What i do see are many vaxxed people just shrugged their shoulders non-chalantly, because they can only and will only relate to themselves not having problems or side effects from the jab and in the process had to accept their own safety as scientific proof that this illness does not exist. Assuming their body not being affected as the one and only sign of pure science. Almost as if the human empathy and sympathy just vanished into thin air. Many are just look the other way.
Just had this thought that I’ll share in comments on all the SUBSTACKS I subscribe to…
Howzabout a daytime rally of the jab-injured in baseball/football stadiums across the nation. There are enough ambulatory jab-injured in the various cities to fill the stadiums, and they need visibility and a voice. A millionaire or 2 (perhaps jab-injured themselves) would be needed for the rentals, or perhaps a crowd-sourcing campaign.
I think you made it much more complex than it really is. Your mathematical approach though very simple can be simplified using all cause mortality on a yearly basis. This eliminates the sinusoidal wave of months and averaging multiple years also straightens the graph.
We can then see that all cause mortality across the whole as showing a substantial increase from 2020 to now versus 2017-2019.
Yes it would be great to see actual deaths, ages etc and compare them to when the vax was rolled out. But the powers that be don’t want laymen like us to see the correlation.
In order to calculate the seasonality-adjusted trend, I first take a 15-day moving average of the daily data. I then do linear regression to fit a line to the data for 2015-2019. Then for each 366 days of the year, I calculate the difference from the linear trend during the prediction interval in 2015-2019, and I then add the difference to the linear trend for the corresponding day of each subsequent year. So for example in the age group 30-39 on September 26th, when using the 15-day moving average, the average number of deaths in 2015-2019 was about 0.54 higher than the linear trend, so I add about 0.54 to the linear trend on September 26th for each subsequent year.
I think my method produces a more accurate estimate of seasonal variation in mortality than the method of fitting a sine wave that you used earlier, because the waveform of seasonal variation in mortality doesn't look anything like a sine wave in most countries: https://i.ibb.co/wzsvzZT/1.png (R code: https://pastebin.com/raw/2psmRf40).
Thanks for detailing the methodology. I had trouble understanding the Step 5: "fit a polynomial to the cumulative data. Again, in the absence of cohort depletion, this curve is expected to be exponential if the weekly data fit is linear." Could you expand on this step?
Also question on whether you think it helps to also adjust for the population in each age band? Or that sort of comes out in the excess calculation anyway.
Your first three steps provide a consistent view of the underlying data. After that, I believe that what we care about is the shape of the waves in the data ... when was the peak of the wave and what was the excess mortality during the wave. I think that plotting rolling averages of a period of a few weeks would locate the peaks and valleys.
Joel, can you take a look at excess deaths in Scottish infants <1yo before and after COVID vax ? (Vax start 'at risk' 6mon-4yo May 29th-2023) https://ibb.co/KmDTMD9
I calculate a very noteable 30% increase in mortality post jab.
What i do see are many vaxxed people just shrugged their shoulders non-chalantly, because they can only and will only relate to themselves not having problems or side effects from the jab and in the process had to accept their own safety as scientific proof that this illness does not exist. Assuming their body not being affected as the one and only sign of pure science. Almost as if the human empathy and sympathy just vanished into thin air. Many are just look the other way.
Every death certificate should be released
Just had this thought that I’ll share in comments on all the SUBSTACKS I subscribe to…
Howzabout a daytime rally of the jab-injured in baseball/football stadiums across the nation. There are enough ambulatory jab-injured in the various cities to fill the stadiums, and they need visibility and a voice. A millionaire or 2 (perhaps jab-injured themselves) would be needed for the rentals, or perhaps a crowd-sourcing campaign.
Joel
I think you made it much more complex than it really is. Your mathematical approach though very simple can be simplified using all cause mortality on a yearly basis. This eliminates the sinusoidal wave of months and averaging multiple years also straightens the graph.
We can then see that all cause mortality across the whole as showing a substantial increase from 2020 to now versus 2017-2019.
Yes it would be great to see actual deaths, ages etc and compare them to when the vax was rolled out. But the powers that be don’t want laymen like us to see the correlation.
Thanks for your reporting
I posted R code here for calculating seasonality-adjusted excess mortality in the same dataset for daily deaths in England and Wales: https://mongol-fi.github.io/stat.html#Make_a_heatmap_of_weekly_excess_mortality_percentage_by_age_group.
In order to calculate the seasonality-adjusted trend, I first take a 15-day moving average of the daily data. I then do linear regression to fit a line to the data for 2015-2019. Then for each 366 days of the year, I calculate the difference from the linear trend during the prediction interval in 2015-2019, and I then add the difference to the linear trend for the corresponding day of each subsequent year. So for example in the age group 30-39 on September 26th, when using the 15-day moving average, the average number of deaths in 2015-2019 was about 0.54 higher than the linear trend, so I add about 0.54 to the linear trend on September 26th for each subsequent year.
I think my method produces a more accurate estimate of seasonal variation in mortality than the method of fitting a sine wave that you used earlier, because the waveform of seasonal variation in mortality doesn't look anything like a sine wave in most countries: https://i.ibb.co/wzsvzZT/1.png (R code: https://pastebin.com/raw/2psmRf40).
Figure 2 (Mar 20) - See, the choking bronchial spasms could have killed me; apparently did kill some.
Thanks for detailing the methodology. I had trouble understanding the Step 5: "fit a polynomial to the cumulative data. Again, in the absence of cohort depletion, this curve is expected to be exponential if the weekly data fit is linear." Could you expand on this step?
Also question on whether you think it helps to also adjust for the population in each age band? Or that sort of comes out in the excess calculation anyway.
And great insights on the age structure.
Your first three steps provide a consistent view of the underlying data. After that, I believe that what we care about is the shape of the waves in the data ... when was the peak of the wave and what was the excess mortality during the wave. I think that plotting rolling averages of a period of a few weeks would locate the peaks and valleys.
Joel, can you take a look at excess deaths in Scottish infants <1yo before and after COVID vax ? (Vax start 'at risk' 6mon-4yo May 29th-2023) https://ibb.co/KmDTMD9
I calculate a very noteable 30% increase in mortality post jab.
Can you graph this out ?
cheers