Fjorida Llaha
@fllaha.bsky.social
PhD Candidate at @UiTNorgesarktis
Interests #Alcohol #Cancer #Epidemiology #PublicHealth
https://en.uit.no/ansatte/person?p_document_id=769883
Interests #Alcohol #Cancer #Epidemiology #PublicHealth
https://en.uit.no/ansatte/person?p_document_id=769883
Tan solo al ver que salían en El Hormiguero, pedír donaciones públicas y hacer sentir al público responsable de los avances en el campo, me pareció una praxis dudosa.
February 6, 2026 at 4:59 PM
Tan solo al ver que salían en El Hormiguero, pedír donaciones públicas y hacer sentir al público responsable de los avances en el campo, me pareció una praxis dudosa.
Consequences of following Jeremy → constantly reminding myself that it’s my duty to give meaning to “associations” and the results, not the reader’s job. I am the one who knows the study goal, my data, the literature, who chose the methods.
Temptation to write “association” and move on is real :)
Temptation to write “association” and move on is real :)
Sometimes I hear, "we need to frame our research as associational otherwise the MDs reading it will not interpret it correctly."
It took me a while to realize how bonkers this is. It's saying some important primary users of the knowledge created are unable to understand what they're reading.
It took me a while to realize how bonkers this is. It's saying some important primary users of the knowledge created are unable to understand what they're reading.
February 6, 2026 at 12:48 PM
Consequences of following Jeremy → constantly reminding myself that it’s my duty to give meaning to “associations” and the results, not the reader’s job. I am the one who knows the study goal, my data, the literature, who chose the methods.
Temptation to write “association” and move on is real :)
Temptation to write “association” and move on is real :)
Reposted by Fjorida Llaha
Cool paper from @keling-wang.com showing that 35% of randomly selected diabetes guideline recommendations use stronger causal language than the papers they cite. Such "causal jumps" are not necessarily unwarranted but, at best, lack of transparency in how causal conclusions were arrived at.
Causal language jumps and non-alignments between clinical practice guidelines and original studies: a systematic evaluation of diabetes guidelines and their cited evidence
Objectives Clinical practice guidelines are designed to guide clinical practice and often make causal claims when making recommendations. Sometimes, guidelines make or require stronger causal claims t...
bmjopen.bmj.com
February 5, 2026 at 2:13 PM
Cool paper from @keling-wang.com showing that 35% of randomly selected diabetes guideline recommendations use stronger causal language than the papers they cite. Such "causal jumps" are not necessarily unwarranted but, at best, lack of transparency in how causal conclusions were arrived at.
This takes me back to #EpiTwitter and the debates on the use of latent growth curve models for causal questions. That thread SAVED MY PHD.
"What exactly is being compared?", among other questions and issues made me stopped using these models further in my PhD.
"What exactly is being compared?", among other questions and issues made me stopped using these models further in my PhD.
When someone tells me they plan to use a multilevel model, my next question is always 'what's your estimand'?
I see a lot of people using advanced methods like multilevel modes or latent growth curve models without any clear sense of what they are trying to estimate and why.
I see a lot of people using advanced methods like multilevel modes or latent growth curve models without any clear sense of what they are trying to estimate and why.
January 15, 2026 at 10:26 PM
This takes me back to #EpiTwitter and the debates on the use of latent growth curve models for causal questions. That thread SAVED MY PHD.
"What exactly is being compared?", among other questions and issues made me stopped using these models further in my PhD.
"What exactly is being compared?", among other questions and issues made me stopped using these models further in my PhD.
When you don't go to a conference, but your DAG does 😊
Today, I am presenting @opencausal.org at @euripsconf.bsky.social. Come say hi, if you are attending!
December 7, 2025 at 1:55 PM
When you don't go to a conference, but your DAG does 😊
I’m uploading my #DAGs on #alcohol and #cancer to this nice platform for sharing and discussion.
This DAG is also available on DAGitty for easy reuse: dagitty.net/dags.html?id...
A detailed explanation of the assumptions behind the DAGs is here: www.dovepress.com/article/supp...
This DAG is also available on DAGitty for easy reuse: dagitty.net/dags.html?id...
A detailed explanation of the assumptions behind the DAGs is here: www.dovepress.com/article/supp...
November 21, 2025 at 8:04 AM
I’m uploading my #DAGs on #alcohol and #cancer to this nice platform for sharing and discussion.
This DAG is also available on DAGitty for easy reuse: dagitty.net/dags.html?id...
A detailed explanation of the assumptions behind the DAGs is here: www.dovepress.com/article/supp...
This DAG is also available on DAGitty for easy reuse: dagitty.net/dags.html?id...
A detailed explanation of the assumptions behind the DAGs is here: www.dovepress.com/article/supp...
Position as professor/associate professor in biostatistics in Tromsø. Deadline October 12.
www.jobbnorge.no/ledige-still...
www.jobbnorge.no/ledige-still...
Professor/førsteamanuensis i biostatistikk (286394) | UiT Norges arktiske universitet
Stillingstittel: Professor/førsteamanuensis i biostatistikk (286394), Arbeidsgiver: UiT Norges arktiske universitet, Søknadsfrist: søndag 12. oktober 2025
www.jobbnorge.no
September 22, 2025 at 7:18 AM
Position as professor/associate professor in biostatistics in Tromsø. Deadline October 12.
www.jobbnorge.no/ledige-still...
www.jobbnorge.no/ledige-still...
I’ve had the same impression while looking at academic epidemiology postdoc offers. So much focus on AI, machine learning, LLM experience. Are these the core skills we need now? What about subject matter knowledge, study design, bias, statistics, population health knowledge? Outdated?
Looking at job offers (both academia and industry) and it’s basically all “AI” & Co. 😔
And WTF is “experience with LLM” for an academic post in epidemiology??
And WTF is “experience with LLM” for an academic post in epidemiology??
September 20, 2025 at 5:01 PM
I’ve had the same impression while looking at academic epidemiology postdoc offers. So much focus on AI, machine learning, LLM experience. Are these the core skills we need now? What about subject matter knowledge, study design, bias, statistics, population health knowledge? Outdated?
Every time I pass this road, I think its so cool that the #TromsøStudy has its own directional traffic sign.🙂 #PopulationBasedStudy #Norway
lnkd.in/dkGp45Cd
lnkd.in/dkGp45Cd
August 11, 2025 at 1:03 PM
Every time I pass this road, I think its so cool that the #TromsøStudy has its own directional traffic sign.🙂 #PopulationBasedStudy #Norway
lnkd.in/dkGp45Cd
lnkd.in/dkGp45Cd
Excited for my first #SER2025 in Boston next week! Looking forward to meeting US collaborators in person who are advising me on how to properly use target trial emulation and G-methods in #alcohol and #cancer observational studies.
June 4, 2025 at 7:26 AM
Highly recommended! Also, very helpful to improve the quality of my own manuscripts.
📣🧪 PhD students & postdocs in health data sciences: Explore peer review, learn from experienced editors, participate in actual reviewing, & hear how decisions at top journals are made. Apply for our free semester-long online course starting this spring! #episky #medsky iph.charite.de/en/academic_...
Peerspectives: Charité – Universitätsmedizin Berlin
Förderprogramm für Nachwuchswissenschaftler*innen mit dem Ziel, die Qualität von Publikationen zu erhöhen
iph.charite.de
January 29, 2025 at 1:23 PM
Highly recommended! Also, very helpful to improve the quality of my own manuscripts.