Great analyses Ben, and thanks especially for the github repo. Wanted to mention a likely *second* Simpsons paradox situation for the "Ever vaccinated" aggregate curve. To see this, take Table 1 and plot the mortality rate curves for each of the vaccinated subgroups. Interestingly, they all quickly shoot well above the unvaccinated curve and remain there. So it appears the valleys of these subgroup curves cancel out peaks when computing the aggregated curve, and we should account for people moving from one vax subgroup to the next. As you have shown, typically in Simpson's paradox cases, it is the subgroup (stratified) curves that tell the real story.
Would speculate that if we do two-way stratification and adjustment on vax subgroup and age, then the results would clearly favor unvaccinated.
I don't know if "vaccine register dataset" is the correct term to refer to the data from the UK Coronavirus Dashboard API. I think "vaccination register" is just a synonym for NIMS. If you google for `site:coronavirus.data.gov.uk "vaccine register"`, the preview text for one of the search results features the text "VaccineRegisterPopulationByVaccinationDate: Vaccination register (NIMS)". However the text seems to have been removed from the current version of the page and I didn't find the text at Google's cache or the Wayback Machine either.
So since there seem to be different versions of the NIMS data, maybe it's not sufficient to say that you're using data from NIMS either but you have to specify which version of the NIMS data you're using.
Am I understanding this correctly that the jabs aren't causing excess deaths? What would be the cause of the people dropping dead like the athletes, news casters, etc. Is it due to having a prior covid infection?
Great analyses Ben, and thanks especially for the github repo. Wanted to mention a likely *second* Simpsons paradox situation for the "Ever vaccinated" aggregate curve. To see this, take Table 1 and plot the mortality rate curves for each of the vaccinated subgroups. Interestingly, they all quickly shoot well above the unvaccinated curve and remain there. So it appears the valleys of these subgroup curves cancel out peaks when computing the aggregated curve, and we should account for people moving from one vax subgroup to the next. As you have shown, typically in Simpson's paradox cases, it is the subgroup (stratified) curves that tell the real story.
Would speculate that if we do two-way stratification and adjustment on vax subgroup and age, then the results would clearly favor unvaccinated.
You could try this dataset to see what deaths are missing by age up to July 2022?
https://www.ons.gov.uk/peoplepopulationandcommunity/birthsdeathsandmarriages/deaths/adhocs/15018dailydeathsbydateofoccurrence1june2014to31july2022bysingleyearofageandsexengland
I don't know if "vaccine register dataset" is the correct term to refer to the data from the UK Coronavirus Dashboard API. I think "vaccination register" is just a synonym for NIMS. If you google for `site:coronavirus.data.gov.uk "vaccine register"`, the preview text for one of the search results features the text "VaccineRegisterPopulationByVaccinationDate: Vaccination register (NIMS)". However the text seems to have been removed from the current version of the page and I didn't find the text at Google's cache or the Wayback Machine either.
An article published by Public Health England says: "NHS Digital have led the development of a new national vaccination register and call/recall system for COVID-19 and influenza vaccination – the National Immunisation Management System (NIMS)." (https://assets.publishing.service.gov.uk/government/uploads/system/uploads/attachment_data/file/974300/COVID-19_vaccine_surveillance_strategy_March21.pdf)
The data in the Excel files on this page is supposed to come from NIMS: https://www.england.nhs.uk/statistics/statistical-work-areas/covid-19-vaccinations/. In the Excel files, the "Cumulative number of dose 1 vaccinations delivered" is listed as 43,559,688 in England on January 1st 2022. However if you go Coronavirus Dashboard API, you set the area type to "Nation", you set area name to England, you set the metric to "cumPeopleVaccinatedFirstDoseByPublishDate", it shows that the number of vaccinated people on January 1st 2022 was 43,516,101, which is almost the same as in the Excel file but not exactly. (You can also run `curl 'https://api.coronavirus.data.gov.uk/v2/data?areaType=nation&areaCode=E92000001&metric=cumPeopleVaccinatedFirstDoseByPublishDate&format=csv'|grep 2022-01-01`.)
So since there seem to be different versions of the NIMS data, maybe it's not sufficient to say that you're using data from NIMS either but you have to specify which version of the NIMS data you're using.
What's the definition of "unvaccinated?" Does it include the 14 days following the jab? This stupid definition has been the norm.
OMG!! Did you hear this.... Smoking Gun! UK Gov Job Posting For The Coming "Largest Mass Vaccination Program" In History
https://rumble.com/v2bsb8e-smoking-gun-uk-gov-job-posting-for-the-coming-largest-mass-vaccination-prog.html?mref=6zof&mc=dgip3&utm_source=newsletter&utm_medium=email&utm_campaign=Libertytalkcanada&ep=2
WHERE’S MY BOOK!!!!!????
The ONS data stinks to high heaven.
We shouldn't be surprised those complicit in killing people, are also prepared to lie about it.
Am I understanding this correctly that the jabs aren't causing excess deaths? What would be the cause of the people dropping dead like the athletes, news casters, etc. Is it due to having a prior covid infection?