Thursday, April 23, 2020

Maybe Stanford doesn't understand the meaning of random.

Feud over Stanford coronavirus study: ‘The authors owe us all an apology’.

"Researchers are engaged in a fierce debate over the startling estimates in a Stanford study that suggested as many as 81,000 people could already have been infected with coronavirus in Santa Clara County, with some of the world’s top number crunchers calling the study sloppy, biased and an example of “how NOT to do statistics.”"

I talked about this a couple of days ago. But I had forgotten all the local media had publicized the antibody test. That's how we found out.

If they had one in the burbs, Mr S. would have had the test.

Now, it could be true there is more exposure than we know. But the first people that are going to get the test are more likely to be positive because they have exposure in some way.



HT @yellingatwind

4 comments:

  1. Capital of Texas RefugeeThursday, April 23, 2020 6:15:00 PM

    COOF COOF selection bias COOF COOF

    WHEEEEEEZE self-selecting groups WHEEEEEEZE

    Told you, this is "science" at its best! :-)

    ReplyDelete
  2. Tex,

    It's ON!

    https://daily.jstor.org/wp-content/uploads/2019/07/what_we_mean_by_better_living_alt_1050x700.jpg

    https://images.fineartamerica.com/images/artworkimages/mediumlarge/2/chemistry-gifts-my-weakness-is-chocolateperiodically-festivalshirt.jpg

    https://i.etsystatic.com/7015445/r/il/dd12ac/1423637016/il_570xN.1423637016_6z13.jpg

    ReplyDelete