Read on Twitter
1) Doing a little light reading... The @Pfizer Study (as well as the other Covid-19 Trials) is a disgrace.
Inject 44,000 subjects, half with placebo... they analyzed 94 “positive” cases...no consistency in behavior nor exposure...they then use PCR to “confirm” ONE symptom
Inject 44,000 subjects, half with placebo... they analyzed 94 “positive” cases...no consistency in behavior nor exposure...they then use PCR to “confirm” ONE symptom
2) (actually one of 3 PCR/rapid kits, all EUA - no validation ... the study will be complete when 164, in total are deemed positive. So this BIG NEWS is that of the 44,000 dosed, 94 have gotten ill....So, of 22,000 dosed with vaccine,
3) 9 subjects got sick and of the other 22,000 placebo subjects, 85 got sick... so of the vaccine cohort, 99.959% have no illness and 99.614% of placebo have no illness... this IS NOT how you prove efficacy!
4) (Unless Fauci is involved). Is this 90-95% efficacy or is this a shit study, showing a 0.345% difference between the vaccine and placebo. @richardursomd @drdavidsamadi @JamesTodaroMD @zev_dr @drsimonegold @dockaurG @kksheld @Thomas_Binder @DrAntoniSerraT1 @rlamartini
5) From the protocol: "Statistical Methods
The sample size for Phase 1 of the study is not based on any statistical hypothesis testing.
For Phase 2/3, the VE evaluation will be the primary objective. The VE is defined as
The sample size for Phase 1 of the study is not based on any statistical hypothesis testing.
For Phase 2/3, the VE evaluation will be the primary objective. The VE is defined as
6) VE = 100 × (1 – IRR), where IRR is calculated as the ratio of the first confirmed COVID-19 illness rate in the vaccine group to the corresponding illness rate in the placebo group. With assumptions of a true VE of 60% and 4 IAs planned,
7) 164 COVID-19 cases will provide 90% power to conclude true VE >30%. This would be achieved with a total 43,998 participants (21,999 vaccine recipients), based on the assumption of a 1.3% per year incidence in the placebo group,
8) accrual of 164 primary-endpoint cases within 6 months, and 20% of the participants being nonevaluable. If the attack rate is much higher, case accrual would be expected to be more rapid, enabling the study’s primary endpoint to be evaluated much sooner.
9) The total number of participants enrolled in Phase 2/3 may vary depending on the incidence of COVID-19 at the time of the enrollment, the true underlying VE, and a potential early stop for efficacy or futility.
10) VE will be evaluated using a beta-binomial model and the posterior probability of VE being >30% will be assessed.
In Phase 3, up to approximately 2000". These assumptions are asinine.
In Phase 3, up to approximately 2000". These assumptions are asinine.
