Tyler Black, MD Profile picture
Dec 31, 2021 12 tweets 5 min read Read on X
The editorial process at @FrontiersIn makes a blunder. A study looking at "Developmental delays in children born during the pandemic" claims that fine motor delay and communication delay were seen comparing 2015-2019 & 2020.

This is very misleading. I see this mistake a lot.

/1
In fact, it is true that comparing 2020 to 2015-19 shows high anomalies in these two delays. But, if i compare 2016 to (2015, 2017-20) I would get the SAME significance testing. 2016 is worse than 2020 for fine motor and on par for communication.

/2
This is a case of a fallacy "cherry-picking."

The authors compared 2015-19 to 2020 but NOT:

2015 to 2016-20
2016 to 2015,2017-20
2017 to 2015-16, 2018-20
2018 to 2015-17, 2019-20
2019 to 2015-2018, 2020

And intentionally so, due to the cherrypicked "pandemic" situation.

/3
Had they done proper statistical tests, it would be completely obvious that 2016 and 2020 had similar rates of both delays.

Instead, cherry picking + selection bias leads to an erroneous association.

/4
The authors suggest they *controlled* this by pooling 2015-2019, but in fact they committed another fallacy!!

This is called statistical underfitting. The average is simply an inappropriate comparator.
You can clearly see the underfit here. By averaging 2015-2019, they created an average line that is supposed to represent all years "on average". But it's clearly underfit, and 2016 sticks out like a middle finger to statistical decency!

/5
Fortunately, the careful critical reader can see just how variable these numbers are, in the **FIRST FIGURE**. The peer reviewers failed the editorial process by not pointing out how this figure elevates a "possible limitation" to a "statistical failure."

Noisy numbers!

/6
The communication number is even more shaky.

While the issue isn't underfit of the average, the main issue is that 2020 would NOT be significantly different when compared to: 2016-2019, 2015-2018, 2018-2019, or ANY combination that *excluded* 2017, which seems low.

/7
In fact, very obviously, the KEY to 2020 being "statistically increased" is not 2020's elevation, but rather 2017's small stature. A simple eyeball test shows this, and yet the reviewers missed it.

/8
If we look at other measures of delay that didn't test significantly, we can see how fluctuations played such an important role.

Sorry for the scratchy comments, but it's late when I'm composing this and its irritating how obvious this is.
This type of error is *critical* during a pandemic, and undoubtedly adds fuel to the type of misattributed "cause" that drives so much covid-denialism activism.

It's not challenging statistics either, and this is what peer review is supposed to correct.

/fin
the paper in question, which *should* have concluded, if either of the two reviewers considered the obvious statistical issue, that "delay rates were within normal year-to-year fluctuation."

frontiersin.org/articles/10.33…

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Tyler Black, MD

Tyler Black, MD Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @tylerblack32

Nov 19
Battling Election Misinformation
Part 2: "The Mandate"

Contrary to media/republican pronouncements, the election of Donald Trump was one of the narrowest (by popular vote, +1.73%) in history, with only 7 elections since 1800 being narrower.

/1Image
In fact, if we look at the margin of victory when we include all eligible voters, Trump wins with 31.3% of the voting population, compared to Harris' 30.2% and 1% going to other candidates. 37.4% did not vote.

If we only include voters, Trump wins 50.03% to 49.97%

/2Image
When we look at the electoral college results, Trump won 58% of available electoral college votes. This would rank his election 41st out of 57 elections since 1800.

/3Image
Read 7 tweets
Nov 15
"[AIDS] is not being caused by a virus. It's not a virus... These people are dying because of 'poppers'... they were people who were part of a gay lifestyle... "

"This is not a viral disease, but it's a disease that is environmental."

- HHS Secretary Nominee RFK Jr

/1Image
Chemicals in water are causing trans kids: "A lot of the problems we see in kids... are coming from chemical exposures, including a lot of the sexual dysphoria that we’re seeing."

- HHS Secretary Nominee RFK Jr

/2Image
Wifi radiation causes autism, allergies, asthma, eczema: “I think it degrades your mitochondria and it opens your blood-brain barrier,”

- HHS Secretary Nominee RFK Jr

/3Image
Read 7 tweets
Nov 7
🧵Battling Antivax Disinfo🧵
Vaccination did NOT increase cancer deaths.

Here I took the 6 deadliest cancers (all 5 survival rates under 50%) in a highly vaccinated population (25-54), and we can see ZERO evidence of vaccine-related cancer deaths, all the way to May 2024.

/1Image
If i move ages to 55+, we see the same thing, and we are now looking at a lot of deaths from these extremely aggressive cancers, so this isn't some underpowered stuff here. There is NO evidence that deadly cancers have increased due to vaccination.

None.

/2Image
If we take all ages 5+ and look for until May 2024, we see no increase in these highly aggressive cancer deaths, or any cancer deaths.

/3Image
Read 8 tweets
Nov 7
The Presidential Election
Data Geekery with my interpretations

1) The Country Shifted, but More Didn't.

The final share will be ~ +1.3 to +1.5% for Trump, which is a shift of ~+5.8%.

If America was a room with 65 people in it, only 2 out of the 65 people switched shirts.

/1Image
Note: this math might seem like it doesn't work, but we have to remember to include those that voted 3rd party (1.5%ish) and those that didn't vote (about 35%).

Excluding non-voters who were eligible,
2020: 22/43 D & 20/43 R
2024: 20/42 D & 21/42 R

/2Image
In other words, the great majority of the country didn't switch, but we know there was definitely a nudge towards republican vote.

What does this mean?
The narratives about "America changing" should be very cautious, as 93% of America did not change.

/3
Read 11 tweets
Sep 3
🚨COVID-19 Vaccination saves lives and improves outcomes 🚨

In this UK study of >3 MILLION PEOPLE who vaccinated, the incidence of mental health problems was significantly reduced when a subsequent COVID-19 infection occurred.

/1Image
Looking at the totals who were infected with COVID-19, it is clear that COVID-19 diagnosis was associated with a ROBUST increase in mental health problems after the diagnosis.

/2 Image
This adds to the massive and still growing body of evidence that Covid 19 Vaccination was safe, effective, and extremely important especially considering that after this study, virtually everyone was infetcted with COVID-19.

/3
Read 5 tweets
Aug 29
Yet another study finding differential impacts (mostly with decrease of symptoms) on the mental health of youth comparing prepandemic to pandemic times.

The media far far far less likely to report on these now common findings.

/1


jamanetwork.com/journals/jaman…
My colleagues and I talked about this at length, that there were many reasons to be cautious about the early "expert predictions" and in fact when good evidence was considered, many so-called evidence based scientists were wrong: dire outcomes on mental health harder to find.

/2


Our '23 peer-reviewed commentary here, g despite many professionals who attacked my us for daring to suggest we interpret evidence cautiously rather than childishly reducing issues & acting like sensationalists, I am certain our publciation holds up well.ncbi.nlm.nih.gov/pmc/articles/P…
Read 4 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(