Posted on 04/10/2020 7:51:59 AM PDT by Kaslin
There's been a lot of discussion by armchair analysts about various models being used to predict outcomes of COVID-19. The armchair analysts I've seen include a philosophy major and a Ph.D. candidate with little experience in statistics, much less in modeling complex systems. In fact, the discussion coming from academia and its sycophants in the media further demonstrates just how deep the "Deep State" runs. For those of us who have built statistical models, all of this discussion brings to mind George Box's dictum: "all models are wrong, but some are useful"...or useless, as the case may be.
The problem with data-driven models, especially when data are lacking, can be easily explained. I'll start with a brief background on statistical analysis (AKA hypothesis testing). First of all, in terms of helping decision-makers make quality decisions, statistical hypothesis testing and data analysis make for just one tool in a large toolbox, and it's based on what we often call reductionist theory. In short, the tool examines parts of a system and then makes inferences as to the whole system.
The tool is usually quite good at testing hypotheses under carefully controlled experimental conditions. For example, the success of the pharmaceutical industry is, in part, due to the fact that it can design and implement controlled experiments in a laboratory. However, even under controlled experimental procedures, the tool has limitations. Simple confidence intervals (C.I.) provide good insight into the accuracy (usefulness) of such models. For the COVID-19 models that we have seen on the so-called "news," the C.I. is often reported as a range of the predicted number of people who will contract or die from the disease (e.g., 60,000 to 2 million).
(Excerpt) Read more at americanthinker.com ...
I have a brother who is an actuary. He crunches numbers for pension plans so that they can try and aim for rates of return on their investments that will stay ahead of the anticipated draw.
This consigns him to the very macabre field of modeling when people will die. He is annoyed that many people, when they find out what he does for a living, will approach him and ask in all sincerity “So, how long have I got?”
The way he explains it to them is “If you take 5000 people your age, and pack them into a gymnasium, and ask me how many of them will still be alive in ten years, I can give you a really accurate prediction. If you ask me how long any one individual has to live I’m clueless”.
Sort of like what has gone on in these models. They are trying to predict big picture stats, while the media is communicating that down to people that experts are predicting their death.
“If you take 5000 people your age, and pack them into a gymnasium, and ask me how many of them will still be alive in ten years, I can give you a really accurate prediction.”
So if he predicted thirty people, but in reality only one died, how long would he keep his job?
Sorry, I posted the number who would die rather than still be alive.
I don't think Trump or his team do.
This article says reductionist models have limitations. Nice insight, Captain O.
You already know how long he’d keep it if he was regarded as an “expert” by the government and especially if it was a government-funded study.
I wlll gladly follow that model!
As people often say — “All models are wrong; but some models are useful.”
That is usually meant sincerely and it can be true. In a lot of scientific studies, a model can point you in the right direction although it won’t be 100% accurate. It’s “wrong”, but it is “useful”.
But the coronavirus is as much political as it is epidemiological. The models that are being used may be “wrong” but are they “useful” — and what does “useful” mean? Well, the models totally derailed Trump’s booming economy. Somebody somewhere is very proud of the very useful model they developed.
The author gets it. Models support the scientific method, they don’t supplant it. You don’t check your brains at the door when you walk into the modeling realm. You have to maintain critical thinking as well as broad perspectives. Of course, much of the entire scientific community has been hijacked by political forces (primarily from the left) with a very definite agenda.
So we can shut down the economy immedistely based on slim data about the virus from unreliable sources, but we can’t restart at a slow roll until a vaccine or treatment has been tested and proven effective after lonfs months study?
Makes perfect sense!
“This article says reductionist models have limitations. Nice insight, Captain O.”
LOLOLOLOL!
Yep I saw that one too.
From my point of view the models are garbage. They are counting anybody that dies around someone with the virus as a victim. Also they only test those that need serious medical attention. I’m no mathematician but you can’t get a good model if your data is crap.
Ten years.
The models did a lousy job of predicting “big picture stats.” The problem is that the federal and state governments used them to develop and distribute resources as well as an action plan on combating the virus.
We shut down the best economy on the planet and plunged us into a recession with almost 17 million people filing unemployment claims in three weeks. We have added trillions to our national debt and lost trillions in wealth. And there is no guarantee that we can revive the economy any time soon.
52 years in the case of Fauci.
52 years in the case of Fauci.
Yup - If you wait I can get ya a lab report
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.