« The worst kept secret will be revealed today | Main | One-dose Pfizer is not happening and here's why »

Comments

Feed You can follow this conversation by subscribing to the comment feed for this post.

MVE

Wow, so this reads as asserting here zero correlation between general human population and those matching 1+ of the list. That seems like the wrong prior.

Kaiser

MVE: That's certainly not what I intended so thanks for pointing this out. People who meet any of these criteria should consult their doctor before taking the vaccine. My prior is that the scientists at Pfizer believe there could be complications and that's why these subgroups were excluded. Because of the exclusion, we did not learn anything specific about these subgroups during the trial.

I think your argument is that the trial data should move the prior towards accepting the vaccine in aggregate and for any subgroup - I might be persuaded on the efficacy front but not on the safety front, because I'm concerned about the small sample size for any subgroup.

Nevertheless, for certain subgroups, such as pregnant women, we have an embedded natural experiment (though small) since some women in each group will have become pregnant by accident during the trial. So if we wait longer, there will be more data.
The FDA may have specific recommendations for certain excluded subgroups. That's why consulting with the doctor is the way to go.

The comments to this entry are closed.

Get new posts by email:
Kaiser Fung. Business analytics and data visualization expert. Author and Speaker.
Visit my website. Follow my Twitter. See my articles at Daily Beast, 538, HBR, Wired.

See my Youtube and Flickr.

Search3

  • only in Big Data
Numbers Rule Your World:
Amazon - Barnes&Noble

Numbersense:
Amazon - Barnes&Noble

Junk Charts Blog



Link to junkcharts

Graphics design by Amanda Lee

Community