- 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
re: Nate silver: the slowdown in CV19 cases in NOLA is unlike anything we have seen elsewhere
Posted on 4/13/20 at 4:26 pm to moneyg
Posted on 4/13/20 at 4:26 pm to moneyg
quote:
The figures with social restrictions do not shed any insight into the quality of the decision to shut down the economy on their own.
I disagree. If your median model with social restrictions still predicts deaths above any flu season we have seen since 1918 in a third of the time, it sheds a ton of insight into its severity.
They were never not going to implement some level of social restrictions. I do not believe that option was ever on the table. So that takes a lot of focus off the IC model.
quote:
Just to clarify, since there is an argument going on in this thread parsing words, that is a range of the "worst case scenario" with no social restrictions? What is the range for "best case scenario" for no social restrictions?
I'm not 100% on this except for these points: 2.2 million deaths was the worst run of the "worst case" scenario.
I don't know what the IC best case scenario was and, for whatever reason, I can't find it online.
quote:
Or, are you saying 1.6 is best case, 2.2 is worst case?
I'm 99% confident that 1.6 million was not best case.
quote:
And, what did the IC project predict with Social restrictions? Can you fill me in on the best and worst case scenario?
I don't believe IC ran a U.S. model with social restrictions, but I could be wrong.
1
Posted on 4/13/20 at 4:27 pm to Korkstand
quote:
You seem to think that whenever an underdog wins, his chances were "underestimated". This betrays your lack of understanding of probabilities.
And, you seem to think that probabilities (based on semi-subjective data) have to be valid as long as they don't end in 100% probability.
His "probabilities" weren't based on perfect data with known margins of error. This isn't like estimating the probability of getting heads 3 out of 5 times. The source data was based on assumptions that had multiple flaws.
He underestimated Trump's chances.
Posted on 4/13/20 at 4:28 pm to Antonio Moss
quote:
The main model - the IMHE - has been pretty solid since March 30th with a few exceptions.
Accurate data = a more reliable model.
How close are the model's current "worst case scenario" when compared to the "worst case scenario" (seemingly broadcast 24/7 by the MSM) at the onset?
Posted on 4/13/20 at 4:29 pm to CptRusty
quote:
Keep watching, she clearly agrees with 100-200k as a "best case" scenario like 20 seconds after the part you quoted.
I watched the whole thing twice.
She never says that.
Posted on 4/13/20 at 4:32 pm to jimmy the leg
quote:
How close are the model's current "worst case scenario" when compared to the "worst case scenario" (seemingly broadcast 24/7 by the MSM) at the onset?
March 30th high end death estimation - 141,995
April 10th high end death estimation - 155,313
Posted on 4/13/20 at 4:33 pm to Antonio Moss
quote:
Remind me the last time we locked down an entire major American city because of influenza.
Probably didn't need to happen this time.
Some sectors/demographics yes. But nationwide what we have done is overkill.
Posted on 4/13/20 at 4:34 pm to RogerTheShrubber
quote:
But nationwide what we have done is overkill.
To be fair, we don't have a nationwide mandate.
But I do agree with your overall point.
Posted on 4/13/20 at 4:36 pm to Antonio Moss
quote:
I disagree. If your median model with social restrictions still predicts deaths above any flu season we have seen since 1918 in a third of the time, it sheds a ton of insight into its severity.
Is that because you think you can reasonably infer what deaths would be without social restrictions? If so, what is that number?
It's retarded to think that the number of total deaths without restrictions isn't important.
quote:
They were never not going to implement some level of social restrictions
Ok. Well, that's good enough for me. We don't have to know what the upside and downside of a decision. I'll just take your word that social restrictions were never not going to happen therefore what we ended up doing is justified.
quote:
I'm not 100% on this except for these points: 2.2 million deaths was the worst run of the "worst case" scenario.
I don't know what the IC best case scenario was and, for whatever reason, I can't find it online.
curious.
A lot of people are wondering if we've made a HUGE error in our judgement. Honestly, I believe they are being reasonable in their questions. I haven't seen you able to show otherwise.
Posted on 4/13/20 at 4:39 pm to jimmy the leg
It is baffling how many people have managed to politicize this pandemic.
Posted on 4/13/20 at 4:41 pm to Antonio Moss
She was asked, directly, if that was the best case scenario, and she didnt say no. She meandered off into a rant about people not being perfect and data from other countries.
This is exactly what I'm talking about, at the very least these people have been reckless with their language, and for the reasons I have outlined earlier, this is completely unacceptable.
This is exactly what I'm talking about, at the very least these people have been reckless with their language, and for the reasons I have outlined earlier, this is completely unacceptable.
Posted on 4/13/20 at 4:43 pm to moneyg
quote:Total misrepresentation of what was said.
And, you seem to think that probabilities (based on semi-subjective data) have to be valid as long as they don't end in 100% probability.
quote:Why the quotes on "probabilities"?
His "probabilities" weren't based on perfect data with known margins of error.
quote:Actually it's almost exactly like that.
This isn't like estimating the probability of getting heads 3 out of 5 times.
quote:And yet the source data is what was available, and sources of error were accounted for as best as they could. Are you suggesting that probabilities should instead be based on feelings?
The source data was based on assumptions that had multiple flaws.
quote:
He underestimated Trump's chances.
Easy to say after the fact.
Tell me this... if we had 100 elections in which one candidate beat the other by over 2% in the popular vote, in how many of those do you think the other candidate would win the EC?
Posted on 4/13/20 at 4:44 pm to Korkstand
quote:
Giving 3:1 odds on a coin flip would be grossly inaccurate and would fly in the face of available data. Giving such odds would not make you "wrong", it would make you incompetent. 538's election odds aligned with available data.
I've said multiple times that the data was wrong. I don't think Silver's model itself was wrong at all.
quote:
So now let's reverse your logic. I give you 1:1 odds on each of 4 coin flips. You flip 3 heads and 1 tail. Was I "wrong"? Would I have been "right" had I given heads 3:1 odds?
No, you weren't wrong. In fact, your model was exactly right. If you had given heads 3:1, your model would have been very wrong...even though the results matched.
And, that's my point. You've assumed that I'm saying Silver was wrong because Trump won. I've said otherwise multiple times. He was wrong because his data was flawed. And, it resulted in him underestimating Trump's chances.
Now, answer the other question you've been dodging. According to Silver's estimates, what were Trump's chances of winning all 3 states (WI, MI, and PA).
Posted on 4/13/20 at 4:44 pm to moneyg
quote:
Is that because you think you can reasonably infer what deaths would be without social restrictions? If so, what is that number?
You can reasonably infer that it would higher. Plus, at the time you had the ongoing saga in Italy to refer to.
quote:
It's retarded to think that the number of total deaths without restrictions isn't important.
Less important
quote:
Ok. Well, that's good enough for me. We don't have to know what the upside and downside of a decision. I'll just take your word that social restrictions were never not going to happen therefore what we ended up doing is justified.
Do you honestly believe that the U.S. was going to be the only country in the world to no implement any level of social restrictions?
quote:
A lot of people are wondering if we've made a HUGE error in our judgement. Honestly, I believe they are being reasonable in their questions. I haven't seen you able to show otherwise.
Depends on who "We" is.
There is no federal mandate; only recommendations.
State governors have taken the lead on this - as they should - and there have been different levels of restrictions. I believe some states have gone overboard.
Isolating hot zones and focusing on metro areas going forward should be the path along with rapid testing and tracking.
That said, I will give governors a little slack because we haven't had the ability to rapidly test until this week and the misinformation from the WHO really damaged our preparation timetable.
Posted on 4/13/20 at 4:46 pm to Antonio Moss
quote:
But I do agree with your overall point.
The problem is policy makers reacting to public pressure which comes from a clickbait press model.
Most death estimates have dropped dramatically but still the public belief is this is going to overflow American health resources and kill hundreds of thousands.
I trust the math, but think initial projections were based out of China and Italy which are overcrowded and have less medical resources.
Posted on 4/13/20 at 4:46 pm to CptRusty
quote:
She was asked, directly, if that was the best case scenario, and she didnt say no. She meandered off into a rant about people not being perfect and data from other countries.
She said the best case scenario was for people to do what they were being asked to do and socially isolate.
quote:
This is exactly what I'm talking about, at the very least these people have been reckless with their language, and for the reasons I have outlined earlier, this is completely unacceptable
She said just before that, in response to a question about worst case scenario, that "that number" is 100K-200K.
You guys are looking for people to blame.
Posted on 4/13/20 at 4:47 pm to Antonio Moss
quote:
March 30th high end death estimation - 141,995
April 10th high end death estimation - 155,313
They just revised. Median is at 69k. Low end 30k high end 175k
Posted on 4/13/20 at 4:51 pm to Antonio Moss
quote:
She said the best case scenario was for people to do what they were being asked to do and socially isolate.
So she was asked a very clear and direct question with numbers to either refute or agree with, and her response was to trail off on a non-answer.
quote:
You guys are looking for people to blame.
I think I've made that pretty clear. Posted on 4/13/20 at 4:54 pm to Korkstand
quote:
About 0.8% to win all 3. And if you think such a probability was "wrong", then you will only be further showing that you do not understand probabilities.
It is you who has a fundamental misunderstanding of probabilities.
You think naming something a probability means the probability value it is scientifically valid. It's not.
If you don't think the polling was off in the 3 main states we've been discussing, I don't know what to tell you.
If you moved those states to 50/50 contests, Silver's overall prediction would have been much, much different.
Posted on 4/13/20 at 5:10 pm to Korkstand
quote:
Total misrepresentation of what was said.
And you didn't misrepresent what I said?
quote:
Why the quotes on "probabilities"?
Because this isn't a known series of factors with known probabilities within.
quote:
Actually it's almost exactly like that.
It's not. And, anyone who understands sampling and the requirements to come up with a valid probability off of said sampling knows this is true. If the sampling wasn't representative of the actual population, you get skewed results. That's exactly what happened. It isn't reasonable to poll outside of churches and expect to end up with valid results. And, it isn't reasonable to poll too many democrats either.
And, any model that is based on either data is going to end up overstating one candidates probability of winning if the underlying data is flawed.
I have no idea why you can't figure that out.
quote:
And yet the source data is what was available, and sources of error were accounted for as best as they could. Are you suggesting that probabilities should instead be based on feelings?
This is the guy who just said I was misrepresenting is comments.
See my comments above. Objectively, if you look a the polling data in those 3 states...not only in the last poll, but all along the way, the polling data was HEAVILY skewed towards Hillary the entire way.
quote:
Easy to say after the fact.
Yes. It's much easier to say after the fact...with objective data. That doesn't make it wrong. In fact, it makes it more right.
quote:
Tell me this... if we had 100 elections in which one candidate beat the other by over 2% in the popular vote, in how many of those do you think the other candidate would win the EC?
This is a PERFECT example of you limited logic skills.
If that's ALL we had to go on (national polling), and that's the only data that was available, you'd get odds that weren't close to even odds in favor of the candidate winning the national polling. That doesn't make the model valid because...
If the actual data showed that the difference in votes was based in two states, and ALL OTHER STATES were polling the other way, the model you reference would be very wrong. And, a more accurate model (based on electoral college) would put high odds in the opposite direction.
This should be obvious.
Posted on 4/13/20 at 5:18 pm to moneyg
quote:Oh, right, you've just said that Silver himself was wrong.
I've said multiple times that the data was wrong. I don't think Silver's model itself was wrong at all.
quote:Because that's exactly what you're doing.
You've assumed that I'm saying Silver was wrong because Trump won.
quote:Poll data is known to have flaws. Do you think the 538 model does not account for this?
I've said otherwise multiple times. He was wrong because his data was flawed.
quote:Again, just because an underdog wins doesn't mean the odds were underestimated.
And, it resulted in him underestimating Trump's chances.
Page 13 of 15
Popular
Back to top
Follow TigerDroppings for LSU Football News