Profile picture
, 7 tweets, 3 min read
New comment on @PubPeer in response to what looks like a fundamental mistake in reporting: pubpeer.com/publications/8…
@PubPeer "primary outcome variables were all treated as continuous"
@PubPeer "Here are some odds ratios"
@PubPeer "Here are some more odds ratios"
@PubPeer "Here are some more odds ratios"
@PubPeer "Here are even more odds ratios"
@PubPeer This could be a simple labeling cockup (e.g. these aren't actually "odds ratios" but were mistakenly labeled as such), or the authors have actually done the wrong analysis for their entire paper (probably by mistake, but still...come on)
Missing some Tweet in this thread?
You can try to force a refresh.

Like this thread? Get email updates or save it to PDF!

Subscribe to Andrew Althouse
Profile picture

Get real-time email alerts when new unrolls are available from this author!

This content may be removed anytime!

Twitter may remove this content at anytime, convert it as a PDF, save and print for later use!

Try unrolling a thread yourself!

how to unroll video

1) Follow Thread Reader App on Twitter so you can easily mention us!

2) Go to a Twitter thread (series of Tweets by the same owner) and mention us with a keyword "unroll" @threadreaderapp unroll

You can practice here first or read more on our help page!

More from @ADAlthousePhD see all

Profile picture
Andrew Althouse
@ADAlthousePhD
JOB ALERT: if you are an aspiring trial statistician (or an experienced trial statistician seeking a change of scenery) that would consider a move to Pittsburgh, feel free to DM me for details.
Background in stats, biostats, epi, or any related field, but clinical trial experience (student experience counts) is highly preferred. The group doing the hiring is specifically looking for someone with interest in trials.
Tossing this out to #statstwitter and #epitwitter for a signal boost.
Read 3 tweets
Profile picture
Andrew Althouse
@ADAlthousePhD
One of the challenging things about teaching Intro Stats and, specifically, linear regression, is trying to get across the idea that two variables need not be perfectly correlated for their relationship to be useful or meaningful.
IMO, a lot of beginning statistics students see a scatterplot with a fair amount of spread, then see a significant p-value and get confused: how can there be evidence of a "linear association" between the variables? The correlation is only 0.3!
But if one variable explains 10% of the variation in another variable, that information can be really important! It doesn't mean that I can predict Y from X by itself, but in biomedical research, that need not be the case for a relationship to be useful.
Read 4 tweets
Profile picture
Andrew Althouse
@ADAlthousePhD
Good passage from the guidelines of reporting for clinical research in urology (ncbi.nlm.nih.gov/pubmed/30537407):
This is a common fallacy: within a group of patients that got a treatment, showing that a specific risk factor is associated with poorer outcome, and concluding that patients with that risk factor are therefore poor candidates for that treatment.
...in doing so, failing to appreciate that the treatment still may have improved the outcome for those patients (vs. them not getting the treatment).
Read 5 tweets

Related threads

Profile picture
Google Transparency Project
@GTP_updates
#NEW: Whenever Google is caught doing something dubious, its response is always the same: Blame someone else.

We've pulled together a sampling of Google's blame-shifting and created a parody "Google Doodle." Play the "Google Blame Game" here:
googletransparencyproject.org/articles/play-… 1/4
When journalists or regulators have raised questions about Google's conduct, Google has cast blame at different times to Microsoft, Apple, Rupert Murdoch, Viacom, Oracle, Fox, AT&T, MPAA, NBC Universal, publishers, competitors... 2/4
...comparison shopping sites, “some existing providers,” “a small number of websites”—even “an anti-Google Industrial Complex.”
politico.com/story/2011/02/… 3/4
Read 4 tweets
Profile picture
G. Elliott Morris
@gelliottmorris
#NEW poll of the 2020 Democratic primary from The Economist and YouGov:

% support among likely voters (change v last month)
Warren: 28 (+4)
Biden: 25 (+1)
Sanders: 13 (-4)
Harris: 5 (0)
Buttigieg: 5 (-1)
Yang: 3 (+1)
Bullock: 2 (+1)
Klobuchar: 2 (+1)

All else ≤ 1%
% of Democratic primary voters considering voting for each candidate (over last month):

Warren: 55%
Biden: 47
Sanders: 39
Harris: 30
Buttigieg: 28
Booker: 18
O'Rourke: 16
Yang: 13
Klobuchar: 11
Castro: 11

All else < 10%
% of Democratic primary voters who would be disappointed if ___ candidate won the nomination (over the last month):

Williamson: 32
Gabbard: 23
Biden: 22
Delaney: 21
Steyer: 20
Sanders: 19
Bennet: 17
Yang: 17
O'Rourke: 16
Booker: 13
Buttigieg: 11
Warren: 8
Read 7 tweets
Profile picture
G. Elliott Morris
@gelliottmorris
#NEW Polling on impeachment from The Economist and YouGov:

- 50% of registered voters support impeaching POTUS. 39% oppose. !! +11 is up from -12 in July. !!
- 36% of Indies and 11% of Reps support impeachment

- 51% of RVs support impeachment AND removal from office, 39% oppose
- 67% of registered voters say that “abuse of power” warrants removal from office
- 68% of RVs say the same about obstruction of justice
- 71% of RVs say that perjury warrants removal
- 59% of registered voters say they believe it is illegal for the president “to threaten withholding foreign aid to a country if that country refuses to take action that benefits the president”
- 69% of RVs say it would be inappropriate for a president to do this
Read 5 tweets
Profile picture
ΞLΞVΞNTH
@3L3V3NTH
#New Trump Tower meeting emerges with Donald Trump Jr. and Saudi representative to discuss "Iran policy." huffpost.com/entry/erik-pri…
The meeting also reportedly included now-top White House aide Stephen Miller and Israeli social media expert Joel Zamel.
Who is Joel Zamel, the Australian-Israeli linked to Mueller’s Trump Probe? haaretz.com/israel-news/.p…
Read 8 tweets
Profile picture
Cyrus Toulabi
@CyrusToulabi
#NEW: Rick Gates told Mueller that he and Manafort shared Trump Campaign Polling Data in 2016 w/ Konstantin Kilimnik, who has ties to Russian Intelligence.

In new unsealed court docs, it was revealed that Gates was at least one source for the revelation.

bloomberg.com/news/articles/…
#BREAKING: In new court filing, it was revealed that Konstantin Kilimnik...WAS IN DC FOR THE INAUGURATION.

The Manafort and Gates associate, with ties to Russian Intelligence, met with Manafort about the "Russia-Ukraine peace plan."

#REDFLAG: In court transcripts, Andrew Weissman, senior Mueller prosecutor, suggested Konstantin Kilimnik's relationship w/ Manafort & Gates...TIES DIRECTLY TO #CONSPIRACY/COLLUSION.

“This goes...very much to the heart of what the [SCO] is investigating.”
Read 5 tweets
Profile picture
Wellington ICU
@WellingtonICU
Chest physiotherapy is a mainstay in routine care and management of ventilated patients with particular roles in respiratory weaning from mechanical ventilation and clearing of secretions.
This includes deep breathing exercises, gravity-assisted drainage, chest wall percussion or vibrations, bagging (manual hyperinflation), suctioning, rib springing, intra-pulmonary percussive ventilation, aerosol therapy (to name a few)
This meta-analysis aims to address the potential role of chest physio in preventing VAP in mechanically ventilated patients.
Read 13 tweets

Trending hashtags

#FactCheck #ISIL #LiminalOrder #FakeNews #NEW #Comey #IGReportUnredacted #RobertKraft #UnitedNotDivided #Zhang #FisaBringsDownTheHouse #LockThemAllUp #DOITQ #EUBudget #Coats #SupremeCourtJustice #CindyYang #Trump #patriotsfight #PutinsPuppet #WeAreTheNewsNow #1MDB #MAGA #Zarif #PatriotsFight
Follow Us on Twitter!

Did Thread Reader help you today?

Support us! We are indie developers!

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

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

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

Donate via Paypal Become our Patreon

Thank you for your support!