Lucy Letby: Guilty or Innocent - a Bayesian analysis
Mathematician Richard Gill (a colleague and friend) put out a tweet with a number of assumptions abou the case of Lucy Letby (the UK nurse convicted in 2023 of multiple baby murders), using a Bayesian analysis to conclude that a sepsis outbreak was much more likely to have been the cause of the baby deaths than Lucy. He claimed that, with his assumptions the posterior odds of sepsis outbreak rather than Lucy being the killer was about 4000:1. Using a simply Bayesian network I show that the posterior odds are more like 166:1 (if I have understood Richard's assumptions). Of course the critical assumptions Richard makes (which were not accepted during the trial) are that a) there was little evidence of malicious harm to the babies; and b) there was much evidence of a sepsis outbreak. Whether or not these assumptions are reasonable this is nevertheless a nice example of a Bayesian network in action ... https://www.youtube.com/watch?v=KVkXBIbkUWM
NOTE error at end of conclusions: should say "proportion of unvaccinated underestimated" - not vaccinated. In this lecture I talk about our ongoing analysis of the latest data published by the Office for Nat Statistics on mortality by vaccine status. The reason this data is incredibly important is because it potentially provides us with the simplest and most objective way to determine the overall risk-benefit of the Covid vaccines, namely the comparison of all-cause mortality between the vaccinated and unvaccinated.
What I will show you is that there are so many inconsistencies and missing information in the data – as is the case for most studies into covid vaccine effectiveness - that few conclusions can be drawn other than that it provides no real evidence that the benefits outweigh the risks.
But before I present these results I provide some background and context for thw work we have been doing on Covid stats
...
https://www.youtube.com/watch?v=6umArFc-fdc
Is attending the cinema deadly?
Or, to express the question statistically, does more frequent attendance increase or decrease mortality?
This sounds like a crazy question because intuitively we know that cinema visits have no impact on your health. But imagine that a study has been done that collected data on people who had died after visiting the cinema and concluded that attending the cinema contributed to an increase in mortality. Should you believe this conclusion?
I show using graphical illustrations that there are two different types of survivor bias which, by suitable manipulation of the statistics, can be used to show both increases or decreases in mortality rates the more cinema visits that are made. If we simply replace ‘cinema visits’ with ‘vaccine doses’ then it is clear that we can create - for a placebo vaccine - exactly the same statistical illusions of either increased safety, the more doses you take, or decreased safety, the more doses you take.
See https://wherearethenumbers.substack.com/p/survivor-bias-cuts-both-ways-and
...
https://www.youtube.com/watch?v=_LtmHS0QQws
This is an excerpt from an interview I did on Bret Weinstein's Dark Horse podcast in 2020 where we talk about the failures of academia during covid and Bret likens academia to a rabid dog that needs to be put down. I am posting this now because the insanity in academia has got to a point where it really cannot be saved. See e.g. this
https://x.com/mihaschw/status/1799107911844819442 and this
https://x.com/profnfenton/status/1799097337773437108
just from today as examples (respectively) of student and staff insanity
...
https://www.youtube.com/watch?v=QuhK5bU9gHQ
(This version fixes errors in previous version =3rd time lucky! But there is still an error at timestamp 4:00 which read as follows: "9 out of 90 (NOT 9 out of 10) of the previously uninfected from the no vaccine group could have been infected in weeks 3 to 4".
In determining the efficacy of a medical intervention (such as a drug or vaccine) to stop a particular disease or virus it is typical to assume that the treatment needs time to work before a person is classified as 'treated'. For example, a person vaccinated against a virus may be classified as 'unvaccinated' until 2 weeks after getting the vaccination. This simple animation with a hypothetical example shows that, with such a classification, a placebo (i.e. no effect) vaccination can be shown to be highly effective.
See also this article for more context https://www.normanfenton.com/post/more-on-the-illusions-of-vaccine-efficacy and note that this applies to observational studies rather than randomized controlled trials
...
https://www.youtube.com/watch?v=WveCXtr3zVM
Based on sampling examples of different materials and observing the number that are faulty, this simple Bayesian network model determines the probability that one type of material is more faulty than the other.
...
https://www.youtube.com/watch?v=Mj6UgiIxCm4
I caught up with the brilliant Kathy Gyngell on the Mark Steyn cruise on 13 July 2023.
Kathy runs the important website: https://www.conservativewoman.co.uk/
See also: https://wherearethenumbers.substack.com/p/mark-steyn-a-tribute
Note: These videos are NOT monetized.
...
https://www.youtube.com/watch?v=h56DeIf0m6I
While this video provides updated information about a follow-up FOI the first part is an excerpt from full https://youtu.be/Dk7HCcmsMiA which should be watched to understand the full context
...
https://www.youtube.com/watch?v=0ZJi9TDf5FQ
This is a clip from an interview I did on 14 Feb 2024 with David Scott for his “Necessarily So” podcast (the full interview is here: https://youtu.be/6Urgh8asMKk). In this clip I answered David’s question about the agenda that was driving many academics’ work toward authoritarian type control. I spoke about how my experience of presenting the BBC Documentary “Climate Change by Numbers” led me to understand the extent to which climate scientists ‘lie for the greater good’ and that the use of easily manipulated data and overly complex mathematical models was common to both climate change alarmism and covid alarmism.
...
https://www.youtube.com/watch?v=t8NDlNdKqnM