I did. Causal analytics is kind of a hobby of mine, which started while working in a High Tech company. I have a couple of papers published. And I'm thinking about a startup using a specific propriatory method used on Information Theory. Still a couple of theoretical problems have to be resolved, but the results thusfar are pretty amazin…
I did. Causal analytics is kind of a hobby of mine, which started while working in a High Tech company. I have a couple of papers published. And I'm thinking about a startup using a specific propriatory method used on Information Theory. Still a couple of theoretical problems have to be resolved, but the results thusfar are pretty amazing. For more information, please pop me an email. I'm very hesitant to use my own name, as TPTB have a proven track record of destroying everything of value.
Edit: ahh, I noticed that no private messages can be send. Well, hopefully in a couple of months our free causal analytics service will be available. Your data driven substack will give ample opportunity to post some of it's results.
I remember this post and wonder if it is quasi-prophetic. We are now essentially hitting the 5 month mark on the bivalent jabs from sept and oct 2022. Seems like it is kicking in now.
Holden did a correlation check. He found a negative correlation. However, his methodology was incomplete. I used this approach to show him that one has to apply time shifts. The figure I refer to is the correlation coefficient versus the time delay based on my approach.
For a time delay of zero, the negative correlation was found that Holden referred to. However, the correlation coefficient was maximized for a 5 months delay.
This was merely an exercise to show Holden how to perform this type of analysis and not to jump to hasty conclusions.
I used the second dose. For all doses, a positive correlation coefficient is found for certain time shifts. However, because monthly data was used, the significance of the correlation coefficient for the boosters was not sufficiently high enough. As indicated, I would have preferred weekly data, plus a different method. Unfortunately I do not have a lot of time.
I did. Causal analytics is kind of a hobby of mine, which started while working in a High Tech company. I have a couple of papers published. And I'm thinking about a startup using a specific propriatory method used on Information Theory. Still a couple of theoretical problems have to be resolved, but the results thusfar are pretty amazing. For more information, please pop me an email. I'm very hesitant to use my own name, as TPTB have a proven track record of destroying everything of value.
Edit: ahh, I noticed that no private messages can be send. Well, hopefully in a couple of months our free causal analytics service will be available. Your data driven substack will give ample opportunity to post some of it's results.
Nice work. You referred To a figure from I think it was Holden. Did he find the same 5 month delay?
I remember this post and wonder if it is quasi-prophetic. We are now essentially hitting the 5 month mark on the bivalent jabs from sept and oct 2022. Seems like it is kicking in now.
Holden did a correlation check. He found a negative correlation. However, his methodology was incomplete. I used this approach to show him that one has to apply time shifts. The figure I refer to is the correlation coefficient versus the time delay based on my approach.
For a time delay of zero, the negative correlation was found that Holden referred to. However, the correlation coefficient was maximized for a 5 months delay.
This was merely an exercise to show Holden how to perform this type of analysis and not to jump to hasty conclusions.
All are using the time of the 2nd dose right? So there would be a negative time shift if a person dies after 1st dose, but before 2nd?
I used the second dose. For all doses, a positive correlation coefficient is found for certain time shifts. However, because monthly data was used, the significance of the correlation coefficient for the boosters was not sufficiently high enough. As indicated, I would have preferred weekly data, plus a different method. Unfortunately I do not have a lot of time.
Thank you!