- My Forums
- Tiger Rant
- LSU Recruiting
- SEC Rant
- Saints Talk
- Pelicans Talk
- More Sports Board
- Fantasy Sports
- Golf Board
- Soccer Board
- O-T Lounge
- Tech Board
- Home/Garden Board
- Outdoor Board
- Health/Fitness Board
- Movie/TV Board
- Book Board
- Music Board
- Political Talk
- Money Talk
- Fark Board
- Gaming Board
- Travel Board
- Food/Drink Board
- Ticket Exchange
- TD Help Board
Customize My Forums- View All Forums
- Show Left Links
- Topic Sort Options
- Trending Topics
- Recent Topics
- Active Topics
Started By
Message
The U. of Washington's model was updated overnight
Posted on 4/6/20 at 7:55 am
Posted on 4/6/20 at 7:55 am
It was better than the Imperial College's half the world is going to die model, but it was still high. More data = better model.
Down from 240k deaths to now projecting 80k.
Mississippi was projected to have 1400 deaths, it has been revised to 237.
LINK
For you non-data geeks, keep in mind that THIS IS THE MODEL THAT WAS PRESENTED L:AST WEEK THAT 240,000 WOULD DIE. Another week of data and the protection dropped by two thirds.
Down from 240k deaths to now projecting 80k.
Mississippi was projected to have 1400 deaths, it has been revised to 237.
LINK
For you non-data geeks, keep in mind that THIS IS THE MODEL THAT WAS PRESENTED L:AST WEEK THAT 240,000 WOULD DIE. Another week of data and the protection dropped by two thirds.
This post was edited on 4/6/20 at 8:14 am
Posted on 4/6/20 at 7:57 am to anc
quote:
80k
Doubt we get there, either.
Posted on 4/6/20 at 7:57 am to anc
And after an Alabama Armageddon, they’re projected at 927 by August
Posted on 4/6/20 at 7:59 am to Jrv2damac
Missouri went from 800 ventilators needed in their March model to 240 needed in their first update to 95 needed in their last update.
Good work, fellas.
Good work, fellas.
Posted on 4/6/20 at 8:00 am to Jrv2damac
They brought Alabama’s number down after factoring in our new stay at home order. Nevermind that our previous order was just a strict as states that had shelter-in-place orders. The new order changes nothing and suddenly our numbers are drastically reduced?
Not to go all denier here but that’s a screwed up way to run a model.
Not to go all denier here but that’s a screwed up way to run a model.
This post was edited on 4/6/20 at 8:02 am
Posted on 4/6/20 at 8:01 am to anc
I’m waiting on Vegas oddsmakers.
Posted on 4/6/20 at 8:01 am to anc
quote:
Down from 240k deaths to now projecting 80k.
will be lower than that.
SUBSTANTIALLY lower of you take out NYC and NO
Posted on 4/6/20 at 8:01 am to anc
quote:
Down from 240k deaths to now projecting 80k.
still way too high
Posted on 4/6/20 at 8:01 am to anc
That model is going to make a lot of sky screamers unhappy
Posted on 4/6/20 at 8:02 am to FairhopeTider
quote:
Not to go all denier here but that’s a screwed up way to run a model.
Same for Missouri. KC and STL metro areas were stay at home. The model didn’t account for it.
Posted on 4/6/20 at 8:02 am to moneyg
Stock futures up 800 points on this.
Posted on 4/6/20 at 8:03 am to anc
Probably way too high still, my guess is flu+ (give or take).
Nice job guys destroying the world on bullshite.
Nice job guys destroying the world on bullshite.
Posted on 4/6/20 at 8:04 am to anc
I am reviewing it right now. I am a data scientist with 50 years pragmatic experience in building and using such models.
My first impression is that while better, the stat's the revision show they are still using averages which give too much reliance on the earliest hospitalized.......THEY ARE ATILL OVER STATING the peak and when it occurs.......
I believe we will see the peak this week, not the 15th ....and at a significantly lower level than being forecast by these models (which have so wide a variance between lower and upper estimates as to be only guides)
This week will be good news in tewrms of peaking!
My first impression is that while better, the stat's the revision show they are still using averages which give too much reliance on the earliest hospitalized.......THEY ARE ATILL OVER STATING the peak and when it occurs.......
I believe we will see the peak this week, not the 15th ....and at a significantly lower level than being forecast by these models (which have so wide a variance between lower and upper estimates as to be only guides)
This week will be good news in tewrms of peaking!
Posted on 4/6/20 at 8:05 am to the808bass
quote:
Missouri went from 800 ventilators needed in their March model to 240 needed in their first update to 95 needed in their last update.
Good work, fellas.
Perhaps the models were simply wrong and that many were really never needed. I know, you believe "social distancing was the "reason" for the decline in the projection. I must say, social distancing is logical.
My take...perhaps the models were wrong AND social distancing helped.
Posted on 4/6/20 at 8:05 am to anc
quote:
Mississippi was projected to have 1400 deaths, it has been revised to 237.
The update before that had Mississippi at 2,200, then 1,400, now 237. Why the change?
This post was edited on 4/6/20 at 8:06 am
Posted on 4/6/20 at 8:06 am to jimmy the leg
quote:
My take...perhaps the models were wrong AND social distancing helped.
I’m on your side. The good work fellas was sarcastically for the model makers.
Popular
Back to top
Follow TigerDroppings for LSU Football News