Statistics

Coronavirus Update XV: The Curse Of Karen

All the good stuff, caveats, code, data sources and explanations are linked, some in Update III, and the most important in Update II, Update IV, Update V, Update VI, Update VII, Update VIII, Update IX, Update X, Update XI, Update XII, Update XIII, Update XIV, Bayes Theorem & Coronavirus, and the Sanity Check Perspective, so go to them first before asking what-about-this-and-that. Skip to the bottom for the latest model. Thanks to everybody emailing me sources, including Ted Poppke, Jeff Jorgensen, Jim Fedako, Joe Bastardi, Philip Pilkington, John Buckner, Harry Goff, John Goetz, Warren McGee, Robert Kinney III, Paul Hainey, Darren Nelson. https://www.wmbriggs.com/post/30606/. I’m way, way behind emails. We have to turn in the book soon.

Assorted Nitwitery

True. Six of my eight slaves died from coronavirus. The price for new ones is really going to skyrocket.

The designer was later found and returned safely to his asylum, sources say.

Calls to add ‘climate change’ to death certificates — New study demands ‘climate change’ be added as ‘pre-existing condition’

Now that the coronadoom panic is ebbing, and given that the left learned how easy it was to roil and enslave the frightened, they will move to something else.

They’ll try a “second wave”, sure. That will work to some extent, but after summer it won’t have the same cutting urgency. They’ll try Orange Man Bad, but, come on. With Biden’s incipient dementia, that’s not going anywhere.

They always have global cooling, also known by many other names. An ICD-10 code for dying from “climate change” is a clever move. Journalists, the enemies of the people, can latch onto it and trumpet daily “death tolls.” Hey: it worked with coronadoom. It is certainly worth trying. And so they are.

CDC Activities and Initiatives Supporting theCOVID-19 Response and the President’s Plan for Opening America Up Again (pdf)

Sixty full pages of bureaucratic brilliance. This is government by people sitting around a (virtual) table saying “I feel…” and where their feelings become law.

“Ask customers to wait in their cars or away from the establishment while waiting to be seated.”

“Reduce occupancy and limit the size of parties dining in together to sizes that ensure that all customer parties remain at least six feet apart (e.g., all tables and bar stools six feet apart, marking tables/stools that are not for use) in order to protect staff and other guests.”

Six has replaced 0.05 as the magic scientific number.

Two headlines:

More than 5 million Americans will be infected with coronavirus and 290,000 will die by the end of July if social distancing isn’t adhered to, according to COVID-19 model

Scientists propose a 50 days on, 30 days off coronavirus lockdown strategy: “In an EU-backed study published on Wednesday, a cohort of researchers from nine countries simulated how various lockdown strategies would impact the spread of the coronavirus.”

I’ve tried to explain many times that models can only say what they’re told to say. All models. Every model. Even our models.

I make my model say “the shape of the viral outbreak shall resemble a logistic curve.” That was all me. Indeed, way back when this started, I created the model for fun as a class project, and only because so many were chimping out about “Exponential! Exponential!” (Which was always an impossibility.)

My initial model for the evolution of an insane reaction was woefully inadequate. I didn’t foresee how what was clearly going to be a routine pandemic (and all are deadly) would turn into a massive lurch toward the left singularity. There’s no excuse for this on my part, because I’ve been preaching its imminence for years!

Anyway, those models predicting more coronadoom and how we should have liberty on Tuesdays and tyranny of Thursdays are only doing what their designers told them to do.

Every single time you hear of a model—any model anywhere—ask yourself these two questions: (1) Why does this guy want me to believe it? (2) Has that model proven itself before in making skillful prediction of data never before seen or used in any way?

If the answer to (2) is “No”, be skeptical. If the answer to (1) is “THE SCIENCE says so”, run away.

Juiced Numbers

Journalist death count: 92,464.

CDC death count: 73,639.

The CDC is about four days behind journalists, but it’s clear the number the media is touting is much higher. They’re all in their hovels now trying to craft the perfect headline for announcing they — I emphasize they — have broken the 100 thousand barrier. Watch for this. There will be a gibbering chorus of ecstasy.

Team Trump Pushes CDC to Revise Down Its COVID Death Counts

President Donald Trump and members of his coronavirus task force are pushing officials at the Centers for Disease Control and Prevention to change how the agency works with states to count coronavirus-related deaths. And they’re pushing for revisions that could lead to far fewer deaths being counted than originally reported, according to five administration officials working on the government’s response to the pandemic.

This is why we’ll instead (below) look at the all-cause deaths. Nobody’s numbers can be trusted.

How Many Are Infected?

We’ve seen at last confirmation from the CDC that the case fatality and infection fatality rates do not match the naive rates—which we have been saying for weeks and weeks.

If you divide the reported deaths by reported cases, you get this chart, for the world and US.

Call these the naive case-fatality rates. Like we’ve been saying, there is no way this bug is killing 5-7% of those it infects, or even that many of those who show symptoms. (That these plots are on the way down, shows you that testing is increasing and deaths are falling.)

There are three rates we need to know:

  1. Raw fatality rate: number actual dead / number of people.
  2. Infection fatality rate: number actual dead / number of infected.
  3. Case fatality rate: number actual dead / number of symptomatic or hospitalized.

The CFR is the most ambiguous, because it’s not well measured. Does a person have to go to the hospital to count? Well, many are keeping away (always wise).

The IFR is clear, as is the raw fatality rate.

As of today: World Raw Fatality Rate is 0.000046. US RFR is 0.00028.

These may be taken as crude estimates of “Chance any person in the world dies from COVID” or “Any American does.” Are they small or large?

Anyway, we need IFR and CFR, which we can use to estimate the total number of actual infected people and actual cases. My own investigations, which come close to the CDC’s numbers are that the IFR is likely somewhere 0.0015 to 0.0026. The CFR is likely between 0.003 o 0.013.

These are in the range of all past pandemics where measurements exist; they are close to Swine flu, and given the body count, coronavirus looking like a Swine flu-like event.

We get this chart for the world:

The two solid lines estimate actual number of infected people; the dashed estimate actual cases; and the dotted is the reported cases. (I have yet to add this legend in the plot: ggplot2 is worse than an alchemists spellbook.)

Same for US:

You can see that the number of infected people, US or world, is much, much higher than the reported cases. As is necessarily true! This bland statement of obvious fact is what got Ioannidis in trouble with the The Science Says crowd.

As I have been warning you and we have been seeing, that they’ll use testing to reveal already-present infections as if they were new in an effort to keep the panic going. We see this below. And if you understand this, could you please share this notion with others so that we end this nonsense sooner?

All Dead

US weekly all dead per capita (up to 2 May; last two weeks left off because they’re too low and will be adjusted upward greatly later; this uses all three sources linked from two weeks ago):

Raw numbers, with official COVID deaths subtracted:

Since the dashed line doesn’t drop as usual, this suggests the lockdown is killing people. Worse in England.

England & Wales week all dead per capita (up to 9 May):

Raw numbers, with official COVID deaths subtracted:

Again, since the dashed line doesn’t drop as usual, this suggests the lockdown is killing people.

Global Model

NOTICE The Southern Hemisphere is just entering its cold & flu season. Look for the media to report deaths and infections in Brazil and elsewhere as if they were ignorant about the tilted earth revolving around the sun.

My fingers almost can’t write it, but these are models of reports not actual numbers. Reports are what count, to us, because it’s reports that make men mad.

Totals:

There’s the logistic shape I told the model to say! New totals: 5.9 million reported cases, 350 thousand deaths. Last week “reported cases 5.2 million, reported deaths 330 thousand”. Convergence is coming! For deaths, not cases.

Daily Cases:

See what I mean? Testing has increased, and to a large extent the infections already there are being revealed. DO NOT LET THIS FRIGHTEN YOU!

Daily Deaths:

The US accounting for about a quarter of all reports accounts for the drop, since it’s Memorial Day weekend. It will surely spike back up. The model does not know this, because I didn’t tell the model this, so it reports the prediction you see.

As long as we expect this, we won’t fear.

USA! USA! USA!

Totals:

There’s the model, doing what it’s told again. New Totals: 1.7 million reported cases, 94 thousand reported deaths. Last week: “reported cases 1.6 million, reported deaths 88 thousand.” Getting there! We’ll see why the under prediction in the daily numbers.

Daily Cases:

Look how the cases refuse to fall! Boo! We already know why. The model does not see this, and so remains mute on it.

Daily Deaths:

Same caution: Memorial day weekend etc. I’ve said 100 times, but this is reported deaths, not actual ones. The CDC is 10-15% lower than reports. Our model is under-predicting reports by about the same. Thus it’s probably a good prediction of actual deaths.

Anyway, we’ll soon have to find something to scare ourselves with.

To support this site and its wholly independent host using credit card or PayPal (in any amount) click here

Categories: Statistics

27 replies »

  1. I liked the bumper tables in a restaurant I saw in a news article. A restaurant has bumper tables 6 feet in diameter. I wondered about food fights, etc, but thought that might actually be a huge bonus after our incarceration at the hands of tyrants.

    Dump all the modelers is in the ocean in a small boat and let them take their chances. Anyone caught making models to take bets on what happens with the modelers will join them in a “second wave”.

    The media is composed of LIARS LIARS LIARS. I hear there is even a test and if you accidentally tell the truth, you’re flogged and dumped in the Sahara Desert. The real question is why even complete idiot, moron brain-dead fool still tune in. The stupid is stifling. We have no answer and studies have proved pointless. We think it’s just how stupid human beings are……

    I hate computer models, not fond of graphs. I’m working on a EM pulse to destroy the insanity and will then incarcerate anyone even saying “smart phone”, computer, etc. It’s my version of “nuke em from space”.

    Bill Gates wants 90% of the population dead (I read that on a conspiracy site, of course) and they claim vaccinations are the method he wants to use. Seriously, just tie up the GrubHub drivers, the meat packers, any chefs and that 90% will occur in a month in the USA. I have never seen such helpless babies as we have in this country. Maybe if we don’t want to repeat the stupid staying home like mindless amoeba, homeschooling might be a very good option. Assuming the parents don’t already possess the sheep gene……

    Note: I know you can’t fix stupid. But I suspect there are pretenders out there and we need to ferret them out and show them stupid is not the way to go. Or dump them in the Sahari with the jouralists if they persist in the stupid game…..

  2. So far Australia has recorded 102 deaths from (or more strictly speaking WITH) Covid – 19. Australia has also tested 5% of the population to date for Covid 19. The death rate is still way below last years death rate for Flu. Death rate for flu in 2019 in Australia approx ten times the current Covid 19 death rate which currently stands at 0.415 per 100.000. 2019 death rate for Flu was 3.9 per 100,000.
    Winter is coming to Australia – maybe the numbers will change a bit on the upwards side. Academics are warning of a second wave. Still waiting. I still see no evidence of a pandemic of the proportions of the Spanish Flu – God help us if we get one of those soon – how on earth will the media cope?
    I mourn for our collective trashed economies.

  3. The CDC has already been caught juicing the infection number as reported in the Atlantic by combining positive virus tests with positive antibody tests. The Atlantic, given its very liberal leanings, tries to spin this as something bad for red states but it really just makes the virus appear to be much more active than it actually is. https://www.theatlantic.com/health/archive/2020/05/cdc-and-states-are-misreporting-covid-19-test-data-pennsylvania-georgia-texas/611935/

  4. RE: Journalist death count: 92,464….CDC death count: 73,639.

    The CDC count from what I can tell from FluVIEW is probably close with a caveat
    https://gis.cdc.gov/grasp/fluview/mortality.html

    Running the “raw” numbers for 2017/2018 and 2019/2020 from week 40 (first week in October) through week 20 (Mid May with modest extrapolation for 2020)

    2020 … … … … … … … … … … … … … … … … 2018
    Influenza … Pneumonia … …. … … … … Influenza … Pneumonia
    8832 … … … 142183 … (151015) … …. 15412 … … 127310 … (142725)

    For 2018, CDC had originally pegged the flu causing 80000 deaths (142725 – 62500 (Expected deaths for that season) or 80000 excessive P&I deaths
    They downcast the flu for 2018 to 61000 (apparently expected deaths should have been higher than originally guesstimated)
    Now if this were a typical flu year, we’re running about 10000 higher or 70000 – 90000 “flu” deaths depending on what the expected deaths should have been. Given we had a “healthy” flu season going into 2020, it’s now necessary to somehow assign raw deaths to flu or covid; if we take the end of February to first week of March, we end up with 71000 – 75500 … CDC seems to know it’s business (do we now get to do some “excessive death” recalculation ;-).

  5. I get a kick out of the Karen meme, but I know some very nice people named Karen so perhaps I’ll go “old skool” and call these annoying folks “nags” instead. Covidnags, anyone? 😉

  6. So reading Dr Strings article reminded me of why the lavatories in the science buildings of my University, had “Sociology Degrees – Please Take One” scrawled above the toilet tissue dispensers…

  7. How about, “Covid Kilgores,” after Robert Duvall’s character in “Apocalypse Now”?

    I believe that, like Col. Kilgore, the hysterics will be utterly lost when this war ends.

  8. What’s the point of statistical analysis when the death rate is completely
    made up? How can we believe that the U.S. with 3% of the worlds population
    has such a high percentage of deaths? This from ostensibly the ‘best’
    healthcare system in the world drummed into us from birth. We pay the
    highest prices for drugs and for what is something rather less than mediocre
    care. I give the devil his due and as many people as possible seem to have
    expired on ventilators, in nursing homes, and by withholding o proven
    anti-viral medication that for all practical purposes is quinine. Stock up on
    gin and ‘tonic’ which was invented by the British East India Co. for use in
    their tropical slave states to ‘control malaria’. Even if it does nothing you’ll
    die at home and happy. I’m almost positive juniper’s good for you too but
    you must add lime or tastes just like medicine.

  9. From my firm, which has stayed open with in-office distancing and liberal work from home accommodations added where this had been prohibited, so far:

    4800 tested (volunteers, one is not compelled to be tested):
    68 positive antibody, with
    57 confirmed (so far) via more reliable secondary testing

    That’s people showing antibodies who had no idea they were infected, or, who knew or suspected they had been infected but recovered and risked being tested.

    Data is being collected & reported on an ongoing basis (the numbers may increase, not decrease, as not all the test results are in for all those 4800, and counting).

    OTHER

    Annual abortions in the US have in recent years been about 600,000 per year. Not so long ago exceeding 1 million per year. Mostly for convenience. Cumulative deaths due to abortion, US only, is on the order of 40 million. That’s more than the population of Sweden, or, about two-thirds the UK’s population.

    Society (as opposed to large subgroups) seems to have nary a concern about that …

  10. Sorry to put that link in this is yet again big pharma telling you
    something that has been in use for centuries and is safe is now scary.
    They’ve got some high priced sure fire cure in the wings that in all
    likelihood is not as safe or effective.

  11. I’m quite surprised not to have seen mention in articles or comments on this blog the situation regarding vaccine development by the University of Oxford, UK. It seems that project leader Professor Adrian Hill, director of the University’s Jenner Institute, has reduced his predicted probability for successfully testing a vaccine by September, 2020, from 80% to 50%, because of a resource scarcity issue. The scarce resource in question turns out to be people infected with COVID19:
    ***Exclusive: Oxford University Covid-19 vaccine trial has 50 per cent chance of ‘no result’***
    https://www.telegraph.co.uk/news/2020/05/23/oxford-university-covid-19-vaccine-trial-has-50-per-cent-chance/
    I didn’t really expect to see this played up in lame-stream media editorial content, for two reasons: it mitigates against the common agenda of inducing and maintaining panic; and because there seems to be a minimum IQ requirement for comprehending irony…

  12. 1. quinine use in malaria, very old news. See can you spot the word in the drug name?
    2.
    The Oxford trial was predicted back in March, again, on video record, explaining that this is just one of many common reasons which vaccines of this sort do not make it to market. It was the same for SARS 1. This time, there will be candidates or voluntary vaccination prior to inoculation with the virus together with trials in other countries. Some are continuing regardless of the bitter hecklers.
    I Note CNBC covered in similar bitter tone a report from a left wing thinker who was ALSO complaining about the Oxford vaccine’s virtuous problem. Something about American money! Wow the two extremes so often agree when the arguments go sour. Default position, blame the UK. *we’re used to it and it wore thin years ago. It’s a kind of flattery, really.

  13. Johns Hopkins University Mortality analysis is where I go to check the numbers.
    They are behind the number that a straight google search returns but after a few hours the numbers always agree. CNN lags behind by a day.
    Last checked the number is 99. something.

    Mr Briggs, I don’t believe you believe what you say you believe.
    Trump believes covid 19 is serious. He simply has a different idea on how it should be managed. I hope he’s not opening up too early. Although the testing is far more readily available over there.
    I wish the US every success and am very much hoping Trump will win. Think he’s been done by his own side, though, AGAIN. Those supposedly on his side appear to be cutting things a bit fine.

  14. @Joy From your reply, I surmise that you have either failed to achieve a passing grade on your irony comprehension examination, or that you are a victim of the pandemic lack of humor disease. Possibly both. Nothing bitter about my remark, honey. A shortage of infected subjects on whom to conduct a vaccine test is an unmitigated ***GOOD*** thing. Don’t you agree? To me, it’s sort of like a shortage of subjects on which to test a new, theoretically more merciful, execution technique. Before you misunderstand (or are tempted to misconstrue) once more, I am in no way identifying or equating vaccination with execution, beyond the statement that an absence of the need for either is a positive value. The irony, since I apparently need to explain it in a more straightforward fashion, using simpler language, is that such a shortage of infected subjects for testing doesn’t exactly support the apocalyptic (meaning “end of the world”) vision of COVID19 that most media and government lackeys have promulgated.

  15. See? Bitter irony!
    0/10 for humour. Must do better.

    The irony (for me) is that listening to the more extreme remarks in these parts so often resemble extreme remarks from those who are of the exact opposite leaning. The characters are switched and the specifics of the conspiracy are adjusted for suit the prejudice.

    Then there are those ironically just getting on with dealing with a pandemic.
    I’m on their side.

    Far be it for anyone to admit that any kind of real disaster has been averted. *that was sarcasm.

    How ever, it had been handled, I was never waiting for someone to tell me what to do.
    Nobody here, and I presume in the US, believed they would be able to persuade free, cynical, people, to stay inside and behave so relatively well for so long. We’ve all been surprised. That’s something on which all can see as a virtue. Sometimes people ARE nice to each other.

    Trouble is, those given to paranoia are already reading into the tea leaves and claiming it’s the foundations for the next part of some grand plan.

    I’m optimistic , that this will heighten public awareness of how governments make policy decisions, what evidence is presented in favour of the concept of climage.
    Which is why they’re getting in early, too.

    Nobody ever said it was going to be an end of the world event. Nobody I heard, anyway.
    Just potentially life changing for many.
    It has been twice as bad as Patrick Valance’s best outcome prediction for loss of life.

  16. Briggs: “Again, since the dashed line doesn’t drop as usual, this suggests the lockdown is killing people.”

    Looks to me that both graphs show the dashed line falling – what am I missing? Perhaps a better explanation needed?

  17. ” . . . ask yourself these two questions: (1) . . . ”

    There’s a simpler way , ala Thomas Sowell:

    (1) Will this person pay any price for being wrong?

    No? Then it’s worthless. This also works for all sorts of things beside models, such as political polls, campaign promises, free advice, comments in blogs, etc.

  18. Joy
    Well said
    Gareth
    Look at the peak of the dashed line.
    For the US the peak almost reaches the peak at the beginning of this flu season. It certainly exceeds any time during last year’s flu season (not that last year’s was very notable, but the point is the dashed line should’ve remained more or less flat – remember the “flu” data represents “excessive deaths” over a more or less flat “normal” death – this says “otherwise normal” deaths rose – why?)
    But if you look at the UK, the dashed line peaks as high as their 2017/2018 flu season! We had 61,000 deaths that year (it doesn’t look like UK’s was that insignificant – “normal deaths” should NOT exceed bad flu seasons)

  19. On the England and Wales numbers. Why do you not include Scotland and N Ireland as well? The data is given in total for all four regions. Why not use all of the data? It is available on line, according to our experts.

    Regarding the remark about lockdowns and killing people, The amount of circulating infection prior to stopping or reducing transmissions is crucial in considering the overall effect. Saying, “look what happened to death rate during lockdown” is not the measure as to whether lock downs “save lives”. And you know it!

    The lockdown is not the end of the story nor is it the beginning of the measure of effectiveness. Timing is everything. The circulating infection still has to run its course. The mop up of people already infected and those due to catch the disease *or high risk, from close family are included in the notion of locking down. It seems you may think otherwise?

    The actual number of infections prior to shut down was not known, anywhere. It was the holy grail number that would have been transformative in decision making terms. It was always an estimate. SOME countries had more land area to spread distance between hot spots!

    It is reasonable to surmise that those who acted early protected more lives. New York’s example instructed other states.
    2. The incoming flow of infected people was greater and more or less diffuse nationwide. That hardly ever gets a mention.

    Those who acted later, lost more people but some countries prevented overwhelming of the service, like the UK. Spain and Italy did not. Nor did China, but that’s another story.
    Knowing what is “late” and “early” are in real numbers is the name of the game. China KNEW about the level of asymptomatic spread. That’s how it looks to me.

Leave a Reply

Your email address will not be published. Required fields are marked *