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

141–150 of 341 posts

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

#141

Post by brody_hamer »

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…

In Canada (and likely elsewhere), there were a number of restrictions which were tied to hospital capacity. As the number of available ICU beds dropped: more restrictions were put in place, and vice versa.

A lot of emphasis was placed on preventable deaths. That is; situations where we’re turning away a patient that we could’ve saved, because we don’t have a bed available for them.

I thought this was a solid, intuitive approach. Preventable deaths are really, really unfortunate.

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

#142

Post by autoexec »

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…

You're the unfortunate but inevitable result of our total failure to keep critical institutions honest and trustworthy. When scientists can accept money to produce fake results, or to bury any results unfavorable to corporations without consequences, and doctors can lie or take kickbacks from pharmaceutical companies without severe consequences for both the pharmaceutical company or the doctors, and politicians and news organizations can tell outright lies with impunity, this is what we get. People like you who can't see the truth even when it's staring them in the face.

Your stance that covid numbers are all lies and vaccines are a conspiracy is wrong, but it's not entirely your fault. Politicians, scientists, doctors, and media have a responsibility to continuously prove that they can and should be trusted, but they haven't been willing to do that and until they do we'll see more and more people like you who feel like they just can't trust anything anymore. At a certain point it's just self-defense to be distrustful.

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

#144

Post by Waterluvian »

brody_hamer wrote: post #141
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…

In Canada (and likely elsewhere), there were a number of restrictions which were tied to hospital capacity. As the number of available ICU beds dropped: more restrictions were put in place, and vice versa. A lot of emphasis was placed on preventable deaths. That is; situations where we’re turning away a patient that we could’ve saved , because we don’t have a bed available for them. I thought this was a solid, intuit…

Yeah that approach really resonated with me as well. A very straightforward concept: how much capacity do we have for higher risk behaviour? And in this case the cut-off for higher risk may be “yeah we’re not going to hockey games for a while.”

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

#145

Post by VancouverMan »

rcbdev wrote: post #126

I don't know about other countries but in Austria nurses were highly incentivized to report deaths immediately following a vaccination or weeks after an infection has passed as a covid death in the sense of national statistics. I would not be surprised if this "nudging" of on the ground reports over the course of the pandemic has rendered the data around covid deaths unreliable.

The death counts from Canada from that era are very questionable.

As early as June of 2020, the "public health" authority in Canada's most-populous city (4th highest population in North America) revealed that the counting of deaths was being done using a methodology that sounds quite dubious:

"Individuals who have died with COVID-19, but not as a result of COVID-19 are included in the case counts for COVID-19 deaths in Toronto."

https://twitter.com/TOPublicHealth/status/127588839006028596...

By mid-2021, there were news reports like the following ("LTC" stands for "long-term care"):

"Patients died from neglect, not COVID-19, in Ontario LTC homes, military report finds: ‘All they needed was water and a wipe down’"

https://www.theglobeandmail.com/canada/article-canadian-mili...

After stuff like that and everything else that went on from 2020 through 2022, I can't trust "public health" officials at all at this point.

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

#146

Post by chpatrick »

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…

I think that's kind of with the benefit of hindsight though. In 2020 we really didn't know if this stuff would kill everyone or just be a nuisance/deadly if you're vulnerable.

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

#147

Post by jfengel »

brianpan wrote: post #71
SilverBirch wrote: post #8

I think the funny thing is that Nate can be a flippant twit on Twitter but has totally fallen for it in critiques of him. Essentially this article is “a bunch of people baselessly speculated about an assertion I made, so I’m going to spend lots of time proving something they don’t care about”

"Bunch of people" doesn't seem like a good characterization considering he's at least partially responding to Martin Kulldorff, a professor of medicine and biostatistician at Harvard and a co-author of the GBD.

A biostatistician who told this professional stats guy to go consult a statistician after taking a guess at a confounding variable. He could have run those numbers himself, but apparently didn't bother, because Silver took him up on it and Kulldorff was completely wrong.

It would be less egregious if it has been a bunch of random people. It was someone who really should have known better. Instead, it provides more evidence that Kulldorff is seeking to confirm an ideological position and tossing his medical and biostatistical accomplishments aside to do it.

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

#148

Post by biorach »

Izkata wrote: post #104
flashback2199 wrote: post #64

A regression analysis without one single graph rolls eyes

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.

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

#149

Post by vcdimension »

logicchains wrote: post #137
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…

Yes, there are papers attempting that, such as this recent one, which looked at whether shelter in place policies reduced overall excess mortality: https://onlinelibrary.wiley.com/doi/full/10.1002/hec.4737 . "Using an event study approach and data from 43 countries and all U.S. states, we measure changes in excess deaths following the implementation of COVID-19 shelter-in-place (SIP) policies. We do not find that cou…

There's also this one: https://sites.krieger.jhu.edu/iae/files/2022/01/A-Literature... which is summarised here: https://www.facebook.com/econometricsguru/posts/pfbid0wtvVjJ...

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

#150

Post by stefan_ »

rcbdev wrote: post #126

I don't know about other countries but in Austria nurses were highly incentivized to report deaths immediately following a vaccination or weeks after an infection has passed as a covid death in the sense of national statistics. I would not be surprised if this "nudging" of on the ground reports over the course of the pandemic has rendered the data around covid deaths unreliable.

So take excess mortality. Surprise, nothing changes. Did you read the article, the part where it mentions all the little things people try and bring up on the path to confirmation bias?
Post reply on HN