When researchers bring up confounders without ever having declared the actual analysis goal
October 28, 2025 at 10:24 AM
When researchers bring up confounders without ever having declared the actual analysis goal
A professional confounder
January 25, 2026 at 1:37 PM
A professional confounder
I am absolutely sure no matching on other metrics occurred whatsoever
confounder, what confounder
confounder, what confounder
August 9, 2026 at 3:04 PM
I am absolutely sure no matching on other metrics occurred whatsoever
confounder, what confounder
confounder, what confounder
if I was a confounder I would simply be easy to observe
My job would be so much easier if correlation was causation😔
October 13, 2025 at 2:25 AM
if I was a confounder I would simply be easy to observe
Yeah, and I think another confounder is you have older "working class" people who have ended up comparatively comfortably off - house paid for, decent pension income.
September 26, 2026 at 7:55 AM
Yeah, and I think another confounder is you have older "working class" people who have ended up comparatively comfortably off - house paid for, decent pension income.
"Fecal microbial load is a major confounder in microbiome studies."
Fecal microbial load is a major determinant of gut microbiome variation and a confounder for disease associations. #Cell @cellpress.bsky.social
Open Access
www.cell.com/cell/fulltex...
Fecal microbial load is a major determinant of gut microbiome variation and a confounder for disease associations. #Cell @cellpress.bsky.social
Open Access
www.cell.com/cell/fulltex...
December 1, 2024 at 8:24 AM
"Fecal microbial load is a major confounder in microbiome studies."
Fecal microbial load is a major determinant of gut microbiome variation and a confounder for disease associations. #Cell @cellpress.bsky.social
Open Access
www.cell.com/cell/fulltex...
Fecal microbial load is a major determinant of gut microbiome variation and a confounder for disease associations. #Cell @cellpress.bsky.social
Open Access
www.cell.com/cell/fulltex...
just controlled for a post-treatment confounder and it felt good
February 22, 2025 at 6:13 AM
just controlled for a post-treatment confounder and it felt good
two party system a major confounder obviously but some of the dynamics overlap
July 5, 2024 at 12:21 PM
two party system a major confounder obviously but some of the dynamics overlap
Many acetaminophen–autism studies don’t control for why the drug was taken, often viral illness, a major confounder. Viral infections during pregnancy can affect neurodevelopment.
The current admin doesn’t seem to want to prevent these
The current admin doesn’t seem to want to prevent these
September 23, 2025 at 5:27 AM
Many acetaminophen–autism studies don’t control for why the drug was taken, often viral illness, a major confounder. Viral infections during pregnancy can affect neurodevelopment.
The current admin doesn’t seem to want to prevent these
The current admin doesn’t seem to want to prevent these
Confounder Klaxon Alert!
September 11, 2025 at 7:08 AM
Confounder Klaxon Alert!
New blog post!
Let's say you have two measures meant to capture the same confounder. They're highly correlated. Can you still proceed with your regression analysis?
(I admit, the title is a bit of a spoiler)
www.the100.ci/2025/10/13/i...
Let's say you have two measures meant to capture the same confounder. They're highly correlated. Can you still proceed with your regression analysis?
(I admit, the title is a bit of a spoiler)
www.the100.ci/2025/10/13/i...
If you have two measures of the same confounder, you can just include both of them in your regression model
Sometimes, researchers worry about multicollinearity in situations where it’s actually a non-issue. Here’s one such scenario.
Imagine a situation where you are interested in the effect of X on Y (X...
www.the100.ci
October 13, 2025 at 1:14 PM
New blog post!
Let's say you have two measures meant to capture the same confounder. They're highly correlated. Can you still proceed with your regression analysis?
(I admit, the title is a bit of a spoiler)
www.the100.ci/2025/10/13/i...
Let's say you have two measures meant to capture the same confounder. They're highly correlated. Can you still proceed with your regression analysis?
(I admit, the title is a bit of a spoiler)
www.the100.ci/2025/10/13/i...
A fun thing about being a tech reporter married to an econometrician is constantly misreading the word "cofounder" as "confounder" and vice versa
October 23, 2025 at 6:31 PM
A fun thing about being a tech reporter married to an econometrician is constantly misreading the word "cofounder" as "confounder" and vice versa
when you see an IV bruise on a man who says that it is "probably his last" attendance at an annual event it usually means he's dying. the main confounder is that he's also an idiot who says nonsensical things
March 28, 2025 at 7:40 PM
when you see an IV bruise on a man who says that it is "probably his last" attendance at an annual event it usually means he's dying. the main confounder is that he's also an idiot who says nonsensical things
confounder harpy
and also confounder harpy [in a bunnysuit]
and also confounder harpy [in a bunnysuit]
April 5, 2026 at 3:11 AM
confounder harpy
and also confounder harpy [in a bunnysuit]
and also confounder harpy [in a bunnysuit]
I guess the big confounder here is that a lot of the Soviets started to be anti-Trump around the Ukraine invasion for obvious reasons, while the Americans still loved culture war slop.
August 28, 2025 at 2:18 AM
I guess the big confounder here is that a lot of the Soviets started to be anti-Trump around the Ukraine invasion for obvious reasons, while the Americans still loved culture war slop.
Adjusting for local politics, I am more rightwing than these people, I don’t get how a pollster doesn’t realise “wait, this a confounder for living in a big city!”
September 4, 2025 at 8:52 PM
Adjusting for local politics, I am more rightwing than these people, I don’t get how a pollster doesn’t realise “wait, this a confounder for living in a big city!”
The piece is entirely destructive with no alternative control states proposed. There's no reanalysis with other controls or a test of their own COVID confounder hypothesis. Every section introduces doubt without offering any path to resolution. But sowing doubt is exactly what SEGM is designed to do
May 28, 2026 at 3:45 PM
The piece is entirely destructive with no alternative control states proposed. There's no reanalysis with other controls or a test of their own COVID confounder hypothesis. Every section introduces doubt without offering any path to resolution. But sowing doubt is exactly what SEGM is designed to do
The critique of unmeasured confounding is often levied in a lazy/broad way. It is trivially true in any observational study. But if the critic can't think of a plausible such confounder and posit a reasonable direction/magnitude of its bias then they're not doing productive science.
We really do need to get away from the binary. It should be "is there unmeasured confounding or not." Almost certainty there is - it's a matter of how much and what direction.
March 1, 2026 at 6:47 PM
The critique of unmeasured confounding is often levied in a lazy/broad way. It is trivially true in any observational study. But if the critic can't think of a plausible such confounder and posit a reasonable direction/magnitude of its bias then they're not doing productive science.
got tickets to an event I never expected to see, a carefully remastered and uncut and duly NC-17 rated exhibition of Ken Russell's THE DEVILS exclusively in AMC theaters (that last part is the real confounder)
I am in the group who has no idea what they're in for and frankly I'm good with that
I am in the group who has no idea what they're in for and frankly I'm good with that
September 26, 2026 at 1:02 AM
got tickets to an event I never expected to see, a carefully remastered and uncut and duly NC-17 rated exhibition of Ken Russell's THE DEVILS exclusively in AMC theaters (that last part is the real confounder)
I am in the group who has no idea what they're in for and frankly I'm good with that
I am in the group who has no idea what they're in for and frankly I'm good with that
its a confounder because French men being perverts is sort of a "pass go, collect twenty bucks" thing
bsky.app/profile/surc...
bsky.app/profile/surc...
Okay, but there's a major confounding factor here in that PEG is French.
i see they are once again playing my music! so i will provide the words: i think it is important to recognize how much of the new right's politics is drawn from barely-sublimated pornographic fantasies. that is part of what they are selling to young men!
April 2, 2025 at 7:31 PM
its a confounder because French men being perverts is sort of a "pass go, collect twenty bucks" thing
bsky.app/profile/surc...
bsky.app/profile/surc...
“But the endorsement is post treatment so she’s a mediator not a confounder” send that trash to PNAS Contributed where it belongs
September 11, 2024 at 3:34 AM
“But the endorsement is post treatment so she’s a mediator not a confounder” send that trash to PNAS Contributed where it belongs
Of course we must note the confounder here, which is inherent intelligence - college-bound students tend to be the smartest in their age cohort. But the relationship holds in groups with lower college attainment (more smart kids not going to college)...
December 10, 2025 at 5:28 PM
Of course we must note the confounder here, which is inherent intelligence - college-bound students tend to be the smartest in their age cohort. But the relationship holds in groups with lower college attainment (more smart kids not going to college)...
It’s actually confounder and E <- C -> O
October 13, 2025 at 10:26 PM
It’s actually confounder and E <- C -> O
The pregnancy claims are even worse.
With many other papers showing no increased risk of miscarriage after vaccination, he cherry picks one paper claiming it shows an increased risk of pregnancy loss after vaccination, when their analysis after confounder adjustment showed no evidence.
With many other papers showing no increased risk of miscarriage after vaccination, he cherry picks one paper claiming it shows an increased risk of pregnancy loss after vaccination, when their analysis after confounder adjustment showed no evidence.
June 13, 2025 at 7:37 PM
The pregnancy claims are even worse.
With many other papers showing no increased risk of miscarriage after vaccination, he cherry picks one paper claiming it shows an increased risk of pregnancy loss after vaccination, when their analysis after confounder adjustment showed no evidence.
With many other papers showing no increased risk of miscarriage after vaccination, he cherry picks one paper claiming it shows an increased risk of pregnancy loss after vaccination, when their analysis after confounder adjustment showed no evidence.