I describe a novel ratio analysis technique that is totally objective. If the vaccines are killing people in close proximity to the shot, this analysis can detect even small shifts.

Obviously, the more data points the more robust could be our conclusions. We need to get Dr. Ladapo to do this in Florida, to decrease the chance of confounding.

The only argument could be that the vaccinated deaths occurred in a later time period, on average, versus the unvaccinated, and that some other factor could cause deaths to rise as we move through the 730 day period. An argument could be made that something like “long covid” has an increasing lethality over time? A reach, I know, just playing Devil’s Advocate.

1) No anecdotes about vax success, but MANY about vax injury and death.

2) No anti-vaxxers that convert to vaxxers, but many that have transitioned the other way.

3) This simple 3-input model that shows life shortening consequences of jabs.

Below is the email/letter that I wrote to Ohio Governor Mike DeWine challenging him to have his Director of Public Health take this "Steve Kirsch Challenge." I referenced Steve's first Substack article on this a couple of days ago. - Tom Haviland

Governor DeWine,

You can become a HERO to our country and the world by taking the steps outlined in Steve Kirsch's Substack article below!

Sir, here is your opportunity to "get on the correct side" of this issue that not only are the COVID-19 "vaccines" ineffective in stopping anyone from catching or transmitting the virus, they are also killing and injuring millions of people around the world.

Please instruct your Director of the Ohio Department of Health, Dr. Bruce Vanderhoff, to provide the death records and COVID vaccination records for all deceased Ohioans for the years 2021 and 2022 to include: 1) Age at time of death, 2) Date of death, and 3) Date of last COVID vaccination.

That data, once compiled, will indicate one of three results:

Result 1. There is no correlation at all between date of last vaccination and date of death, or

Result 2. Recently vaccinated Ohioans enjoy safe and strong protection from the vaccines, or

Result 3. Recently vaccinated Ohioans are dying shortly after getting the vaccines.

Governor DeWine, it is my guess that you believe such an examination of the death records and COVID vaccination records will yield "Result 2."

It is Steve Kirsch's and my belief that such an examination of the death records and COVID vaccination records will most certainly yield "Result 3."

Let's find out who is correct.

Please instruct Dr. Bruce Vanderhoff to conduct this data compilation and make it available to the public for inspection. Or you can have the Ohio Department of Health provide the death records and COVID vaccination records of these deceased Ohioans to me, and I will be glad to perform the data compilation task that will yield either Result 1, Result 2, or Result 3 as described above.

Governor DeWine, Ohioans deserve to know if the COVID vaccines are actually "saving" Ohioans or "killing" Ohioans.

Here is a chance to cement your legacy as the only governor of 50 states that had "the guts" to search for the truth about the vaccines.

You can become a HERO to our country and the world.

Wow, Steve. When you’ve authored more than a thousand evidence-packed articles, I’m going to pay special attention when you say, “this is the most important article I have ever written in my life.”

I want to thank you for permitting me to publish the long version of your op-ed before you submit the short version and wanted to let you know people are finding it incredibly valuable and are planning to use it in their own fights against mandates:

Hi. I’ve collected thousands of Covid-19 vaccine injuries, deaths, and “died suddenly” video footage from security cameras.

I’m sharing everything on my Rumble channel found at VaxGenocide.com

(I’m featured in the Died Suddenly movie credits. I’m Covid BC.)

You won’t find this type of footage anywhere else. I have so many videos to upload… I am exhausted. Lots of really graphic videos of kids passing away so please view with caution.

This "analysis technique" is so apparently flawed! Just try it against ANY most harmless intervention that exhibits similar dynamics as jabbing, and you will get the same circa 0.3 result.

There should be a relation between the Ratio value obtained from the same data set when analysed by method 1 to get R1 (fixed window T= T1-T2 all data points) and method 2, which gives R2 by setting the vaccination date as the time origin but keeping the same T2 end point. I believe the relation is

R2/R1 = 2/3

by the following argument: Consider a particular death date tdi . In method 1 this contributes tdi/T to the ratio taking T1 as 0 for our time measurements. On average the time from vaccination to tdi will be ti = tdi/2 if the vaccination and death are not correlated. On average the time from vaccine to T2 will then be tpi = T -tdi/2. The ratio of method 2 replaces the tdi/T with on average ti/tpi so we find R2 = R1/2(1-R1/2) and for R1 =1/2 (the random death case equally probable across the fixed window) R2 = 1/3. So R2/R1 = 2/3. When the same data are just recalculated as you have done.

Interestingly for the age group 0-20 your data do show R2/R1=0.4/0.6= 2/3. The older groups have R2/R1< 2/3 when the same data are replotted.

Analysis of the ONS data for the UK ap2021 to nov2022 for different age groups and for noncovid deaths shows that the % vaccinated among the dead of the age group is always less than the % vaccinated in the age group, except in the oldest group 70-90 where it was slightly higher. Both these observations are arguments against there being statistically significant numbers of deaths caused by the vaccines.

Your Method is good, your data are good, your data tables are good so good job so far BUT the threshold criterion you use for R to indicate harm is wrong in the context of the data. Consequently, your conclusions are not valid deductions from your data!

In fact, your data actually show the vaccine is not causing harm! Let me explain:

You apply your “Ratio test” in two different ways to the data:

1) a fixed time window is defined T1-T2( eg Jan21 to dec22). All the individual deaths in a data set which occur in that window are selected. Each death date, tdi, splits the window into two parts, before tbi= tdi-T1 and after tai=T2-tdi. The ratio is defined as R=< tbi>/<T2-T1>. Which is 0.5 if there is no “bunching of the deaths” in the window. i.e if there is a constant probability of dying across the whole window, (the death rate is uniform).

2) For the vaxxd alone you make the date of vaccination the start point of the window T1=tvi, but the end point of the window is the same as before T2, so now every death has tbi= tdi – tvi = ti and T2- tvi = tpi so now R is defined as R =< ti>/<tpi>. This statistic is not always 0.5 even when the probability of vaccination and the probability of death are independent (i.e. the no harm from vaccine case). If the all death rate is falling, R can be reduced considerably; if it is rising, R increases above 0.5 for the no harm hypothesis. The UK ONS data (march 2023) for the overall death rates and vaccine rollout show across the period april21 to nov22 the death rate was falling, with small rises due to the covid waves which were maximum at dec2021-jan22. The vaccine rollout rate was not uniform, but for the 18-39 group was almost bell shaped centred at Jul 2021. Using these data to get Pv(t), Pd(t), prob of vaccination , and of death during the period, we can ask: “If the vaccine rates and death rates observed for the 18-39 group were independent what would the R=<ti>/<tpi> value be?” (This is a standard problem using joint probability distributions). A calculation using the ONS data for Pv and Pd gives R=0.370 not 0.500. This is the criterion for whether the vaccine rate is correlated to the death rate. If R< 0.370 then it is possible the vaccine is causing harm, if R>0.370 the vaccine is possibly delaying death.

Your data support the hypothesis that the vaccine is not causing harm since R > 0.400 for the vaccinated in all cases using method 2. All the data you present in your tables indicate when you apply method 1 (fixed window) for all the data the ratio is always R>0.500. Only when you extract the vaccinated and use method 2 do you find all those data give ratios 0.5>R> 0.4 Which actually supports the hypothesis that the vaccine rate and death rate are independent, if the US data is anything like the UK’s data. Your data further support this conclusion:

A comparison of the Method 1 Ratios for the Vaxxd and the unvaxxd in the window jan21 to dec 22 can be made from your data. For each age group above 30 the ratio for the vaxxed is always higher than for the unvaxxed and above 0.5, while the unvaxxed ratio falls below 0.5 but remains above 0.4. This is compatible with the vaccine not killing people but actually saving lives.

The two groups where the ratio for the vaxxd is below the unvaxxd are 0-30 and these are the least reliable results because the number of deaths in these groups in your data set is so small compared to the other age groups.

If I understand your method correctly the ith death record in the data set from time period 0-T where 0=jan 2021, T= jan2023, records the vaccination time tvi and death time tdi giving an interval ti=tdi-tvi and a period tpi= T-tvi . Your ratio statistic, R, is then the ratio of the means <ti>/ <tpi> of the whole data set which is 0.5 if the all causes death rate remains constant between 0-T and if the vaccination rate and the death rate are not correlated. You then calculate R for your data set and find it less than 0.5 and deduce the vaccine rate and the death rate are correlated. You then assume correlation is causation: that is a basic statistical mistake. But that is not my main concern with your method, which is when the death rate is not constant through 0-T , as it was not during the epidemic smaller values of R than 0.5 are consistent with no correlation between the vaccination rate and the death rate. For example the ONS mortality figures for 18-39 yr olds allow us to deduce the all causes death rate from april 2021 to nov 2022. Vaccine rollout data for this age group give the vaccination rate across this period. Using this data we can calculate the expected R value under the assumption of no correlation between them and the value obtained is 0.411, this is because the all cause death rate was falling across this time period except for increase as the covid wave swept through. The vaccination rate is far from uniform during the period in fact it is more like a bell curve centered at june 2021. These combine to lower the R value threshold which applies to non correlation.

A better statistic to test for excess vaccine induced death is to compare the % vaxxd among the noncovid dead and compare that to the % of the group who are vaxxed

If the vaccines were causing harms, would'nt it show in death rates for the "non covid dead" when the ever vaxxd were compared to the never vaxxd. These rates were the same in all the age groups from 18-60 in the period aug 2021 to nov 2022 in the ONS mortality figures (see my plots on substack) suggesting the vaccine did not cause harm. Also they should show in the % vaxxd among the noncovid dead being higher than the %vaxxd in the population. This is never the case in the 18-60 age groups. I have plotted all the ONS data mortality numbers, rates, % vaxxed among the dead from covid, all deaths and noncovid deaths here for reference: https://nickcanning.substack.com/p/analysis-of-the-ons-monthly-covid

"We are now over two years into the vaccination program and not only is nobody publishing the data that would prove or not that the vaccines are safe, but nobody is even asking for the data to be published.

It’s almost as if nobody wants to know the truth. That’s the big take away."

This is genius in its elegant simplicity.

Obviously, the more data points the more robust could be our conclusions. We need to get Dr. Ladapo to do this in Florida, to decrease the chance of confounding.

The only argument could be that the vaccinated deaths occurred in a later time period, on average, versus the unvaccinated, and that some other factor could cause deaths to rise as we move through the 730 day period. An argument could be made that something like “long covid” has an increasing lethality over time? A reach, I know, just playing Devil’s Advocate.

1) No anecdotes about vax success, but MANY about vax injury and death.

2) No anti-vaxxers that convert to vaxxers, but many that have transitioned the other way.

3) This simple 3-input model that shows life shortening consequences of jabs.

A hat trick for the home team!

Below is the email/letter that I wrote to Ohio Governor Mike DeWine challenging him to have his Director of Public Health take this "Steve Kirsch Challenge." I referenced Steve's first Substack article on this a couple of days ago. - Tom Haviland

Governor DeWine,

You can become a HERO to our country and the world by taking the steps outlined in Steve Kirsch's Substack article below!

Sir, here is your opportunity to "get on the correct side" of this issue that not only are the COVID-19 "vaccines" ineffective in stopping anyone from catching or transmitting the virus, they are also killing and injuring millions of people around the world.

Please instruct your Director of the Ohio Department of Health, Dr. Bruce Vanderhoff, to provide the death records and COVID vaccination records for all deceased Ohioans for the years 2021 and 2022 to include: 1) Age at time of death, 2) Date of death, and 3) Date of last COVID vaccination.

That data, once compiled, will indicate one of three results:

Result 1. There is no correlation at all between date of last vaccination and date of death, or

Result 2. Recently vaccinated Ohioans enjoy safe and strong protection from the vaccines, or

Result 3. Recently vaccinated Ohioans are dying shortly after getting the vaccines.

Governor DeWine, it is my guess that you believe such an examination of the death records and COVID vaccination records will yield "Result 2."

It is Steve Kirsch's and my belief that such an examination of the death records and COVID vaccination records will most certainly yield "Result 3."

Let's find out who is correct.

Please instruct Dr. Bruce Vanderhoff to conduct this data compilation and make it available to the public for inspection. Or you can have the Ohio Department of Health provide the death records and COVID vaccination records of these deceased Ohioans to me, and I will be glad to perform the data compilation task that will yield either Result 1, Result 2, or Result 3 as described above.

Governor DeWine, Ohioans deserve to know if the COVID vaccines are actually "saving" Ohioans or "killing" Ohioans.

Here is a chance to cement your legacy as the only governor of 50 states that had "the guts" to search for the truth about the vaccines.

You can become a HERO to our country and the world.

Sincerely,

Thomas F. Haviland

3873 Maple Grove Lane

Beavercreek, OH 45440

thomashaviland@sbcglobal.net

Phone: 937-431-0801

Wow, Steve. When you’ve authored more than a thousand evidence-packed articles, I’m going to pay special attention when you say, “this is the most important article I have ever written in my life.”

I want to thank you for permitting me to publish the long version of your op-ed before you submit the short version and wanted to let you know people are finding it incredibly valuable and are planning to use it in their own fights against mandates:

• “Letter to the Stanford Daily” (https://margaretannaalice.substack.com/p/letter-to-the-stanford-daily)

It was a joy collaborating with you, and I look forward to seeing the final version in the Stanford Daily.

Hi. I’ve collected thousands of Covid-19 vaccine injuries, deaths, and “died suddenly” video footage from security cameras.

I’m sharing everything on my Rumble channel found at VaxGenocide.com

(I’m featured in the Died Suddenly movie credits. I’m Covid BC.)

You won’t find this type of footage anywhere else. I have so many videos to upload… I am exhausted. Lots of really graphic videos of kids passing away so please view with caution.

Please share this link with everyone you know.

This "analysis technique" is so apparently flawed! Just try it against ANY most harmless intervention that exhibits similar dynamics as jabbing, and you will get the same circa 0.3 result.

There should be a relation between the Ratio value obtained from the same data set when analysed by method 1 to get R1 (fixed window T= T1-T2 all data points) and method 2, which gives R2 by setting the vaccination date as the time origin but keeping the same T2 end point. I believe the relation is

R2/R1 = 2/3

by the following argument: Consider a particular death date tdi . In method 1 this contributes tdi/T to the ratio taking T1 as 0 for our time measurements. On average the time from vaccination to tdi will be ti = tdi/2 if the vaccination and death are not correlated. On average the time from vaccine to T2 will then be tpi = T -tdi/2. The ratio of method 2 replaces the tdi/T with on average ti/tpi so we find R2 = R1/2(1-R1/2) and for R1 =1/2 (the random death case equally probable across the fixed window) R2 = 1/3. So R2/R1 = 2/3. When the same data are just recalculated as you have done.

Interestingly for the age group 0-20 your data do show R2/R1=0.4/0.6= 2/3. The older groups have R2/R1< 2/3 when the same data are replotted.

Analysis of the ONS data for the UK ap2021 to nov2022 for different age groups and for noncovid deaths shows that the % vaccinated among the dead of the age group is always less than the % vaccinated in the age group, except in the oldest group 70-90 where it was slightly higher. Both these observations are arguments against there being statistically significant numbers of deaths caused by the vaccines.

Your Method is good, your data are good, your data tables are good so good job so far BUT the threshold criterion you use for R to indicate harm is wrong in the context of the data. Consequently, your conclusions are not valid deductions from your data!

In fact, your data actually show the vaccine is not causing harm! Let me explain:

You apply your “Ratio test” in two different ways to the data:

1) a fixed time window is defined T1-T2( eg Jan21 to dec22). All the individual deaths in a data set which occur in that window are selected. Each death date, tdi, splits the window into two parts, before tbi= tdi-T1 and after tai=T2-tdi. The ratio is defined as R=< tbi>/<T2-T1>. Which is 0.5 if there is no “bunching of the deaths” in the window. i.e if there is a constant probability of dying across the whole window, (the death rate is uniform).

2) For the vaxxd alone you make the date of vaccination the start point of the window T1=tvi, but the end point of the window is the same as before T2, so now every death has tbi= tdi – tvi = ti and T2- tvi = tpi so now R is defined as R =< ti>/<tpi>. This statistic is not always 0.5 even when the probability of vaccination and the probability of death are independent (i.e. the no harm from vaccine case). If the all death rate is falling, R can be reduced considerably; if it is rising, R increases above 0.5 for the no harm hypothesis. The UK ONS data (march 2023) for the overall death rates and vaccine rollout show across the period april21 to nov22 the death rate was falling, with small rises due to the covid waves which were maximum at dec2021-jan22. The vaccine rollout rate was not uniform, but for the 18-39 group was almost bell shaped centred at Jul 2021. Using these data to get Pv(t), Pd(t), prob of vaccination , and of death during the period, we can ask: “If the vaccine rates and death rates observed for the 18-39 group were independent what would the R=<ti>/<tpi> value be?” (This is a standard problem using joint probability distributions). A calculation using the ONS data for Pv and Pd gives R=0.370 not 0.500. This is the criterion for whether the vaccine rate is correlated to the death rate. If R< 0.370 then it is possible the vaccine is causing harm, if R>0.370 the vaccine is possibly delaying death.

Your data support the hypothesis that the vaccine is not causing harm since R > 0.400 for the vaccinated in all cases using method 2. All the data you present in your tables indicate when you apply method 1 (fixed window) for all the data the ratio is always R>0.500. Only when you extract the vaccinated and use method 2 do you find all those data give ratios 0.5>R> 0.4 Which actually supports the hypothesis that the vaccine rate and death rate are independent, if the US data is anything like the UK’s data. Your data further support this conclusion:

A comparison of the Method 1 Ratios for the Vaxxd and the unvaxxd in the window jan21 to dec 22 can be made from your data. For each age group above 30 the ratio for the vaxxed is always higher than for the unvaxxed and above 0.5, while the unvaxxed ratio falls below 0.5 but remains above 0.4. This is compatible with the vaccine not killing people but actually saving lives.

The two groups where the ratio for the vaxxd is below the unvaxxd are 0-30 and these are the least reliable results because the number of deaths in these groups in your data set is so small compared to the other age groups.

If I understand your method correctly the ith death record in the data set from time period 0-T where 0=jan 2021, T= jan2023, records the vaccination time tvi and death time tdi giving an interval ti=tdi-tvi and a period tpi= T-tvi . Your ratio statistic, R, is then the ratio of the means <ti>/ <tpi> of the whole data set which is 0.5 if the all causes death rate remains constant between 0-T and if the vaccination rate and the death rate are not correlated. You then calculate R for your data set and find it less than 0.5 and deduce the vaccine rate and the death rate are correlated. You then assume correlation is causation: that is a basic statistical mistake. But that is not my main concern with your method, which is when the death rate is not constant through 0-T , as it was not during the epidemic smaller values of R than 0.5 are consistent with no correlation between the vaccination rate and the death rate. For example the ONS mortality figures for 18-39 yr olds allow us to deduce the all causes death rate from april 2021 to nov 2022. Vaccine rollout data for this age group give the vaccination rate across this period. Using this data we can calculate the expected R value under the assumption of no correlation between them and the value obtained is 0.411, this is because the all cause death rate was falling across this time period except for increase as the covid wave swept through. The vaccination rate is far from uniform during the period in fact it is more like a bell curve centered at june 2021. These combine to lower the R value threshold which applies to non correlation.

A better statistic to test for excess vaccine induced death is to compare the % vaxxd among the noncovid dead and compare that to the % of the group who are vaxxed

If the vaccines were causing harms, would'nt it show in death rates for the "non covid dead" when the ever vaxxd were compared to the never vaxxd. These rates were the same in all the age groups from 18-60 in the period aug 2021 to nov 2022 in the ONS mortality figures (see my plots on substack) suggesting the vaccine did not cause harm. Also they should show in the % vaxxd among the noncovid dead being higher than the %vaxxd in the population. This is never the case in the 18-60 age groups. I have plotted all the ONS data mortality numbers, rates, % vaxxed among the dead from covid, all deaths and noncovid deaths here for reference: https://nickcanning.substack.com/p/analysis-of-the-ons-monthly-covid

"We are now over two years into the vaccination program and not only is nobody publishing the data that would prove or not that the vaccines are safe, but nobody is even asking for the data to be published.

It’s almost as if nobody wants to know the truth. That’s the big take away."

America, ... " ... home of the brave."

The question ❓ is why do they want to hide all the data on this vaXX? Why are they letting people die off?

The reasons are simple.

1. 65+, can't pay out social security or pensions

2.

3.

Take a gues-Fill in #2, #3.

Artcles like this make me sad because they are CAP

He is stinky and is wrong

This guy is bull shit and has a small pp

This artcile sucks and is fake