Donald Szlosek
@dszlosek.bsky.social
Biostatistician @IDEXX formerly at harvardmed, @BIDMChealth, @nasa. Big data, clinical trials, and medical diagnostics. Mainer. Opinions are my own. he/him
Reposted by Donald Szlosek
Survey Statistics: weights and MRP for voters
statmodeling.stat.columbia.edu/2025/11/11/s...
statmodeling.stat.columbia.edu/2025/11/11/s...
Survey Statistics: weights and MRP for voters | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
November 12, 2025 at 10:05 PM
Survey Statistics: weights and MRP for voters
statmodeling.stat.columbia.edu/2025/11/11/s...
statmodeling.stat.columbia.edu/2025/11/11/s...
It’s fascinating how cohorts of statisticians have parallel pockets of hyper-specific knowledge due to textbooks, like the collective familiarity with blue fiddler crab mating patterns, courtesy of Agresti. Palmer penguins, iris data, ect, any others I'm missing? #statssky #statistics #rstats
November 12, 2025 at 5:09 PM
It’s fascinating how cohorts of statisticians have parallel pockets of hyper-specific knowledge due to textbooks, like the collective familiarity with blue fiddler crab mating patterns, courtesy of Agresti. Palmer penguins, iris data, ect, any others I'm missing? #statssky #statistics #rstats
Reposted by Donald Szlosek
Well, it's official. #UNL Chancellor Bennett submitted his final proposal and it includes eliminating the #statistics department. budgetprocess.unl.edu/final-budget...
Guess it's time to go look for jobs. Anyone looking for a couple of very talented #datavis researchers?
Guess it's time to go look for jobs. Anyone looking for a couple of very talented #datavis researchers?
Final Budget Reduction Plan | Budget Process | Nebraska
budgetprocess.unl.edu
November 10, 2025 at 10:09 PM
Well, it's official. #UNL Chancellor Bennett submitted his final proposal and it includes eliminating the #statistics department. budgetprocess.unl.edu/final-budget...
Guess it's time to go look for jobs. Anyone looking for a couple of very talented #datavis researchers?
Guess it's time to go look for jobs. Anyone looking for a couple of very talented #datavis researchers?
Reposted by Donald Szlosek
Quick thread on the BBC and the political and societal significance of recent developments:
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
November 10, 2025 at 1:43 PM
Quick thread on the BBC and the political and societal significance of recent developments:
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
One of the main reasons the UK has historically been so much less polarised than the US, is that Britain has a shared source of information, consumed and trusted by most people regardless of their politics.
One thing I have noticed a lot in meta-analysis (thinking of those involving comparison of prognostic models) is that most focus on Embase and Medline, but no mention of Compendium (think IEEE) WoS or Scopus. Granted the sheer volume for data extraction would be astronomical.
OK So here’s a list of errors in meta-analysis in (mainly) Cochrane Collaboration work. bmcmedresmethodol.biomedcentral.com/articles/10....
I don’t think any of them have been withdrawn. Which ones should have been?
I don’t think any of them have been withdrawn. Which ones should have been?
Overstating the evidence – double counting in meta-analysis and related problems - BMC Medical Research Methodology
Background The problem of missing studies in meta-analysis has received much attention. Less attention has been paid to the more serious problem of double counting of evidence. Methods Various problem...
bmcmedresmethodol.biomedcentral.com
November 8, 2025 at 7:21 PM
One thing I have noticed a lot in meta-analysis (thinking of those involving comparison of prognostic models) is that most focus on Embase and Medline, but no mention of Compendium (think IEEE) WoS or Scopus. Granted the sheer volume for data extraction would be astronomical.
Does anyone else automictically reach for the PDF symbol when opening a new article on a journal site? It just seems like I can read the them faster. #AcademicSky
November 8, 2025 at 2:31 PM
Does anyone else automictically reach for the PDF symbol when opening a new article on a journal site? It just seems like I can read the them faster. #AcademicSky
It's a shame I didn't find this before Oct. 31st. And also a shame the term "Ghost-time bias" never caught on.
November 7, 2025 at 6:16 PM
It's a shame I didn't find this before Oct. 31st. And also a shame the term "Ghost-time bias" never caught on.
Reposted by Donald Szlosek
NEW PAPER: "Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when?"
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
November 7, 2025 at 12:44 PM
NEW PAPER: "Reporting guidelines for studies involving generative artificial intelligence applications: what do I use, and when?"
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
--> www.nature.com/articles/s41...
#HealthTech #ClinicalAI #MachineLearning #MedAI #AIinMedicine #TransparentAI #HealthInnovation #GenAI
Probably the papers I share the most often are @f2harrell.bsky.social 1996 on how to effectively develop multivariate models and @benvancalster.bsky.social 2019 paper on Calibration. Both extremely well written and informative. What are you most shared stats paper? #statistics #statssky #academicsky
November 7, 2025 at 12:12 PM
Probably the papers I share the most often are @f2harrell.bsky.social 1996 on how to effectively develop multivariate models and @benvancalster.bsky.social 2019 paper on Calibration. Both extremely well written and informative. What are you most shared stats paper? #statistics #statssky #academicsky
I recently rederived the poisson pdf distribution from the binomial. Reminds me of @kareemcarr.bsky.social recent blog about memorization vs proof. No computer around and needed it for something. Certainly there are times where knowing something will be time saving then re-deriving it from scratch.
November 6, 2025 at 1:21 PM
I recently rederived the poisson pdf distribution from the binomial. Reminds me of @kareemcarr.bsky.social recent blog about memorization vs proof. No computer around and needed it for something. Certainly there are times where knowing something will be time saving then re-deriving it from scratch.
Reposted by Donald Szlosek
Can Game Theory Help Us with Causal Discovery?
What's Your Guess?
In this week's issue of Causal Python Weekly, expect a solid mix of history, fresh discoveries, and good teaching:
1/
#CausalSky #EconSky #StatSky #MLSky #EpiSky
What's Your Guess?
In this week's issue of Causal Python Weekly, expect a solid mix of history, fresh discoveries, and good teaching:
1/
#CausalSky #EconSky #StatSky #MLSky #EpiSky
November 2, 2025 at 10:19 AM
Can Game Theory Help Us with Causal Discovery?
What's Your Guess?
In this week's issue of Causal Python Weekly, expect a solid mix of history, fresh discoveries, and good teaching:
1/
#CausalSky #EconSky #StatSky #MLSky #EpiSky
What's Your Guess?
In this week's issue of Causal Python Weekly, expect a solid mix of history, fresh discoveries, and good teaching:
1/
#CausalSky #EconSky #StatSky #MLSky #EpiSky
Reposted by Donald Szlosek
We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?
October 27, 2025 at 5:39 PM
We wrote an article explaining why you shouldn't put several variables into a regression model and report which are statistically significant - even as exploratory research. bmjmedicine.bmj.com/content/4/1/.... How did we do?
I have hiked and led hikes up Mt Washington about 30 times now. Fall is definitely one of the most deceptively dangerous times of year to hike it and you need to be prepared for overnight and winter weather!
People are so fascinatingly stupid about Mt. Washington.
“Oh, it’s not that tall,” they say, little knowing it is haunted by Weather Demons
“Oh, it’s not that tall,” they say, little knowing it is haunted by Weather Demons
I’m sorry but what were over 20 people thinking:
October 29, 2025 at 2:28 AM
I have hiked and led hikes up Mt Washington about 30 times now. Fall is definitely one of the most deceptively dangerous times of year to hike it and you need to be prepared for overnight and winter weather!
I went into the office recently and I realized that the depth of my answer to a question a generally related to my proximity to a whiteboard. Anyone else? #statistis #statssky
October 27, 2025 at 1:08 PM
I went into the office recently and I realized that the depth of my answer to a question a generally related to my proximity to a whiteboard. Anyone else? #statistis #statssky
This reminds me of a Penn & Teller quote related to the Gilbert-Shannon-Reeds model, where in 1955, they showed 7 "riffles" were needed to fully randomize a deck of cards. Below is a fascinating extension by Rick Wicklin showing how my riffles are required to restore a deck to its initial order
October 26, 2025 at 12:56 AM
This reminds me of a Penn & Teller quote related to the Gilbert-Shannon-Reeds model, where in 1955, they showed 7 "riffles" were needed to fully randomize a deck of cards. Below is a fascinating extension by Rick Wicklin showing how my riffles are required to restore a deck to its initial order
Reposted by Donald Szlosek
Excellent app!
Dr. Who solves the
"should we lump or should we split"
dilemma.
Compare lots of stat methods in this interactive app.
#rshiny #rstats #statistics #rstudio #bayesian #medical #treatment
Lumping&splitting.
Bias&variance.
Individuals&groups.
Borrowing strength
🧪
trials.shinyapps.io/Bias-varianc...
"should we lump or should we split"
dilemma.
Compare lots of stat methods in this interactive app.
#rshiny #rstats #statistics #rstudio #bayesian #medical #treatment
Lumping&splitting.
Bias&variance.
Individuals&groups.
Borrowing strength
🧪
trials.shinyapps.io/Bias-varianc...
September 26, 2025 at 5:03 PM
Excellent app!
Robert Frost was certainly more familiar with iambic pentameter
than he was with estimated parameters, but in 1942 he wrote a couplet that sounds very much like a poet's perception of a confidence interval: #statistics #statssky #academicsky
than he was with estimated parameters, but in 1942 he wrote a couplet that sounds very much like a poet's perception of a confidence interval: #statistics #statssky #academicsky
October 24, 2025 at 4:11 PM
Robert Frost was certainly more familiar with iambic pentameter
than he was with estimated parameters, but in 1942 he wrote a couplet that sounds very much like a poet's perception of a confidence interval: #statistics #statssky #academicsky
than he was with estimated parameters, but in 1942 he wrote a couplet that sounds very much like a poet's perception of a confidence interval: #statistics #statssky #academicsky
Reposted by Donald Szlosek
Since efficiency is defined in terms of variance (the second moment) and typically used to assess the performance of estimators for the mean, would estimators of higher-order moments such as skewness or kurtosis require an efficiency criterion based on correspondingly higher moments? Are these used?
October 24, 2025 at 4:03 AM
Since efficiency is defined in terms of variance (the second moment) and typically used to assess the performance of estimators for the mean, would estimators of higher-order moments such as skewness or kurtosis require an efficiency criterion based on correspondingly higher moments? Are these used?
This paper’s been popping as “evidence” that you can’t do real #causalinference w/ obs data. To me it shows you need rigorous pre-specified design (in addition to the willingness to fold when your hypothesis is not possible to answer with the data at hand). #EpiSky, #CausalSky, #AcademicSky
October 22, 2025 at 2:59 PM
This paper’s been popping as “evidence” that you can’t do real #causalinference w/ obs data. To me it shows you need rigorous pre-specified design (in addition to the willingness to fold when your hypothesis is not possible to answer with the data at hand). #EpiSky, #CausalSky, #AcademicSky
Reposted by Donald Szlosek
TOMORROW! 📢 R Consortium webinar: J&J’s Hybrid SAS/R FDA Submission: What Worked and Why
Most pharma teams live in a mixed world of SAS and R. Go inside a successful hybrid SAS/R FDA submission and see exactly how the team made it work!
r-consortium.org/webinars/jnj...
#rstats #pharma #sas
Most pharma teams live in a mixed world of SAS and R. Go inside a successful hybrid SAS/R FDA submission and see exactly how the team made it work!
r-consortium.org/webinars/jnj...
#rstats #pharma #sas
October 20, 2025 at 7:18 PM
TOMORROW! 📢 R Consortium webinar: J&J’s Hybrid SAS/R FDA Submission: What Worked and Why
Most pharma teams live in a mixed world of SAS and R. Go inside a successful hybrid SAS/R FDA submission and see exactly how the team made it work!
r-consortium.org/webinars/jnj...
#rstats #pharma #sas
Most pharma teams live in a mixed world of SAS and R. Go inside a successful hybrid SAS/R FDA submission and see exactly how the team made it work!
r-consortium.org/webinars/jnj...
#rstats #pharma #sas
Would be curious is anyone has follow through with this suggestion from this excellent @significancemag.bsky.social article from August 2011 by Alan Karr and S Stanley Young rss.onlinelibrary.wiley.com/doi/full/10....
October 20, 2025 at 4:59 PM
Would be curious is anyone has follow through with this suggestion from this excellent @significancemag.bsky.social article from August 2011 by Alan Karr and S Stanley Young rss.onlinelibrary.wiley.com/doi/full/10....
Reposted by Donald Szlosek
Here is a regular reminder of my deconstructR package, which offers self-destructing plots in R (gravity plot, black hole plot, ...). You'll find the sources here: github.com/brandmaier/d... No need to thank me. And here is a gravity plot attached.
#rstats
#academicsky
#phdsky
#rstats
#academicsky
#phdsky
November 12, 2024 at 12:28 PM
Here is a regular reminder of my deconstructR package, which offers self-destructing plots in R (gravity plot, black hole plot, ...). You'll find the sources here: github.com/brandmaier/d... No need to thank me. And here is a gravity plot attached.
#rstats
#academicsky
#phdsky
#rstats
#academicsky
#phdsky
Reposted by Donald Szlosek
My fav starter packs so far, a thread:
stats: go.bsky.app/Ki7PjpS
stats: go.bsky.app/7TBN5rX
causal inference: go.bsky.app/FdemGAZ
package devs: go.bsky.app/N1569Qh
data peeps: go.bsky.app/8TdEfdK
medical stats: go.bsky.app/ArqEz36
bioinformatics: go.bsky.app/Ha64Gmv
r-ladies: go.bsky.app/Vgxwa2F
stats: go.bsky.app/Ki7PjpS
stats: go.bsky.app/7TBN5rX
causal inference: go.bsky.app/FdemGAZ
package devs: go.bsky.app/N1569Qh
data peeps: go.bsky.app/8TdEfdK
medical stats: go.bsky.app/ArqEz36
bioinformatics: go.bsky.app/Ha64Gmv
r-ladies: go.bsky.app/Vgxwa2F
October 26, 2024 at 7:23 PM
My fav starter packs so far, a thread:
stats: go.bsky.app/Ki7PjpS
stats: go.bsky.app/7TBN5rX
causal inference: go.bsky.app/FdemGAZ
package devs: go.bsky.app/N1569Qh
data peeps: go.bsky.app/8TdEfdK
medical stats: go.bsky.app/ArqEz36
bioinformatics: go.bsky.app/Ha64Gmv
r-ladies: go.bsky.app/Vgxwa2F
stats: go.bsky.app/Ki7PjpS
stats: go.bsky.app/7TBN5rX
causal inference: go.bsky.app/FdemGAZ
package devs: go.bsky.app/N1569Qh
data peeps: go.bsky.app/8TdEfdK
medical stats: go.bsky.app/ArqEz36
bioinformatics: go.bsky.app/Ha64Gmv
r-ladies: go.bsky.app/Vgxwa2F