For the same reasons, plus the likelehood that the virus arrived in NYC early and frequently, NYC's figures cannot be extrapolated to the rest of the state or country.
I would like to see how these figures match up to the sewage-sampling method of estimation.
Those that did stay and still need food (ie produce) are having it delivered.
People who are shopping in stores are absolutely a very biased sample.
Very specifically, this bias excludes older people who are locking themselves away very very judiciously.
Seriously? Your personal network is evidence the this study is useless because of sampling bias?
Everyone I know voted for Hilary Clinton and yet here we are.
> People who are shopping in stores are absolutely a very biased sample.
People who have jobs that allow them to work from home are a very biased sample. How many grocery stockers are there in NYC compared to let’s say, software developers? I suspect you haven’t a clue, since by your own admission you don’t know a single person who needs to leave their home to work. So maybe your mental model if who makes up the population is skewed.
Yes, exactly. ...just like the study's data that excludes them.
That's my point.
And let's be real, biasing your sample by not including a small minority doesn't affect the outcome of a study nearly as much as doing the opposite and sampling mostly from that small minority. Does it make the results less accurate? Yes. Does it make the results nearly as inaccurate as it would be if they excluded most of people but that minority? Not at all.
This surprises me if for no other reason than it takes a lot of space to store 1-2 months of food. Might be true, but is certainly different than what is going on in suburban Connecticut based on my social network.
One explanation might be that it got an earlier start in NYC, but both the hospitalizations and fatalities seem to have started showing up on about the same dates in the city and the surrounding suburbs.
There seems to be a significant ethnic variation, but ethnicity is such a correlate to other issues that it is not likely to be informative on its own.
I think people see these studies of places they visited once and determine that those areas are way more dense and that they have seen the news and that all those deaths are due to tons of people having it.
That is just not true. The studies are biased and likely this will go on for a long-time. We know this is way more deadly than the flu. That is obvious when you look at simple examples like the princess cruise in Japan. How often do 7+ people die on a cruise ship on a single voyage?
I am suffocating under the irony.
Would be useful to know how many deaths from the same zip codes are people who visited crowded grocery stores.
Should be re-written as:
"Preliminary test results suggest 21% of of people approached in a crowded grocery store and who would agree to give blood have Covid antibodies"
All of these tests suffer the same sample bias, and that sample bias is massive.
People who are already in a grocery store (risky behavior), who are willing to give a blood sample (believes they may have been previously exposed) are not the same as people who are leaving their house only for very limited purposes and ordering food online.
If we assume that the % of people shopping in grocery stores and willing to take the test are in risk group A, and the people not shopping are in risk group B. We can run the following quick analysis.
First, assume risk group A is 5 times as likely to have had COVID than Risk group B (but plug any assumption in there necessary)
Then assume that risk group A is only 10% of the population, then rerun the numbers as follows:
For every 100 people in risk group A who tested, 21 were positive.
Risk group A is 100 people, and risk group B is 900.
Risk group A's 100 were 21 prior positive. Risk group B's 900 could be estimated that 4.2 people per 100 were positive, so in total of the 900 people 37.8 were positive.
21+37.8 = 59 people of 1000, or 5.8%.
Plug any numbers you want in the analysis, but the assumptions drive huge variability in the % of New Yorkers infected. Without a less biased sample, we really don't know much other than that way less than 21% of New Yorkers have anti-bodies.