14.32 KiB) Viewed 457 times

Code: Select all

Analysis of Variance Table

Response: log(SpecCases)
              Df Sum Sq Mean Sq F value    Pr(>F)    
poly(date, 2)  2 4.1394 2.06970 188.260 2.986e-13 ***
day            6 0.6836 0.11394  10.364 3.826e-05 ***
Residuals     19 0.2089 0.01099                      
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Coefficients:
               Estimate Std. Error t value Pr(>|t|)    
(Intercept)     9.96505    0.05494 181.391  < 2e-16 ***
poly(date, 2)1  2.59545    0.18063  14.369 1.17e-11 ***
poly(date, 2)2  0.01161    0.17037   0.068 0.946401    
dayMon          0.40533    0.07419   5.464 2.85e-05 ***
dayTue          0.31398    0.07431   4.225 0.000458 ***
dayWed          0.26584    0.07454   3.567 0.002059 ** 
dayThu          0.13923    0.07488   1.859 0.078525 .  
dayFri          0.24910    0.07436   3.350 0.003366 ** 
daySat         -0.05936    0.07419  -0.800 0.433524    
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.1049 on 19 degrees of freedom
Multiple R-squared:  0.9585,	Adjusted R-squared:  0.941 

OffTheRock
Stargoon
Posts: 91
Joined: Mon Dec 02, 2019 6:52 pm

Re: COVID-19

Post by OffTheRock » Sat Jan 02, 2021 4:30 pm

To much to hope that the 74,510 cases with a specimen date of the 29/12 is some kind of mistake? Apart from the obvious mistake of allowing households to mix 4 days previously.

User avatar
lpm
Stummy Beige
Posts: 2776
Joined: Mon Nov 11, 2019 1:05 pm

Re: COVID-19

Post by lpm » Sat Jan 02, 2021 4:48 pm

OffTheRock wrote:
Sat Jan 02, 2021 4:30 pm
To much to hope that the 74,510 cases with a specimen date of the 29/12 is some kind of mistake? Apart from the obvious mistake of allowing households to mix 4 days previously.
29 Dec was the first day back at work after the bank holidays. So likely that many people delayed getting themselves tested until that day?
What ever happened to that Trump guy, you know, the one who was president for a bit?

OffTheRock
Stargoon
Posts: 91
Joined: Mon Dec 02, 2019 6:52 pm

Re: COVID-19

Post by OffTheRock » Sat Jan 02, 2021 5:32 pm

That might explain some of it, but I don't think all of it. I'm still trying to get my head round the positive cases vs tests processed data and how they do or don't match up.

KAJ
Clardic Fug
Posts: 197
Joined: Thu Nov 14, 2019 5:05 pm
Location: UK

Re: COVID-19

Post by KAJ » Sat Jan 02, 2021 6:00 pm

OffTheRock wrote:
Sat Jan 02, 2021 4:30 pm
To much to hope that the 74,510 cases with a specimen date of the 29/12 is some kind of mistake? Apart from the obvious mistake of allowing households to mix 4 days previously.
See the graph. 29/12 agrees very closely with the model based on the previous month's data. 29/12 was not considered when fitting that model (weight = zero).

User avatar
Opti
Catbabel
Posts: 723
Joined: Mon Nov 11, 2019 11:21 pm
Location: Got a home right by the sea.

Re: COVID-19

Post by Opti » Sat Jan 02, 2021 6:20 pm

There we are then. Gibraltar is f.cked. Incredibly fast acceleration of cases. All the adjoining ayuntamientos in Cadiz province are now locked down as well.
Covid don't give a sh.t about anyone taking control of are borders.
Only a day or so ago, you could fly from UK to Gib without a prior PCR test. Tested only on arrival. By then, you were Gib's problem.
He cannot be killed by conventional weapons. True. He and Mrs Opti are wicked cool.

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Sat Jan 02, 2021 6:30 pm

OffTheRock wrote:
Sat Jan 02, 2021 4:30 pm
To much to hope that the 74,510 cases with a specimen date of the 29/12 is some kind of mistake? Apart from the obvious mistake of allowing households to mix 4 days previously.
shpalman wrote:
Thu Dec 24, 2020 8:12 pm
.... It seems ridiculous that we might be seeing 80,000 on one of the days next week but maybe we will.
Italy only has 11,831 new covids today (and 364 deaths) but that's 17.6% of the days tests; it clearly relates to less testing on New Year's Day.

Not sure if it relates to saving up a few cases and deaths so that a higher number gets reported on Wednesday or Thursday next week when the new "colours" get announced...
molto tricky

KAJ
Clardic Fug
Posts: 197
Joined: Thu Nov 14, 2019 5:05 pm
Location: UK

Re: COVID-19

Post by KAJ » Sat Jan 02, 2021 7:04 pm

OffTheRock wrote:
Sat Jan 02, 2021 5:32 pm
That might explain some of it, but I don't think all of it. I'm still trying to get my head round the positive cases vs tests processed data and how they do or don't match up.
When trying to understand the day-of-week dependence of cases by specimen date I tried looking at the relation to test numbers. I was stymied, in part, by different sources and types of tests ("pillars" see link, inter alia) and different meanings of "date".
Finally I gave up trying to understand the day-of-week dependence and settled for being able to model it, so that I could better characterise the underlying trends.

User avatar
Brightonian
Snowbonk
Posts: 581
Joined: Mon Nov 11, 2019 3:16 pm
Location: Usually UK, often France and Ireland

Re: COVID-19

Post by Brightonian » Sat Jan 02, 2021 7:05 pm

Big jump in the number of new cases in Ireland: 3394 today. Over the previous week it ranged from 744 to 1754. Here's hoping it's just an artefact of the Christmas period, but I'm pessimistic.

User avatar
Bird on a Fire
Light of Blast
Posts: 5225
Joined: Fri Oct 11, 2019 5:05 pm
Location: nadir of brie

Re: COVID-19

Post by Bird on a Fire » Sat Jan 02, 2021 7:21 pm

Portugal slightly relaxed its covid restrictions - including compulsory work-from-home, closing shops at 1:00 and a curfew - during the weekends around Christmas and New Years, which had been in place since early November.

The slight relaxation in covid restrictions looked like this:
scrot.png
scrot.png (166.39 KiB) Viewed 368 times
The peak in reports was 31 December, though I'm not sure if there were delays because of the holidays.

Hospitalisations are still trending downwards, thankfully. I hope we don't see a big spike next week.
He has the grace of a swan, the wisdom of an owl, and the eye of an eagle—ladies and gentlemen, this man is for the birds!

OffTheRock
Stargoon
Posts: 91
Joined: Mon Dec 02, 2019 6:52 pm

Re: COVID-19

Post by OffTheRock » Sat Jan 02, 2021 8:10 pm

KAJ wrote:
Sat Jan 02, 2021 7:04 pm
OffTheRock wrote:
Sat Jan 02, 2021 5:32 pm
That might explain some of it, but I don't think all of it. I'm still trying to get my head round the positive cases vs tests processed data and how they do or don't match up.
When trying to understand the day-of-week dependence of cases by specimen date I tried looking at the relation to test numbers. I was stymied, in part, by different sources and types of tests ("pillars" see link, inter alia) and different meanings of "date".
Finally I gave up trying to understand the day-of-week dependence and settled for being able to model it, so that I could better characterise the underlying trends.
I think the pillars are less of an issue. The problem is the dates and perhaps to a lesser extent the fact we don’t count the number of people tested, but the number of tests. I assume it’s because the number of cases is about how many new cases there are on a given day whereas the testing data is all about how many tests our world beating testing system can process not how those tests relate to the number of positive cases.

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Sat Jan 02, 2021 8:25 pm

Number of people tested was being given, but the last data I have is the 22nd of May. They lost track of it after that.

It's not always entirely clear what date is used for postal tests.

This is why I tend to just 7-day average everything.
molto tricky

User avatar
jimbob
After Pie
Posts: 2198
Joined: Mon Nov 11, 2019 4:04 pm
Location: High Peak/Manchester

Re: COVID-19

Post by jimbob » Sat Jan 02, 2021 10:29 pm

shpalman wrote:
Sat Jan 02, 2021 8:25 pm
Number of people tested was being given, but the last data I have is the 22nd of May. They lost track of it after that.

It's not always entirely clear what date is used for postal tests.

This is why I tend to just 7-day average everything.
A similar reason for doing this for most data connected to this.
Have you considered stupidity as an explanation

User avatar
sTeamTraen
Dorkwood
Posts: 1579
Joined: Mon Nov 11, 2019 4:24 pm
Location: Palma de Mallorca, Spain

Re: COVID-19

Post by sTeamTraen » Sun Jan 03, 2021 1:01 am

Opti wrote:
Sat Jan 02, 2021 6:20 pm
There we are then. Gibraltar is f.cked. Incredibly fast acceleration of cases. All the adjoining ayuntamientos in Cadiz province are now locked down as well.
Covid don't give a sh.t about anyone taking control of are borders.
Only a day or so ago, you could fly from UK to Gib without a prior PCR test. Tested only on arrival. By then, you were Gib's problem.
Fark. 686 cases in the last 7 days. That's 2% of the population in a week.

On the plus side, the hospital has 210 beds, which is about twice the per-1,000 population number of GB.
Something something hammer something something nail

User avatar
Brightonian
Snowbonk
Posts: 581
Joined: Mon Nov 11, 2019 3:16 pm
Location: Usually UK, often France and Ireland

Re: COVID-19

Post by Brightonian » Sun Jan 03, 2021 1:06 am

Brightonian wrote:
Sat Jan 02, 2021 7:05 pm
Big jump in the number of new cases in Ireland: 3394 today. Over the previous week it ranged from 744 to 1754. Here's hoping it's just an artefact of the Christmas period, but I'm pessimistic.
Seems there's a massive backlog in reporting.

User avatar
lpm
Stummy Beige
Posts: 2776
Joined: Mon Nov 11, 2019 1:05 pm

Re: COVID-19

Post by lpm » Sun Jan 03, 2021 12:00 pm

Woah, this can't be good.
Chinese authorities have launched an investigation into a mysterious viral pneumonia which has infected dozens of people in the central city of Wuhan.

A total of 44 cases have been confirmed so far, 11 of which are considered "severe", officials said on Friday.

The Wuhan health commission said on Friday it was investigating the cause of the outbreak.

In a statement on its website, it said it had already ruled out a number of infection sources - including influenza, avian influenza and common respiratory diseases.
https://www.bbc.co.uk/news/world-asia-china-50984025
What ever happened to that Trump guy, you know, the one who was president for a bit?

User avatar
lpm
Stummy Beige
Posts: 2776
Joined: Mon Nov 11, 2019 1:05 pm

Re: COVID-19

Post by lpm » Sun Jan 03, 2021 12:01 pm

No wait, getting muddled, that article is from a year ago. Phew!
What ever happened to that Trump guy, you know, the one who was president for a bit?

User avatar
shpalman
Stummy Beige
Posts: 3581
Joined: Mon Nov 11, 2019 12:53 pm
Location: One step beyond

Re: COVID-19

Post by shpalman » Sun Jan 03, 2021 12:05 pm

Yeah whatever happened to that anyway?
molto tricky

User avatar
Sciolus
Snowbonk
Posts: 496
Joined: Mon Nov 11, 2019 6:42 pm

Re: COVID-19

Post by Sciolus » Sun Jan 03, 2021 4:08 pm

Don't worry, I'm sure the authorities won't allow the Chinese New Year, that great national celebration in which large swathes of the population travel across the country to see their families, to spread and entrench the disease.

OffTheRock
Stargoon
Posts: 91
Joined: Mon Dec 02, 2019 6:52 pm

Re: COVID-19

Post by OffTheRock » Sun Jan 03, 2021 4:18 pm

We can always apply border control here and ensure people travelling from affected areas quarantine. Being an island should give us an advantage.

Post Reply