[cb1972]

where can i find the most accurate data regarding the covid #s in Florida. For example the John Hopkins site continues to indicate that the percent of tests positive on a daily basis in Florida is above 10, while Florida Health reports that our Percent positive rate has been between 4 and 5 percent for weeks . Why would there be such conflicting numbers, many states are basing their quarantine policies on these metrics which seem at odds

[CoachKandSportsguy]

OP,

Your question is valid, but then the data has more than one way to be calculated, which is the root cause for your question. So without understanding the different viewpoints of the basis of calculation, you are staring at just numbers, not enough context, very nuanced so read the fine print of basis The following discussion is not to discredit the prior poster's graphics and data, but to understand the basis and use/abuse of the data presented.

1) calculate the positivity per test. seems valid, but may not represent the population. Why? what if the tests are only of health care workers? or the tests are for long term care patients? Raw test data will also include the same person tested over and over, which introduce a time dimension or repeat versus never tested blend. best answer is to test the entire population but not possible nor practical, especially at the very beginning, which led to small populations and symptomatic only, so much higher rate of positivity. Statistical sampling will infer that rate to the population, but if not bias adjusted for sample definition, a poor or wrong inference will occur. (hence data confusion)

2) counting the only individuals tested. May be better, but has the same population bias. Then throw in what do you do with positive people? stop counting them? make sense, but then as the virus spreads, your denominator of tested individuals will continue to shrink, and with a smaller denominator, the positivity rate will start to creep higher.

3) inferential stats are based on random sampling. The testing here on covid is not random in general. There are population tested, and the rate of college student positivity probably won't represent the florida over 65 population rate of positivity. One can population adjust the testing stats, but if the populations don't overlap with any common attributes, like the college student positivity in the villages, there is no validity of information.

So, these type of issues plague (pun intended) data analytics, especially in a population as large and diverse as the US. That point is why i have stated in a post about what have we learned about the virus, a lot, but information / knowledge is assymetrical, increasing over time, from very wrong conclusions to a more accurate but never complete understanding because the entire population can never be tested and never routinely tested.

I hope this helps you understand that the fine print must be read to understand the relevance of the population and the frequency, and any transformations, such as a exponential weighted average to smooth out daily noise.

sportsguy

[Dana1963]

Originally Posted by cb1972

where can i find the most accurate data regarding the covid #s in Florida. For example the John Hopkins site continues to indicate that the percent of tests positive on a daily basis in Florida is above 10, while Florida Health reports that our Percent positive rate has been between 4 and 5 percent for weeks . Why would there be such conflicting numbers, many states are basing their quarantine policies on these metrics which seem at odds

It’s the old saying figures don’t lie people do

[Bay Kid]

Who do you believe anymore? They all have an agenda.

[vintageogauge]

I don't pay attention to any of the statistics anymore, I'm really tired of seeing them and hearing about them. I continue to be cautious and playing it safe by using common sense. I feel that I wasted 8 or 9 months of what is left of my life worrying about this and won't continue to do so.

[OrangeBlossomBaby]

This is the desktop version:
Experience

[stephen.q.pankow]

I have a related question: On the Florida Covid-19 Dashboard web site, the data for Sumter County seem to have been averaging about 10 new cases per day, but then spiking to 61 and 80 new cases on September 29 and 30. That doesn't seem realistic. I've noted similar spikes in previous months, most commonly occurring on a Thursday or Friday.

Can anyone explain this, or at least offer a theory as to a possible cause?

[Ragman]

This is the most complete site I have found:

Home | Florida Department of Health COVID-19 Outbreak

Both the state prison in Bushnell and the federal Coleman complex are included in the county reporting. Coleman had a surge in reporting the days mentioned. Sumter's total case number ( 2,481) include 624 (25% vs. 3% state average)from the corrections system.

Sometimes you need to track the data presented yourself. For instance, daily statewide hospitalizations from Covid-19 on 7/22/20 was 9,595 and yesterday was 2,154.

Anyone is, of course, free to believe what they wish, but I think overall The Villages and its population have been doing a good job in a difficult situation.

[cb1972]

Thanks all for your input, wanted to come down to get the house ready for the winter season but it looks like Father Andrew will make us quarantine for two weeks based on false metrics

[CoachKandSportsguy]

I know that people think that numbers are lying or that statistics are lying, but this is the reality of medical reporting data. The world is not simple, the world is not linear, and the world has a very, very large component of randomness with which humans have a hard time synthesizing.

So one poster asked for a reason for a jump in data test results. That will be impossible to know from here as there are so many variables involved, starting with samples taken. not every day is there a standard number of tests taken. not everyday is the same population tested, again, new people or retests for job availability. there is variability in the daily sample collection process. Then there is sample transport, time from sample site to lab site. Don't assume that its instantaneous or the same time from each location. Then there is daily testing rate. humans must log and set up the tests and then run the tests. don't assume that there is a standard rate of daily testing The rate will be variable based upon humans working and backlog of samples, and breakage and new machine acquisition.

So the output timing is a combination of all these variables, so which one is responsible for the increase in positives? most likely a combination of location and people taken, and sample backlog and throughput. There is a more randomness in this process than one might image, since in the rest of one's daily life, this randomness has been eliminated by industrial process control and advanced planning and safety stock, ie, your food being available at the store when you arrive.

There was a poster a while back who made the blank statement that "you don't understand medical records" and I agree, but he did not elaborate further. I will elaborate a little bit on the current state of reporting processes later, but i would suspect that its not what one might assume, given the similar complexities of medical reporting.

Which is why understanding the data and the information contained within requires a level of experience and education. So its also highly unlikely that the daily journalist has this level of nuanced understanding.

sportsguy

[jebartle]

Originally Posted by CoachKandSportsguy

OP,

Your question is valid, but then the data has more than one way to be calculated, which is the root cause for your question. So without understanding the different viewpoints of the basis of calculation, you are staring at just numbers, not enough context, very nuanced so read the fine print of basis The following discussion is not to discredit the prior poster's graphics and data, but to understand the basis and use/abuse of the data presented.

1) calculate the positivity per test. seems valid, but may not represent the population. Why? what if the tests are only of health care workers? or the tests are for long term care patients? Raw test data will also include the same person tested over and over, which introduce a time dimension or repeat versus never tested blend. best answer is to test the entire population but not possible nor practical, especially at the very beginning, which led to small populations and symptomatic only, so much higher rate of positivity. Statistical sampling will infer that rate to the population, but if not bias adjusted for sample definition, a poor or wrong inference will occur. (hence data confusion)

2) counting the only individuals tested. May be better, but has the same population bias. Then throw in what do you do with positive people? stop counting them? make sense, but then as the virus spreads, your denominator of tested individuals will continue to shrink, and with a smaller denominator, the positivity rate will start to creep higher.

3) inferential stats are based on random sampling. The testing here on covid is not random in general. There are population tested, and the rate of college student positivity probably won't represent the florida over 65 population rate of positivity. One can population adjust the testing stats, but if the populations don't overlap with any common attributes, like the college student positivity in the villages, there is no validity of information.

So, these type of issues plague (pun intended) data analytics, especially in a population as large and diverse as the US. That point is why i have stated in a post about what have we learned about the virus, a lot, but information / knowledge is assymetrical, increasing over time, from very wrong conclusions to a more accurate but never complete understanding because the entire population can never be tested and never routinely tested.

I hope this helps you understand that the fine print must be read to understand the relevance of the population and the frequency, and any transformations, such as a exponential weighted average to smooth out daily noise.

sportsguy

In other words, you can make numbers say anything you want!

[Altavia]

Sumter's 21% Positivity Linked To COVID-19 Cases At Coleman Prison | Health News Florida

Sumter's 21% Positivity Linked To COVID-19 Cases At Coleman Prison
By JOE BYRNES - WMFE • OCT 1, 2020

An increase in COVID-19 cases in Sumter County is tied to newly reported data Wednesday from the federal prison complex in Coleman.

But The Villages retirement community also added 20 cases, according to the state, as it prepares to revive its social life next week.

The Villages will begin nightly concerts on the town squares and club activities in the recreation centers.

Sumter added 61 new positive tests on Tuesday and one additional death, bringing its death toll to 70. The positivity rate was 9.4% on Monday and more than 21% on Tuesday.

A Florida Department of Health spokeswoman says cases from Coleman are contributing to the spike.

The Federal Bureau of Prisons reports 257 active cases among prisoners there and 106 among staff. So far, three inmates have died.

[CoachKandSportsguy]

Originally Posted by jebartle

In other words, you can make numbers say anything you want!

That is the abuse of statistics and data, and to some extent you are correct, but there are limits. But the "trick" with the data to information process is to simplify complex data down to its principle components. in predictive analytics its called principle component analysis, PCA, and with that the presentation can be intuitive between data and information. But the other side of the coin is that certain people want the different cuts or presentations of data. so one presentation doesn't answer all questions to all readers. so as my boss says, the right information at the right time to the right audience

However, with time series, or trending, such as by day, there is more randomness so averages are used, such as a 7 day average, or like in the stock market a 50 day moving average. Same concept.

[Chitown]

Originally Posted by cb1972

where can i find the most accurate data regarding the covid #s in Florida. For example the John Hopkins site continues to indicate that the percent of tests positive on a daily basis in Florida is above 10, while Florida Health reports that our Percent positive rate has been between 4 and 5 percent for weeks . Why would there be such conflicting numbers, many states are basing their quarantine policies on these metrics which seem at odds

The following numbers are from the New York Times they went state by state here is Florida’s results as of October 7, 2020. 724,000 cases since it’s inception of the virus, 14,900 deaths since it’s inception. Just over a 2% death rate or shall I say a 98% recovery rate. I know the next thing I’m going to get hit with is we don’t know what the long-term effects are on our organs. I do No this much, in April both my wife and I developed Covid both of us had minor symptoms of low fever and a little cough both of us recovered just fine. Several friends also have had it since then also with minor symptoms all have recovered. To this day we all feel great. We are all in our mid-60s and a couple couple of my friends were in their early 70s. Just saying!

[Topspinmo]

Originally Posted by cb1972

where can i find the most accurate data regarding the covid #s in Florida. For example the John Hopkins site continues to indicate that the percent of tests positive on a daily basis in Florida is above 10, while Florida Health reports that our Percent positive rate has been between 4 and 5 percent for weeks . Why would there be such conflicting numbers, many states are basing their quarantine policies on these metrics which seem at odds

It’s guessamont. I imagine it’s based on reported. So the integrity fails on agenda’s of the reporter’s if any.