CDC data from over 3,000 US counties, with a population of about 330 million people, show that the COVID-19 vaccine in 2022 caused 138,229 (95% CI: 90,178-186,279) deaths, and 150,602 (95% CI: 118,606-182,599) in 2023.
Why don’t you make correct adjustments so your model doesn’t leave so much variation unexplained.
Why that correlation is meaningless for causation
1. Age confounding:
Older counties (Florida, Pennsylvania, Midwest) had both higher vaccination rates and higher baseline mortality.
Unless you age-adjust, you automatically create a “positive association.”
2. COVID burden:
Counties hit hardest by COVID were more likely to vaccinate and to record excess deaths from the disease.
The model treats those deaths as “vaccine-caused.”
3. Socio-economic differences:
Mortality strongly tracks poverty and chronic-disease prevalence.
None of those were included as controls in his regression.
4. Statistical fit problems:
The R² values (~0.45–0.57) mean the model leaves roughly half the variation unexplained.
When you include confounders (age structure, COVID incidence, race, income), the “vaccine-uptake” coefficient collapses to near zero or reverses sign — a pattern shown by independent demographers re-running the same data.
Is everyone else lying. Or is myAI somehow biased or do you not adjust for those factors.
"CDC data from over 3,000 US counties, with a population of about 330 million people, show that the COVID-19 vaccine in 2022 caused 138,229 (95% CI: 90,178-186,279) deaths, and 150,602 (95% CI: 118,606-182,599) in 2023."
Now I wonder what the 2024 data looks like. If it's a linear curve we're talking 162.000 give or take a few hundred. I'm guessing it's not. I think it's going to be exponential.
Im not sure where to start. In the population that adheered to the CDC recommandation there is a wast overrepresentation of people with pre-excisting condiditons and risk factors. This part of the population also has an icreased mortality risk regardless of vaccines, or covid for that matter.
How do you conclude that all increase in excsess mortality regardless of cause is linked to the vaccine? Have other factors such as sosio-economic, availability of healthcare, access to medicine for those whit cronic conditions ect. been adjusted for? The opioid epidemic, malnutrition, an aging population? The increase in mental health related morbitity and decrease in mental health care?
Small counties with small populations will have a huge variation in % excess mortality with a variation of only a few deaths pr. year. In the example from the article the increase from 100 to 120 deaths could just as well have resulted from a fire, a local e.coli epidemic, a school bus accident or a mass shooting? Or a cornestone industry closing a factory, resulting in increased poverty, unemployment and social despair. All factors known to reduce expected lifespan and incresed morbidity and mortality for both somatica and psychiatric diseases. Lover socioeconomic groups are at increased risk of allmost all causes of premature death.
The demograpic in counties with very lov vaccination rates might differ from the mean population regarding all these factors.
My conclusion regarding this analysis is that there has not been established a steong enough link between the increase in excess mortality and the vaccine uptake in a given county.
Why not take a look at the population as a whole, sorted in to two groups accounting for afromenshioned factors with the only variable being the vaccine? And heres a freebe. Those results would indeed show an increased mortality, but not 5% and a tiny fraction of people who dies due to covid or covid-related causes.
If we are not exploring the effects of variables in each county, using deaths pr. county only obscures the results.
Why not analyse the p-value in the stated example, where 20 deaths give a 20% increase in excess mortalty?
Reading this it seems obvious to me that the aim of this study was to find, analyse and present data that confirmed the authors hypothesis that the covid vaccine has caused far more deaths and disease than empirical studies shows. A more constructive and, well, scientific approach would be to eliminate all other variables as described above. Maby cov-19-vaccine does lead to increased excess deaths. Respiratory and circulatory, phsyciatric, hell, lets throw autism in for free. I can't say it doesn't, just as this article doesn't show that it does. But cov-19-vaccine causing an increase in banana-slipping or parachute related mortalities?
To me this only serves as an example of how to use statistics and data analysis to create a heavily biased article targeted at an scientificly illiterate audience for them to validate their beliefs.
This is not ment as critisism of the author or anyone else, but as a critisism of pseudoscience and misrepresentation/manipulation/cherrypicking. The scientific method and the ethical principles in research are fundemental in our search for empirical knowledge and objective truths. Now more than ever.
Why show the general public all these charts and figures ? We can’t understand any of it . Or what it means or says . Someone else will dhow their charts and figures. And say theirs are the true facts . At this point in the game . The public has been told so many lies by the American government. It’s a total shame .
This is a wonderful piece of work showing the covid vaccines were net harm.
Why don’t you make correct adjustments so your model doesn’t leave so much variation unexplained.
Why that correlation is meaningless for causation
1. Age confounding:
Older counties (Florida, Pennsylvania, Midwest) had both higher vaccination rates and higher baseline mortality.
Unless you age-adjust, you automatically create a “positive association.”
2. COVID burden:
Counties hit hardest by COVID were more likely to vaccinate and to record excess deaths from the disease.
The model treats those deaths as “vaccine-caused.”
3. Socio-economic differences:
Mortality strongly tracks poverty and chronic-disease prevalence.
None of those were included as controls in his regression.
4. Statistical fit problems:
The R² values (~0.45–0.57) mean the model leaves roughly half the variation unexplained.
When you include confounders (age structure, COVID incidence, race, income), the “vaccine-uptake” coefficient collapses to near zero or reverses sign — a pattern shown by independent demographers re-running the same data.
Is everyone else lying. Or is myAI somehow biased or do you not adjust for those factors.
That estimate is pretty modest to put it mildly. 🤣
"CDC data from over 3,000 US counties, with a population of about 330 million people, show that the COVID-19 vaccine in 2022 caused 138,229 (95% CI: 90,178-186,279) deaths, and 150,602 (95% CI: 118,606-182,599) in 2023."
Now I wonder what the 2024 data looks like. If it's a linear curve we're talking 162.000 give or take a few hundred. I'm guessing it's not. I think it's going to be exponential.
Im not sure where to start. In the population that adheered to the CDC recommandation there is a wast overrepresentation of people with pre-excisting condiditons and risk factors. This part of the population also has an icreased mortality risk regardless of vaccines, or covid for that matter.
How do you conclude that all increase in excsess mortality regardless of cause is linked to the vaccine? Have other factors such as sosio-economic, availability of healthcare, access to medicine for those whit cronic conditions ect. been adjusted for? The opioid epidemic, malnutrition, an aging population? The increase in mental health related morbitity and decrease in mental health care?
Small counties with small populations will have a huge variation in % excess mortality with a variation of only a few deaths pr. year. In the example from the article the increase from 100 to 120 deaths could just as well have resulted from a fire, a local e.coli epidemic, a school bus accident or a mass shooting? Or a cornestone industry closing a factory, resulting in increased poverty, unemployment and social despair. All factors known to reduce expected lifespan and incresed morbidity and mortality for both somatica and psychiatric diseases. Lover socioeconomic groups are at increased risk of allmost all causes of premature death.
The demograpic in counties with very lov vaccination rates might differ from the mean population regarding all these factors.
My conclusion regarding this analysis is that there has not been established a steong enough link between the increase in excess mortality and the vaccine uptake in a given county.
Why not take a look at the population as a whole, sorted in to two groups accounting for afromenshioned factors with the only variable being the vaccine? And heres a freebe. Those results would indeed show an increased mortality, but not 5% and a tiny fraction of people who dies due to covid or covid-related causes.
If we are not exploring the effects of variables in each county, using deaths pr. county only obscures the results.
Why not analyse the p-value in the stated example, where 20 deaths give a 20% increase in excess mortalty?
Reading this it seems obvious to me that the aim of this study was to find, analyse and present data that confirmed the authors hypothesis that the covid vaccine has caused far more deaths and disease than empirical studies shows. A more constructive and, well, scientific approach would be to eliminate all other variables as described above. Maby cov-19-vaccine does lead to increased excess deaths. Respiratory and circulatory, phsyciatric, hell, lets throw autism in for free. I can't say it doesn't, just as this article doesn't show that it does. But cov-19-vaccine causing an increase in banana-slipping or parachute related mortalities?
To me this only serves as an example of how to use statistics and data analysis to create a heavily biased article targeted at an scientificly illiterate audience for them to validate their beliefs.
This is not ment as critisism of the author or anyone else, but as a critisism of pseudoscience and misrepresentation/manipulation/cherrypicking. The scientific method and the ethical principles in research are fundemental in our search for empirical knowledge and objective truths. Now more than ever.
Why show the general public all these charts and figures ? We can’t understand any of it . Or what it means or says . Someone else will dhow their charts and figures. And say theirs are the true facts . At this point in the game . The public has been told so many lies by the American government. It’s a total shame .
These charts suck they don’t account for anything.
I just do the opposite in response to government guidance...