Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Fine, I'll run a regression analysis but it won't make you happy

natesilver.net

Post reply on HN
Print view View original

151–160 of 341 posts

Re: Fine, I'll run a regression analysis but it won't make you happy

#151

Post by orangecat »

dehrmann wrote: post #83
jsnell wrote: post #27

Earlier quoted context omitted.

Eliminating Covid stopped being an option roughly around January 2020. The partial elimination you seem to be implying with "as much as possible" was never an option. It was always all or nothing.

and China tried really, really hard to eliminate it over the next 3 years. They couldn't.

Right, and they had the "advantages" of having no limitations on government power, and assigning no value to individual freedom. If they couldn't do it, it's lunacy to believe that anyone else could.

Re: Fine, I'll run a regression analysis but it won't make you happy

#152

Post by the_third_wave »

KerrAvon wrote: post #2

This is all fine, but the focus on deaths is sort of missing the larger societal problem. The COVID devastation is also about long COVID, and even people who had COVID but either recovered “fully” or never displayed symptoms. None of this is over, and we are so, so fucked. edit: Which is to say: The Great Barrington Declaration was wrong directionally as well. We really needed to optimize to eliminate COVID as much a…

> None of this is over, and we are so, so fucked.

Humans used to be "so, so fucked" when...

- the volcano on the island erupted,

- the harvest failed for the third year in a row

- the neighbouring tribe learned to ride horses and started a campaign for domination

- some strange curse fell upon the land killing ⅓ of the population which left the fields unworked and the land barren

We're still the same species with the same instincts for survival, the same alarm mechanisms for detecting impending catastrophic situations and the same urge to act upon impending disasters. Modern society has - especially since the introduction of antibiotics - largely done away with those traditional doom scenarios. We're no longer starving, no longer dying in droves from infectious diseases, no longer totally at the mercy of nature... but our alarm mechanisms are still in place although they are differently tuned in different people. In some people - you seem to be one of those - these mechanisms are so finely tuned that they pick up minute signals which are amplified until they trigger the 'impending catastrophic situation' alarm (we're so, so fucked) where those same signals do not even register for others. The same is true for other triggers like 'climate change', 'migration', 'systemic ...-ism' and others where some people are completely taken over by their alarms going off where others don't even hear a single bell. Many of these triggers - 'systemic ...-ism' and to a lesser extent 'migration' being prime examples - are intentionally amplified because those who do the amplification stand to gain power (and money) by doing so, others - 'climate change' - are being used by third parties for monetary gain ('greenwashing' and the multitude of 'green' scams like 'carbon offsets'/'carbon credits') or political power.

Are we 'fucked'? That depends on who you ask. Ask me and I'll say "only if we want to be". Is SARS-2 going to be with us for the foreseeable future? Yes, most likely. Is that a big problem? No, not really since it has rapidly mutated to become 'yet another Corona-related upper airway infection' while our species has developed a form of natural immunity which has taken the edge off the disease. Upper airway diseases are annoying and lead to a loss in productivity, sure, but they tend not to mail or kill. What remains is the long tail of the initial pandemic and even more of the (over)reaction to it, especially in those countries which had strict lockdown regimes. Recovering from the damage caused by those measures will take a lot of time and money and it can only be hoped that a lesson will be learned from this experience.

As to returning to 'normality' I can safely state that we have done so quite a while ago here in Sweden [1].

[1] https://www.thelocal.se/20230310/fact-check-did-sweden-have-...

Re: Fine, I'll run a regression analysis but it won't make you happy

#153

Post by flashback2199 »

biorach wrote: post #148
Izkata wrote: post #104

Earlier quoted context omitted.

For the downvoters, we even have a name for this: Anscombe's quartet. https://en.wikipedia.org/wiki/Anscombe%27s_quartet Always visualize your data.

The downvotes were due to the complete lack of context in the vaguely derogatory post.

Plots are such a basic expectation for stats that I don't see why I should be required to write more about it..

Re: Fine, I'll run a regression analysis but it won't make you happy

#154

Post by vcdimension »

Waterluvian wrote: post #131

It was a hard thing to broach at the time without people frothing at the mouth about how I must be anti vaccine or something: Has there been any attempt to calculate the cost-benefit of all the various measures and how extreme we should go with them? I’m guessing it’s hard to quantify and compare. A lot of things like general depression, isolation, kids missing half a year of school, etc. can’t really be evaluated ag…

Most people don't even know how to mentally frame the problem. It's the number of life years lost that matters, not the number of lives, e.g. the death of a child with their whole life before them is worse than the death of an elderly person who's already on deaths door. Current statitics focus solely on number of deaths rather than expected years of life lost so we can't even make a fair assessment of the trade-offs involved in different policies.

Re: Fine, I'll run a regression analysis but it won't make you happy

#155

Post by noirbot »

munch117 wrote: post #46
noirbot wrote: post #3

Earlier quoted context omitted.

I haven't read the specifics of the GBD, but isn't some of the "it was clearly quackery" confounded by: 1. In 2020 especially, and even now, the specifics of long covid and other side effects, as compared to other downsides of lockdowns on mental health/delayed treatments are hard to predict? We don't have the counterfactual of what would have been the 3-5-10 year implications of a multi-year lockdown. 2. Does the ge…

The west did not go for a strategy of elimination through lockdown. Rather, the strategy was to delay the spread, initially only so that the health care system could keep up, and later in the hope that vaccines would arrive in time to curb the brunt of it - as they did. The GBD is easy to find and a short read ( https://gbdeclaration.org/ ), it does not refer to any elimination strategy - instead it discusses the cos…

Yea, for sure. Mostly responding to the OP more than stating what happened. I think we generally agree - for better or worse, most of the world decided on some limited strategy, which made the prospect of doing any sort of elimination essentially impossible. In that light, balancing whatever success at delaying infections vs. the downsides of being even partially locked down is a non-quack question in my mind.

Re: Fine, I'll run a regression analysis but it won't make you happy

#156

Post by noirbot »

b112 wrote: post #87
newZWhoDis wrote: post #77

Earlier quoted context omitted.

Where I come from, “good ideas doomed to fail” are called “bad ideas”

I recall clearly, at the time, the first two weeks of lockdown. No one, anywhere, had a clue wtf was going on, except that some new virus was spreading like wildfire, that it spread before symptoms appeared, and it seemed like Italy had a crazy high death rate. Blaming people with the knowledge of hindsight is just plain wrong. Later lockdowns? Now that's a different conversation.

Yea, by october when the "maybe we shouldn't do a lockdown any more" talk was 6+ months in, it feels like it's clearly in the "there's a case to be made" zone.

Re: Fine, I'll run a regression analysis but it won't make you happy

#157

Post by mikem170 »

autoexec wrote: post #108
mikem170 wrote: post #44

Earlier quoted context omitted.

Agreed. There's a lot of animals that can catch and spread covid [0]: > many if not most mammalian ACE-2 receptors are susceptible > the virus has gone from humans to the animals and back again to human > found signs of antibodies against SARS-CoV-2 in significant percentages of six urban wildlife species > found signs of the pathogen infecting 17 percent of New York City sewer rats tested > Exposure could also occur…

I'm not too worried about a random sick deer in the middle of some forest infecting a whole bunch of humans. The worry with animals is that they could mutate the virus into something much more nasty. Especially in factory farm settings where animals aren't properly cared for and are packed in like sardines while covered in shit and open sores, and where workers who are also treated terribly could end up getting expos…

I brought up covid in animals because the original poster mentioned the elimination of covid in the context of lockdowns.

The fact that covid can move between animal and human populations would seem to mean that lockdowns for the purpose of elimination will not work. Eventually humans would be reinfected from animals - mice, rats, pets, etc.

This has perhaps already happened. There is dna evidence that omicron evolved in mice and then jumped back into humans [0].

On the idea of lockdowns to eliminate the virus:

> The coronavirus’ ability to infect so many different animals, and to spread within some of those populations, is worrying news: It means there’s virtually no chance the world will ever be rid of this particularly destructive coronavirus, scientists said [1].

It would be a bummer to be locked down for months or years in an effort to eliminate the virus, and have to deal with the negative repercussions of lockdowns during and afterwards, only for everyone to become reinfected again from animals, and the whole thing start up again.

My apologies if I misunderstood your reply. You did seem to have a different angle than the original post. I just don't get it when people mention lockdowns to eliminate covid, when such a thing isn't possible.

I'm not sure what to say about your concern that animals can evolve a more dangerous virus. That seems like it can go either way. Animal evolved variants can also be less dangerous, like omicron, which is a good thing. Also locked down humans could be more vulnerable to more dangerous variants, their immune systems not having any prior exposure. How can anyone be so sure lockdowns always help?

[0] https://www.medicalnewstoday.com/articles/covid-19-did-omicr...

[1] https://www.latimes.com/science/story/2023-06-09/coronavirus...

Re: Fine, I'll run a regression analysis but it won't make you happy

#158

Post by blueskies89 »

walnutclosefarm wrote: post #84
KerrAvon wrote: post #2

This is all fine, but the focus on deaths is sort of missing the larger societal problem. The COVID devastation is also about long COVID, and even people who had COVID but either recovered “fully” or never displayed symptoms. None of this is over, and we are so, so fucked. edit: Which is to say: The Great Barrington Declaration was wrong directionally as well. We really needed to optimize to eliminate COVID as much a…

> The COVID devastation is also about long COVID, and even people who had COVID but either recovered “fully” or never displayed symptoms. None of this is over, and we are so, so fucked. SARS-CoV-2 is certainly with us to stay, so in that sense it's not over. But beyond that, I don't see how "we are so, so fucked" as you say. Covid is no doubt taking a small nibble out of life expectency, and yes there is some long Co…

This isn't how the math works.

The reason why life expectancy is going down is because middle age people are dying. People dying in their 80s has almost no impact on life expectancy calculations

Re: Fine, I'll run a regression analysis but it won't make you happy

#159

Post by lamontcg »

fwungy wrote: post #25

I really don't trust any of the numbers on covid. A vaccine for a dangerous illness that can affect billions of people is a very big payday. There's lots of money to spread around to politicians, corrupt scientists, and corrupt media. I'd like to see a real scientific debate with adversarial inquiry so we could know if numbers are being fudged and which ones they are. I trust science, but not greed driven capitalists…

There was a lot more money involved in attempting to force everyone back to work during the pandemic and let them take their chances before a vaccine was produced.
Post reply on HN