Can blockchain save us?

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

Sine poena nulla lex.

claym711 said:

---

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

---

This is pretty much where I am at this point. It is not spreading in any western countries that have active cases, and it's barely spreading in countries like Thailand and India. The cases we are seeing in China are happening because it got out of control before anything was done to stem the spread. It will take time to get it under control there, but it looks like the rest of the world is ready and able to prevent any significant outbreaks.

I have reached the point where i think other international leaders see the numbers in China as somewhat irrelevant - not to come across cruel or dismissive of this awful disease, but the Chinese are have more questions about their numbers than the Iowa caucus. I think what everyone else is truly watching are the non- China numbers. If China can contain (more evidence based on the military presence) then Foreign leaders won't protest the lack of clarity. However knowing the true numbers in the Philippines, Thailand and US are what matters.

C@LAg said:

---

GE said:

---

Explain please

---

cut and pasted from internet. you should get the gist of it from this:



R-square tell us how much variation in the dependent variable is accounted for by the regression model, the adjusted value tells us how much variance in the dependent variable would be accounted for if the model had been derived from the population from which the sample was taken. Specifically, it reflects the goodness of fit of the model to the population taking into account the sample size and the number of predictors used.

A data-set should always be explored to see if it meets the assumptions of the statistical methods applied. The multivariate data analyses we are intending assume normality, linearity and absence of multicollinearity .

Normality refers to the shape of the data distribution for an individual variable and its correspondence to the normal distribution. In this study, the assumptions of normality were examined by looking at histograms of the data, and by checking skewness and kurtosis. The distribution is considered normal when it is bell shaped and values of skewness and kurtosis are close to zero.

The linearity of the relationship between the dependent and independent variables represents the way changes in the dependent variable are associated with the independent variables, namely, that there is a straight-line relationship between the independent variables and dependent variable. This assumption is essential as regression analysis only tests for a linear relationship between the independent variables and dependent variable. Pearson correlation can capture the linear association between variables.

Multicollinearity is the existence of a strong linear relationship among variables, and prevents the effect of each variable being identified. Many Scholars recommend examining the variable inflation factor (VIF) and tolerance level (TOL) as a tool for of multicollinearity diagnostics. VIF represents the increase in variance that exists due to collinearities and interrelationships among the variables. VIFs larger than 10 indicate strong multicollinearity and as a rule of thumb VIFs should be less than 0.1

An R-square=1 indicates perfect fit. That is, you've explained all of the variance that there is to explain. you can always get R-square=1 if you have a number of predicting variables equal to the number of observations, or if you've estimated an intercept the number of observations .

---

I have a decent sense of most of that but am not following from that to what the other poster said. The data released doesn't fit well enough to be completely formulaic unless someone is adjusting them just to throw noise in the system. I'm questioning the statement that it is statistically impossible for those numbers to be the actual numbers

Sine poena nulla lex.

FWIW. Family friend works for WHO in Switzerland. Says it's a foregone conclusion that it will be a pandemic, travel is too widespread. They also think it's more contagious than SARS but less deadly. I can't qualify if that's based on better insight than any of us have, or even if this isn't just their opinion.

Also, for those saying we know how it's going to roll, I don't think that's quite the case. Start date in China was likely early December.

C@LAg said:

---

GE said:

---

C@LAg said:

---

GE said:

---

Explain please

---

---

I have a decent sense of most of that but am not following from that to what the other poster said. The data released doesn't fit well enough to be completely formulaic unless someone is adjusting them just to throw noise in the system. I'm questioning the statement that it is statistically impossible for those numbers to be the actual numbers

---

aren't they saying the R went from 2.1 to almost 1.

thus it is statistically impossible unless someone is lazily fudging the numbers.

---

If the R was a law of nature I would agree

GE said:

---

C@LAg said:

---

GE said:

---

Explain please

---

cut and pasted from internet. you should get the gist of it from this:



R-square tell us how much variation in the dependent variable is accounted for by the regression model, the adjusted value tells us how much variance in the dependent variable would be accounted for if the model had been derived from the population from which the sample was taken. Specifically, it reflects the goodness of fit of the model to the population taking into account the sample size and the number of predictors used.

A data-set should always be explored to see if it meets the assumptions of the statistical methods applied. The multivariate data analyses we are intending assume normality, linearity and absence of multicollinearity .

Normality refers to the shape of the data distribution for an individual variable and its correspondence to the normal distribution. In this study, the assumptions of normality were examined by looking at histograms of the data, and by checking skewness and kurtosis. The distribution is considered normal when it is bell shaped and values of skewness and kurtosis are close to zero.

The linearity of the relationship between the dependent and independent variables represents the way changes in the dependent variable are associated with the independent variables, namely, that there is a straight-line relationship between the independent variables and dependent variable. This assumption is essential as regression analysis only tests for a linear relationship between the independent variables and dependent variable. Pearson correlation can capture the linear association between variables.

Multicollinearity is the existence of a strong linear relationship among variables, and prevents the effect of each variable being identified. Many Scholars recommend examining the variable inflation factor (VIF) and tolerance level (TOL) as a tool for of multicollinearity diagnostics. VIF represents the increase in variance that exists due to collinearities and interrelationships among the variables. VIFs larger than 10 indicate strong multicollinearity and as a rule of thumb VIFs should be less than 0.1

An R-square=1 indicates perfect fit. That is, you've explained all of the variance that there is to explain. you can always get R-square=1 if you have a number of predicting variables equal to the number of observations, or if you've estimated an intercept the number of observations .

---

I have a decent sense of most of that but am not following from that to what the other poster said. The data released doesn't fit well enough to be completely formulaic unless someone is adjusting them just to throw noise in the system. I'm questioning the statement that it is statistically impossible for those numbers to be the actual numbers

---

An R^2 value of 1.000 means the real world data is a perfect fit to a mathematical prediction model. This is fundamentally impossible because there is no such thing as a perfect fit. You will always have noise and data points that don't fit a model exactly. In other words, you will have data points that are regularly above or below the trendline with varying percentage differences. You may see an R^2 of 0.923 if you have a really good model, but never a 1.000. A perfect fit means every single data point fit the trendline almost exactly, so close that the R^2 is 1.000. This is not possible for real world data, which means the Chinese numbers are clearly just made up from a formula.

R^2 is regression, it's a comparison of the measured data to the model.

In real life you don't get empirical data to have R^2 values of 0.999 unless you're measuring something for which you have an analytical solution.

What I mean is, if you're measuring a behavior against a known physical formula, what your regression is telling you is your measurement error.

When you're looking at statistical sampling, your best fit curve is created to fit your data - so the regression is telling you your model error.

If your regression is zero / R^2 is 1.000 that means you have no measurement error and no model error. Can't be, without rounding or general lack of precision. Or tampering.

Nuclear Scramjet said:

---

GE said:

---

C@LAg said:

---

GE said:

---

Explain please

---

cut and pasted from internet. you should get the gist of it from this:



R-square tell us how much variation in the dependent variable is accounted for by the regression model, the adjusted value tells us how much variance in the dependent variable would be accounted for if the model had been derived from the population from which the sample was taken. Specifically, it reflects the goodness of fit of the model to the population taking into account the sample size and the number of predictors used.

A data-set should always be explored to see if it meets the assumptions of the statistical methods applied. The multivariate data analyses we are intending assume normality, linearity and absence of multicollinearity .

Normality refers to the shape of the data distribution for an individual variable and its correspondence to the normal distribution. In this study, the assumptions of normality were examined by looking at histograms of the data, and by checking skewness and kurtosis. The distribution is considered normal when it is bell shaped and values of skewness and kurtosis are close to zero.

The linearity of the relationship between the dependent and independent variables represents the way changes in the dependent variable are associated with the independent variables, namely, that there is a straight-line relationship between the independent variables and dependent variable. This assumption is essential as regression analysis only tests for a linear relationship between the independent variables and dependent variable. Pearson correlation can capture the linear association between variables.

Multicollinearity is the existence of a strong linear relationship among variables, and prevents the effect of each variable being identified. Many Scholars recommend examining the variable inflation factor (VIF) and tolerance level (TOL) as a tool for of multicollinearity diagnostics. VIF represents the increase in variance that exists due to collinearities and interrelationships among the variables. VIFs larger than 10 indicate strong multicollinearity and as a rule of thumb VIFs should be less than 0.1

An R-square=1 indicates perfect fit. That is, you've explained all of the variance that there is to explain. you can always get R-square=1 if you have a number of predicting variables equal to the number of observations, or if you've estimated an intercept the number of observations .

---

I have a decent sense of most of that but am not following from that to what the other poster said. The data released doesn't fit well enough to be completely formulaic unless someone is adjusting them just to throw noise in the system. I'm questioning the statement that it is statistically impossible for those numbers to be the actual numbers

---

An R^2 value of 1.000 means the real world data is a perfect fit to a mathematical prediction model. This is fundamentally impossible because there is no such thing as a perfect fit. You will always have noise and data points that don't fit a model exactly. In other words, you will have data points that are regularly above or below the trendline with varying percentage differences. You may see an R^2 of 0.923 if you have a really good model, but never a 1.000. A perfect fit means every single data point fit the trendline almost exactly, so close that the R^2 is 1.000. This is not possible for real world data, which means the Chinese numbers are clearly just made up from a formula.

---

Show me the derivation of that being 1.000 - I havent calculated it but that's not how it looks to me

This will lead to accurate results

k2aggie07 said:

---

R^2 is regression, it's a comparison of the measured data to the model.

In real life you don't get empirical data to have R^2 values of 0.999 unless you're measuring something for which you have an analytical solution.

What I mean is, if you're measuring a behavior against a known physical formula, what your regression is telling you is your measurement error.

When you're looking at statistical sampling, your best fit curve is created to fit your data - so the regression is telling you your model error.

If your regression is zero / R^2 is 1.000 that means you have no measurement error and no model error. Can't be, without rounding or general lack of precision. Or tampering.

---

Exactly!

R^2 of 0.999 means the numbers are completely bogus. Taken from a math formula with a small fudge factor applied so the R^2 isn't exactly 1.0.

The numbers that China is reporting isn't just inaccurate. They are completely devoid from reality.

From the beginning, people have speculated that the Chinese numbers are underreported. Several times I said "Take China's number and multiply by 100 and you'll get the actual numbers". This regression value proves that I was wrong.

China's numbers aren't merely a scaled down version of the actual numbers. They are completely manufactured.

Sine poena nulla lex.

claym711 said:

---

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

---

Based on the reported 2-2.5 week incubation period, we're at least eight days out from knowing if we have a problem here in the US of A.

C@LAg said:

---

GE said:

---

Show me the derivation of that being 1.000 - I havent calculated it but that's not how it looks to me

---

Read his comment here:

look at the point graph, at the daily observations (the green line).

It has achieved a nearly perfect flat line (at 2.1%) for the last week.

Daily deviation is essentially 0, so the R^2 = 1.

---

Your last comment only applies to the mortality rate doesn't it

Sine poena nulla lex.

GE said:

---

C@LAg said:

---

GE said:

---

Show me the derivation of that being 1.000 - I havent calculated it but that's not how it looks to me

---

Read his comment here:

look at the point graph, at the daily observations (the green line).

It has achieved a nearly perfect flat line (at 2.1%) for the last week.

Daily deviation is essentially 0, so the R^2 = 1.

---

Your last comment only applies to the mortality rate doesn't it

---

You can model everything the Chinese are reporting to within a percentage point or two. That's insane and should not be possible.

AG 2000' said:

---

claym711 said:

---

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

---

Based on the reported 2-2.5 week incubation period, we're at least eight days out from knowing if we have a problem here in the US of A.

---

2-2.5 weeks? Isnt it 3-14 days?

I suspect it can be modeled when you have a fixed capacity for testing to confirm nCor. They can only produce data for what they have been able to confirm meaning only what they have the capacity to test.

Sine poena nulla lex.

If you take out the medieval warming in any virus model the plot will show...EVERYBODY DIES

AG 2000' said:

---

claym711 said:

---

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

---

Based on the reported 2-2.5 week incubation period, we're at least eight days out from knowing if we have a problem here in the US of A.

---

False. Incubation is not 14-18 days.

Then all you'd be able to see is the number of maximum tests, times the total positive result rate (including false positives).

At any rate unless the testing capacity / number of tests and positive result rate are increasing at the same rate you won't see a sustained parabolic growth to the same curve day after day.

swimmerbabe11 said:

---

That's the second or third time you've attempted to call him out.. Do you think it will work this time?

---

Ask him

Average incubation period is about 5 days. Up to 14 is possible, but it's an outlier, not the norm.

claym711 said:

---

AG 2000' said:

---

claym711 said:

---

It has been long enough. If it was going to take off here, it would have by now. Wuhan may be devastated but it's not going to be anywhere near that serious here.

---

Based on the reported 2-2.5 week incubation period, we're at least eight days out from knowing if we have a problem here in the US of A.

---

False. Incubation is not 14-18 days.

---

Say false all you want. US military intel from Asia is reporting back 14-16 days. Via military family deployed to that part of the world in the last month who was part of our SARS response in Thailand who have good medical contacts in Thailand, Japan, and China.

And just to clarify, the *average* is coming in at about six days for people in poor hygiene / health in that part of the world. There's enough data to know that with our hygiene, personal space, and general health, that the time to onset of symptoms is longer.

I understand why hygiene is important for preventing transmission but why does it affect the incubation period?

Madman said:

---

I understand why hygiene is important for preventing transmission but why does it affect the incubation period?

---

Incubation period was the wrong term to use. It's about time from exposure to exhibiting symptoms.

JJxvi said:

---

Seems bad for the CDC to recommend 14 day isolation for a 16 day incubation period disease...

---

CDC is under enormous political and economic pressure from within the US and the world. They're basically hoping for the best while quietly preparing for the worst.

Here is a little 3rd hand info coming out of mainland China. This is via my friend who speaks mandarin after several trips over and over a year living there.

His MD contact, a hospital pulmonary specialist, is barred from leaving the hospital and has not been home for several days, 24/7 at the hospital. They are running out of n95 masks and are requesting them from my fiend. Scary that they can't even keep medical professionals supplied with proper PPE. This is troubling, when the MDs get sick who is going to take care of patients.

His party member contact is quarantined at home, allowed to leave once per week to go to the market. This contact still maintains that the rumor going around the CCP is that the virus is an escaped bio weapon in development.

Both are unnerved by the lack of transparency within the government (duh). They say this is on a whole new level compared to the party's normal shenanigans.

AG 2000' said:

---

Madman said:

---

I understand why hygiene is important for preventing transmission but why does it affect the incubation period?

---

Incubation period was the wrong term to use. It's about time from exposure to exhibiting symptoms.

---

A lot of cases are taking as long as 2-3 weeks to actually turn serious after first becoming symptomatic, as well.

Good point and true. But i wouldn't think they are randomly applying the test. More likely than not it is skewed in some form.