« The children | Main | Do vaccines have halo effects? »


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


About high CT and false positive rate, I suggest you to read the following post:
From what I have understood it is a false problem.


Antonio: Thanks for the link. You'd notice I have not opined on two issues you've brought up here: whether CT thresholds are "creating fake cases" or whether most test results are "false positives". That's because I don't speak about something unless I have sufficient confidence in what I'm writing down. You may see something in the future now that you've piqued my interest.

A Palaz

Hi Kaiser,

There have been in Europe and many other places surges in school age children associated with mass testing pre school year ending and beginnings. But it is this year start that they had become a vaccination group. The same is true for students and I think the pattern also is in the US.

On ONS study the methodology is actually very complex with ablotbof model and adjustment from raw data, which may interest you. I think it is available

Methodology link here


The sample has been changed quite a few time. The projection from small sample is very big. They use a lot of regression I think. And some big assumption even still after 1 half years not verified on data to infection ratio. missed opportunity I think but used by people amd maybe modelers for prevalences.

All across Europe also we have just had holidays season and many people flying and travel around.
People were asked to test eben if vaccination twice. So a good chance

To discover good data. And test is sometimes multiple. Unfortunately some countries use quick testing so a lateral flow test another sometimes PCR. In UK they are counted as the same and most test since December is lateral.

So background to next is I got a problem on this because I was asked to look atbholidays data. The people were testing 3ir 4 times 1 or 2 before leaving/ arriving 1 or 2 before returning and after lading.

So remember this is same people.

I find this some paper


Problem was I am not surevof in repeated testing of samevpeople whether the probabilities are independent or nested ? Contingent? Conditional. And how to compute if they are so? If positive as described in first document. But what are chances of false positives (with assumptions on prevalence covid and cross reactivrs?

Note that the outcome, stay at home for some more days was so low that second tPCR tests is mostly not taken .

Can you help on repeat test probabilities?

On CT values I think they are back computed from end counts but I do not know the way. Some inverse exponential?

As usual thankyou for your posting!

A Palaz

Hi Kaiser so I think I got the study methodolgy mixed with the ONS survey. Not sure on React it is the same and also not the panel..

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.


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

Amazon - Barnes&Noble

Junk Charts Blog

Link to junkcharts

Graphics design by Amanda Lee

Next Events

Jan: 10 NYPL Data Science Careers Talk, New York, NY

Past Events

Aug: 15 NYPL Analytics Resume Review Workshop, New York, NY

Apr: 2 Data Visualization Seminar, Pasadena, CA

Mar: 30 ASA DataFest, New York, NY

See more here

Principal Analytics Prep

Link to Principal Analytics Prep