All Hokie, All the Time. Period. Presented by

The Lounge Board

Freddyburg Hokie

Joined: 10/07/1999 Posts: 36084
Likes: 2092


There's a part of this article that isn't worded well, and it adds to....


the confusion, IM(ns)HO:

"The reason for this is a simple matter of statistics. The lower prevalence there is of a trait in a studied population — here, coronavirus infection — the more likely that a test will return a false positive. While a more accurate test will help, it can’t change the statistical reality when the base rate of infection is very low."

I really don't like the words "the more likely that a test will return a false positive", as they imply that the accuracy of any one test is reliant on the base rate of infection. It's not. The accuracy of the test doesn't change, it's just that the ratio of false positives to true positives changes based on the base rate of infection.

I would change the above words to "the more likely that any given positive result is a false positive".

And yes, Gadfly's link to Wikipedia has some great examples there.

(In response to this post by Stork)

Posted: 05/13/2020 at 11:09AM



+0

Insert a Link

Enter the title of the link here:


Enter the full web address of the link here -- include the "http://" part:


Current Thread:
  Simple statistical math -- `lag 05/13/2020 1:03PM
  It sure takes a village.... -- Freddyburg Hokie 05/13/2020 11:11AM
  Let's go through a simple example... -- BB Hokie 05/13/2020 10:27AM
  From the linked study, my interpretation -- HokieForever 05/13/2020 10:19AM
  Quick recap says -- Stork 05/13/2020 10:15AM

Tech Sideline is Presented By:

Our Sponsors

vm307