People say things like “depression causes alcohol use disorder and alcohol use disorder causes depression” all the time. CLDs depict the conceptual idea easily. I agree that they lack the precision of meaning that DAGs have about effects of well-defined exposures/outcomes.
29.01.2026 23:24 — 👍 1 🔁 0 💬 0 📌 0
Bidirectional causation looks bidirectional on a causal loop diagram that doesn’t have time-specific nodes (academic.oup.com/ije/article/...).
29.01.2026 21:17 — 👍 1 🔁 0 💬 1 📌 0With @akregan.bsky.social and @oacarah.bsky.social
27.01.2026 21:11 — 👍 1 🔁 0 💬 0 📌 0
How well do electronic health records and health insurance claims capture COVID-19 vaccine doses in the US? And how does measurement error impact estimates of vaccine safety and effectiveness in studies using these data sources?
link.springer.com/article/10.1...
A less cynical take might be that in team science, there is value added from people who focus on working with particular types of data because they better understand dataset-specific issues with measurement, selection, etc. But I also agree with what you and @pwgtennant.bsky.social say below.
15.01.2026 16:36 — 👍 2 🔁 0 💬 1 📌 0
#PedSky #MedSky #EpiSky #addictionsci #policysky #polisky 🛟🫁💊
Today, California starts selling insulin at $11 per injection pen, the second drug sold under the CalRX label after naloxone. Albuterol inhalers and vaccines are next.
American food safety could be headed for a breakdown www.statnews.com/2025/12/22/a...
22.12.2025 12:01 — 👍 134 🔁 71 💬 9 📌 21
Re. Prediagnostic Exposures and Cancer Survival: Can a Meaningful Causal Estimand be Specified?
…research questions and estimands should concur on and be explicit about the target population(s)
#Causalinference #CausalSky #CausalEstimands #TargetPopulation #EpiSky
journals.lww.com/epidem/fullt...
Text reads: About synthetic panels Recruiting the right participants for a study can be difficult. You may not get the exact demographics you need, and the shorter the deadline, the less sure you can be that everyone will answer on time. One possible solution can be to use synthetic panels. Synthetic panels are powered by a first party proprietary AI model developed here at Qualtrics. Our synthetic panel is trained on thousands of responses from a variety of demographic backgrounds in order to more accurately predict how certain populations would respond to a survey. Our synthetic panel is based on the United States General Population, and is only available in English. This panel comes with ready-made quotas and target breakouts in order to represent your chosen population and make it easy to launch your survey right away.
Text reads: Question-writing best practices To get the most reliable and actionable results from synthetic audiences, consider these question-writing best practices: Ask forward-looking and attitudinal questions. Synthetic panels perform best with perceptions, preferences, and intent-based questions. For example, “How likely are you to try…?” Synthetic panels are less applicable for studies on past behaviors, detailed recall, brand recall, or awareness questions. For example, “When did you last visit…?”
Text reads: Discussion The current study aimed to conduct a meta-analysis of the TPB when applied to health behaviours which addressed the limitations of previous reviews by including only prospective tests of behaviour, applying RE meta-analytic procedures, correcting correlations for sampling and measurement error, and hierarchically analysing the effect of behaviour type and sample and methodological moderators. Some 237 tests were identified which examined relations amongst model components. Overall the analysis indicated that the TPB could explain 19.3% of the variance in behaviour and 44.3% of the variance in intention across studies. This level of prediction of behaviour is slightly lower than that of previous meta-analytic reviews which have found between 27% (Armitage & Conner, 2001; Hagger et al., 2002) and 36% (Trafimow et al., 2002) of the variance in behaviour to be explained by intention and PBC.
Did you know that from tomorrow, Qualtrics is offering synthetic panels (AI-generated participants)?
Follow me down a rabbit hole I'm calling "doing science is tough and I'm so busy, can't we just make up participants?"
Grading and googling hallucinated citations, as one does nowadays, and now that LLMs have been around for a while, I've discovered new horrors: hallucinated journals are now appearing in Google Scholar with dozens of citations bc so many people are citing these fake things
15.12.2025 20:41 — 👍 3989 🔁 1275 💬 132 📌 276
New paper for #causalinference folks in all fields
#DAGs
#CausalDiagrams
#CausalSky #StatsSky #EpiSky
academic.oup.com/ije/article/...
In Ireland we probably averted about 500 newborn RSV hospitalizations once nirsevimab was introduced last year (~75% risk reduction). Uptake was > 80%, and that's what's threatened by these cynical safety concerns from the antivaxxers in the US government.
www.medrxiv.org/content/10.1...
We're seeing a massive institutional deportation and state violence apparatus being built and it honestly feels like people dont grasp the sheer scale of it and what already is in place. For every horrific video of masked feds kidnapping people there are so many people pushing paper to help.
30.10.2025 18:06 — 👍 2776 🔁 1254 💬 51 📌 37
In response to anti-DEI legislation in the states, universities have started to hire more white male faculty.
This increase starts before bills are signed into law.
Universities appear to be anticipating anti-DEI legislation and preemptively hiring more white men.
The subtext of this comment is that the Mayor of Boston is Asian-American, whereas the Mayor of Chicago (like almost everyone else that Trump refers to as “a low IQ person”) is Black.
15.10.2025 20:29 — 👍 2235 🔁 543 💬 32 📌 12
Protecting the nation’s public health demands data, whether it be new measles cases, a surge in ER visits, or shifting patterns in obesity. The most recent job cuts at the CDC threaten the mostly unseen foundation of that research enterprise.
www.statnews.com/2025/10/14/c...
New study in @thelancet.com
“After nearly 2 years of war and severe restrictions in humanitarian aid, tens of thousands of preschool-aged children in the Gaza Strip are suffering from preventable acute malnutrition and facing an increased risk of mortality”
www.thelancet.com/journals/lan...
Holy shit. As someone who teaches global public health & policy, I find this absolutely chilling. It’s *impossible* to teach this topic without discussing politics, conflicts, social determinants of health, power, equity, disparities, colonialism & neocolonialism….
06.10.2025 22:32 — 👍 82 🔁 31 💬 3 📌 0
CDC is being run by politicians now.
"there are few experienced leaders left at the CDC; some 80% of..center leaders were laid off or terminated, or have [left]. Houry was the only permanent career official in CDC's office of the director... there were 10 political appointees remaining, she said."
Great to see this paper!
You have probably already noted this, but is Fig 2B supposed to be labeled about pregnancies instead of infants?
Useful polling data: In 2025, confidence in public health institutions has steeply declined among Democrats, but hasn't gained under Republicans. MAHA public health takeovers appear very unconvincing, even to supporters.
www.annenbergpublicpolicycenter.org/public-confi...
(h/t @tgof137.bsky.social)
Realizing that the endpoint here is probably massively scaling back screening for autism spectrum disorders, limiting resources for people who need them, but leading to a decline in cases & declaration of victory.
"If we stopped testing right now, we'd have very few cases, if any."
This graph shows a U.S. public health triumph: near-elimination of pediatric hepatitis B through universal birth vaccination. After 30 years of extraordinary progress, ACIP tomorrow considers dismantling it.
Medical justification: none.
Consequences: catastrophic.
www.cdc.gov/acip/downloa...
If you want to reduce the burden of chronic disease (including cancer), then making the vaccines for HPV & Hep B widely available and accessible with as few barriers as possible helps achieve that goal.
17.09.2025 00:42 — 👍 87 🔁 41 💬 1 📌 1
A VAERS report indicating death after COVID vaccine. The description of the investigation into this death reads: Adverse Event Description On 1/23/21 the patient had a single-car accident, slid off icy road into snowbank. She was seen in our ER, diagnosed w/ trauma and L4 compression fracture. She was transported to Hospital for further trauma workup. We believe she was treated and released. On 1/31/21 the patient had a headache but did not seek medical attention. In the morning of 2/1 she became unresponsive and was pronounced dead on the scene when EMS arrived. Autopsy showed a left temporal subdural hematoma.
The Vaccine Adverse Event Reporting System is getting attention bc RFK Jr. & his antivaxx goons plan to use VAERS to claim COVID vaccines killed children.
This is an actual VAERS report for a reported death after COVID vaccine. This is what these people count as data showing “death after vaccine:”
newsroom.ucla.edu/stories/tere...
#universities #research #funding
The US Supreme Court has derailed researchers’ efforts to reinstate almost $2 billion in grants issued by the NIH. The court’s decision represents a remarkable reversal, allowing the Trump team to proceed with its science cuts.
go.nature.com/3JsraiA
Under Trump, the Consumer Product Safety Commission—the agency that for 50 years has enforced laws that prevent choking hazards in young children’s toys—is trying to dissolve itself
19.08.2025 15:23 — 👍 8 🔁 5 💬 3 📌 1
Turns out most Americans (70%) believe US universities should be receiving previous levels of funding - or even more! - to advance scientific research.
19.08.2025 15:40 — 👍 181 🔁 52 💬 1 📌 4