What's new
By:
USCHO Fan Forum

This is a sample guest message. Register a free account today to become a member! Once signed in, you'll be able to participate on this site by adding your own topics and posts, as well as connect with other members through your own private inbox!

  • The USCHO Fan Forum has migrated to a new plaform, xenForo. Most of the function of the forum should work in familiar ways. Please note that you can switch between light and dark modes by clicking on the gear icon in the upper right of the main menu bar. We are hoping that this new platform will prove to be faster and more reliable. Please feel free to explore its features.

COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Status
Not open for further replies.
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Art.

<blockquote class="twitter-tweet"><p lang="und" dir="ltr"><a href="https://twitter.com/hashtag/OperationGridlock?src=hash&ref_src=twsrc%5Etfw">#OperationGridlock</a> <a href="https://t.co/AN5EQogIvX">pic.twitter.com/AN5EQogIvX</a></p>— Matt Schmucker (@mtschmucker) <a href="https://twitter.com/mtschmucker/status/1250495917461028865?ref_src=twsrc%5Etfw">April 15, 2020</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

French Rage said:
Is the guy spitting in the second one?
Click to expand...

Yeah. I wanted just that one, but for some reason it only embeds as a quote of the top one.

Hard to get a better summation of the rally than the guy hawking a big one with the We Love Nurses billboard in the background.
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Italy, Spain, and France all exceeded the confidence bounds of the IHME model in daily deaths today. For Italy and Spain it's the second day in a row doing so. Considering this model was redone 4 days ago it's doing extremely poorly with the back sides of the peaks (as was discussed a bit last night). New York is just entering this phase now - don't expect there to be as steep a reduction in deaths on a day to day basis there than the model thinks.
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Spartanforlife4 said:
Art.

<blockquote class="twitter-tweet"><p lang="und" dir="ltr"><a href="https://twitter.com/hashtag/OperationGridlock?src=hash&ref_src=twsrc%5Etfw">#OperationGridlock</a> <a href="https://t.co/AN5EQogIvX">pic.twitter.com/AN5EQogIvX</a></p>— Matt Schmucker (@mtschmucker) <a href="https://twitter.com/mtschmucker/status/1250495917461028865?ref_src=twsrc%5Etfw">April 15, 2020</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
Click to expand...

Please, please, please meet more. Face to face would be much more effective. And make sure there are so many that police can't break you up as you yell at the top of your lungs at Madam Governor. The louder and higher effort the better, as long as you are all together.

Prove to us all that we can get back to normal right now.

Just remember in a week, this is just a normal flu, and you don't need to go to the hospital.

edit- and with respect to our #1 rival in the neighboring city- please stay west of downtown. EL is off limits.
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

alfablue said:
Please, please, please meet more. Face to face would be much more effective. And make sure there are so many that police can't break you up as you yell at the top of your lungs at Madam Governor. The louder and higher effort the better, as long as you are all together.

Prove to us all that we can get back to normal right now.

Just remember in a week, this is just a normal flu, and you don't need to go to the hospital.

edit- and with respect to our #1 rival in the neighboring city- please stay west of downtown. EL is off limits.
Click to expand...

This... Just hand the keys over to Darwin, let him do what needs to be done and that we back him 100% to do the job :cool:
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

<blockquote class="twitter-tweet"><p lang="en" dir="ltr">New epidemiology estimates that 90% of US death could have been prevented by just acting 2 weeks earlier. The estimated number of deaths falls sharply with earlier interventions - th US delay cost thousands of lives. <a href="https://twitter.com/hashtag/COVID19?src=hash&ref_src=twsrc%5Etfw">#COVID19</a> <a href="https://t.co/FdSfUp6cck">https://t.co/FdSfUp6cck</a> <a href="https://t.co/rpIntyyCww">pic.twitter.com/rpIntyyCww</a></p>— Eric Feigl-Ding (@DrEricDing) <a href="https://twitter.com/DrEricDing/status/1250370089234444288?ref_src=twsrc%5Etfw">April 15, 2020</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>

That would be roughly 27,000 people.
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Deutsche Gopher Fan said:
From
That same account ...


<blockquote class="twitter-tweet"><p lang="en" dir="ltr">Jesus, they are frightened. <a href="https://t.co/BdNnhTpCoF">https://t.co/BdNnhTpCoF</a></p>— Schooley (@Rschooley) <a href="https://twitter.com/Rschooley/status/1250511412180316161?ref_src=twsrc%5Etfw">April 15, 2020</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
Click to expand...

The GOP cannot win unless they cheat; they are a vanishing demographic sliver -- they are going the way of the Federalists and the Whigs. They know this. And most GOP voters would choose to end democracy if the alternative was losing power. As my fundy boss (who is in general actually a good guy) said about the Russian interference, "I know, but I got my judges."
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

jflory81 said:
Italy, Spain, and France all exceeded the confidence bounds of the IHME model in daily deaths today. For Italy and Spain it's the second day in a row doing so. Considering this model was redone 4 days ago it's doing extremely poorly with the back sides of the peaks (as was discussed a bit last night). New York is just entering this phase now - don't expect there to be as steep a reduction in deaths on a day to day basis there than the model thinks.
Click to expand...

I find it interesting that the Federalist dipsh_ts are trashing them for terminally stupid reasons ("Their model vastly overestimated things!!! IT'S GARBAGE! OPEN THE ECONOMY!") and the academic community seems to be trashing them because it predicted a gaussian curve on the way down ("Their model vastly underestimates things!!! IT'S GARBAGE! KEEP IT CLOSED!"

We all know why it vastly overestimated things (because we reacted to that prediction) but why on earth wasn't this called out earlier? It's not like IHME is made up of idiots. It's a Gates-funded operation with ties to UW and partnerships with The Lancet, Harvard, and other academic institutions. How did they get what seems to be a pretty well-known concept in academia of long-tailed recoveries for biological models? What I also find interesting is that their earliest models show a long-tailed recovery but more recently they've been Gaussian: https://www.covid-projections.com/

Also interesting is their state level projections are almost always more gaussian but national projections tend to be long-tailed. There's a lot going on in their model and I'm just not sure we (public) know why it's falling short.

Edit: Apologies if this was already posted, but I think this is a good thread on the IHME model:
<blockquote class="twitter-tweet"><p lang="en" dir="ltr">1. A short thread about symmetric death curves curves and the @IMHE_UW model. <br><br>Throughout, I'll use a great new tool from <a href="https://twitter.com/yuorme?ref_src=twsrc%5Etfw">@yuorme</a>: <a href="https://t.co/FUHfJCr9qq">https://t.co/FUHfJCr9qq</a><br><br>This allows us to look at how the predictions of the IHME model have changed since it was released in late March.</p>— Carl T. Bergstrom (@CT_Bergstrom) <a href="https://twitter.com/CT_Bergstrom/status/1250304069119275009?ref_src=twsrc%5Etfw">April 15, 2020</a></blockquote> <script async src="https://platform.twitter.com/widgets.js" charset="utf-8"></script>
 
Last edited:
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Side note, I find it interesting when people use the term Gaussian. I recently finished a few advanced statistics courses for grad school and the term is never used in books or lectures- just “normal distribution”
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

dxmnkd316 said:
I find it interesting that the Federalist dipsh_ts are trashing them for terminally stupid reasons ("Their model vastly overestimated things!!! IT'S GARBAGE! OPEN THE ECONOMY!") and the academic community seems to be trashing them because it predicted a gaussian curve on the way down ("Their model vastly underestimates things!!! IT'S GARBAGE! KEEP IT CLOSED!"

We all know why it vastly overestimated things (because we reacted to that prediction) but why on earth wasn't this called out earlier? It's not like IHME is made up of idiots. It's a Gates-funded operation with ties to UW and partnerships with The Lancet, Harvard, and other academic institutions. How did they get what seems to be a pretty well-known concept in academia of long-tailed recoveries for biological models? What I also find interesting is that their earliest models show a long-tailed recovery but more recently they've been Gaussian: https://www.covid-projections.com/

Also interesting is their state level projections are almost always more gaussian but national projections tend to be long-tailed. There's a lot going on in their model and I'm just not sure we (public) know why it's falling short.
Click to expand...

In terms of the national side of things, I think it's mostly because different states have different peaks, and their national prediction is just an amalgamation of their states' models. This is true for a least a couple of the European countries' models as well - replacing states for regions, obviously.

As to why they continue to stick with a mostly Gaussian projection I really do have to wonder if they were leaned on to make things look a little rosier a month or two from now by the administration - perhaps in return for being the Federal model. It's important to note that one of their assumptions is "full social distancing" and even in NY I wouldn't call what we're doing "full" with all the exceptions for "essential businesses" like fast food and such (and this isn't even taking into account idiots like those participating in that Michigan protest). I could see a Gaussian model making sense if you completely removed all possible areas of re-infection and transmittance, but obviously that's not possible in the real world. It could be a technically accurate model, it's just that we don't have the ability to fulfill their assumptions that make the model look a little rosier than most people expect.
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Deutsche Gopher Fan said:
Side note, I find it interesting when people use the term Gaussian. I recently finished a few advanced statistics courses for grad school and the term is never used in books or lectures- just “normal distribution”
Click to expand...

That's because they are not synonyms. A Gaussian distribution is raw. A Normal distribution is a Gaussian distribution normalized with the integrated area under the curve equal to 1.0. Hence, "Normal." :)

In the case of the deaths, the curve is Gaussian but not Normal, because it is a frequency distribution, not a probability function. The people saying "Gaussian" are correct.

We have now exhausted everything I remember from my 32-years past MA in Quantitative Methodology other than how to spell heteroskadactic.* **

* Possibly. I gave it a shot.

** Sh-t. It's an "e."
 
Last edited:
Kepler said:
That's because they are not synonyms. A Gaussian distribution is raw. A Normal distribution is a Gaussian distribution normalized with the integrated area under the curve equal to 1.0. hence, "Normal." :)

We have now exhausted everything I remember from my MA in Quantitative Methodology other than how to spell heteroskadactic.*

* Possibly. I gave it a shot.
Click to expand...

My textbook is in the other room, I don’t have motivation at moment to grab it. Maybe later!
 
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Kepler said:
The people saying "Gaussian" are correct.
Click to expand...

Jeebus. I lucked into that.

In case you thought I was actually smart.

Edit: To my credit, as soon as you made your post, I remembered the difference. I just haven't been using Gaussian over normal intentionally. I've just always called them Gaussian. Maybe I picked that up in stats courses back in high school and college.


Edit 2: More interesting resources and tools:
https://aatishb.com/covidtrends/
http://kestrel.nmt.edu/~rsonnenf/corona/corona_control.html
 
Last edited:
Re: COVID-19 The 7th Part: We're Gonna Be Number One Soon!

Deutsche Gopher Fan said:
My textbook is in the other room, I don’t have motivation at moment to grab it. Maybe later!
Click to expand...

Take it up with Stanford (French Rage will do in a pinch). It's not my fight anymore; I just bomb sh-t now. Once the rockets go up who cares where they come down?
 
Status
Not open for further replies.
Back
Top