Lightnews — Scholar-powered news

Reposted by Georg Heinze

Journal of Clinical Epidemiology @jclinepi.bsky.social · 20d

The distinction between causal, predictive, and descriptive research—there is still room for improvement - Journal of Clinical Epidemiology www.jclinepi.com/article/S089...

The distinction between causal, predictive, and descriptive research—there is still room for improvement

It has been proposed that medical research questions can be categorised into three classes: causal, predictive, and descriptive. This distinction was proposed to encourage researchers to think clearly...

www.jclinepi.com

1 3 10

Georg Heinze @georgheinze.bsky.social · 20d

PS slides available at stratostg2.github.io (see activities)

Georg Heinze @georgheinze.bsky.social · 20d

Excellent collaboration with Mariana Nold, @aliaksandr-hubin.bsky.social , Michael Kammer - and #stratos TG2 - demonstrating the benefits of looking at a problem from two perspectives (n/n)

1 1

Georg Heinze @georgheinze.bsky.social · 20d

We presented 4 case studies of descriptive-predictive modeling. We generated SAPs for each study - 2 frequentist and 2 Bayesian - and included robustness checks of the resp other school. (2/n)

1 2

Georg Heinze @georgheinze.bsky.social · 20d

Great experience with a novel format of an invited session of #stratos TG2 @biometricsociety.bsky.social Austro-Swiss region meeting (ROeS 2025 Graz) (1/n)

1 2 4

Reposted by Georg Heinze

Stephen Senn @stephensenn.bsky.social · Aug 25

#ISCB46 very nice talk by Michael Kammer on COVID-19 prognostic models, which involved a ‘deep dive’ into the pond life of modelling.
Bottom line: “If looking for reliable models, don’t hold your breath.”

4 8

Georg Heinze @georgheinze.bsky.social · Jul 10

Or a problem of confusing a descriptive task with a causal or predictive one (if you are asking me)

3

Georg Heinze @georgheinze.bsky.social · Jun 27

Variable selection is a risk factor for causal analyses. Better drop it

4

Georg Heinze @georgheinze.bsky.social · Jun 26

... and the rejoinder of the authors: onlinelibrary.wiley.com/doi/10.1002/... Enjoy reading! (8/8)

Rejoinder to Commentaries on: On the Uses and Abuses of Regression Models: A Call for Reform of Statistical Practice and Teaching

Click on the article title to read more.

onlinelibrary.wiley.com

3

Georg Heinze @georgheinze.bsky.social · Jun 26

Comment by Stijn Vansteelandt, Johan Steen: onlinelibrary.wiley.com/doi/10.1002/... (7/8)

Discussion of “On the Uses and Abuses of Regression Models: A Call for Reform of Statistical Practice and Teaching”

Click on the article title to read more.

onlinelibrary.wiley.com

1 2

Georg Heinze @georgheinze.bsky.social · Jun 26

Comment by the STRATOS initiative: (including @boulesteixlaure.bsky.social @mhstat.bsky.social) onlinelibrary.wiley.com/doi/10.1002/... (6/8)

Commentary: Regression Models—Efforts Are Required to Improve Statistical Practice and Teaching

Click on the article title to read more.

onlinelibrary.wiley.com

1 1 4

Georg Heinze @georgheinze.bsky.social · Jun 26

Comment by @lesdomes.bsky.social (Sander Greenland): onlinelibrary.wiley.com/doi/10.1002/... (5/8)

Some Ways to Make Regression Modeling More Helpful Than Misleading

Click on the article title to read more.

onlinelibrary.wiley.com

1 2

Georg Heinze @georgheinze.bsky.social · Jun 26

Comment by Mariana Nold and myself: onlinelibrary.wiley.com/doi/10.1002/... (4/8)

Commentary: Teaching Statistics as Minor Subject—Handing on Fire, Not Worshipping Ashes

Click on the article title to read more.

onlinelibrary.wiley.com

1 2

Georg Heinze @georgheinze.bsky.social · Jun 26

Comment by Galit Shmueli: onlinelibrary.wiley.com/doi/10.1002/... (3/8)

To Explain, to Predict, or to Describe: Figuring out the Study Goal [Commentary on “On the Uses and Abuses of Regression Models” by Carlin and Moreno‐Betancur]

I strongly support Carlin and Moreno-Betancur's assertion that regression modeling (and in fact, any modeling) should be driven by the type of research question: descriptive, predictive, or causal. I...

el.wiley.com

1 2

Georg Heinze @georgheinze.bsky.social · Jun 26

Along with several comments: the first one by Robert Platt appeared already in an earlier issue: onlinelibrary.wiley.com/doi/10.1002/... (2/8)

Regression—A Means, Not an End

Click on the article title to read more.

onlinelibrary.wiley.com

1 3

Georg Heinze @georgheinze.bsky.social · Jun 26

Published: the paper 'On the uses and abuses of Regression Models: a Call for Reform of Statistical Practice and Teaching' by John Carlin and Margarita Moreno-Betancur in the latest issue of Statistics in Medicine onlinelibrary.wiley.com/doi/10.1002/... (1/8)

onlinelibrary.wiley.com

3 17 47

Georg Heinze @georgheinze.bsky.social · Jun 20

This is taking statistical education to the next level: www.youtube.com/watch?v=pZTL... by Rafael de Andrade Moral, Maynooth University

Summary Song #9 - Overfitting (Stats Parody - Charlie Puth Attention)

YouTube video by The Raf

www.youtube.com

1 3

Georg Heinze @georgheinze.bsky.social · May 15

pubmed.ncbi.nlm.nih.gov/33920501/

Regression with Highly Correlated Predictors: Variable Omission Is Not the Solution - PubMed

Regression models have been in use for decades to explore and quantify the association between a dependent response and several independent variables in environmental sciences, epidemiology and public...

pubmed.ncbi.nlm.nih.gov

1 1 3

Georg Heinze @georgheinze.bsky.social · Mar 24

I am proud to have authored this with Sean, who provided his invaluable and unique expertise at the intersection of statistics and networks: doi.org/10.1002/sim....

Flexible parametrization of graph‐theoretical features from individual‐specific networks for prediction

Statistical techniques are needed to analyze data structures with complex dependencies such that clinically useful information can be extracted. Individual-specific networks, which capture dependenci....

doi.org

1

Reposted by Georg Heinze

ENAR @enar-ibs.bsky.social · Feb 18

Continuing our #BlackHistoryMonth series, we celebrate Sean Simpson, Professor of Biostatistics & Data Science, for his contributions to neuroimaging analysis, repeated measures, & covariance modeling. Outside of work, he enjoys time with his wife, statistician Felicia, and their daughter Sophia.

1 3 4

Georg Heinze @georgheinze.bsky.social · Mar 24

Happy and proud to be on this impressive author list: @maartenvsmeden.bsky.social @laurewynants.bsky.social @benvancalster.bsky.social @richarddriley.bsky.social @pauladhiman.bsky.social @gscollins.bsky.social @kdpsingh.bsky.social and many more, masterfully led by Karel Moons!

4

Georg Heinze @georgheinze.bsky.social · Mar 24

www.bmj.com/content/388/...

PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods

The Prediction model Risk Of Bias ASsessment Tool (PROBAST) is used to assess the quality, risk of bias, and applicability of prediction models or algorithms and of prediction model/algorithm studies....

www.bmj.com

1 4 8

Reposted by Georg Heinze

Gordon Forbes @gforb.bsky.social · Mar 5

It's amazing how far back ideas go.

This paper from 1984 by @f2harrell.bsky.social discusses the need for train/test data splits and the importance of assessing model calibration and discrimination and instability in variable selection methods.

onlinelibrary.wiley.com/doi/epdf/10....

Regression modelling strategies for improved prognostic prediction

Regression models such as the Cox proportional hazards model have had increasing use in modelling and estimating the prognosis of patients with a variety of diseases. Many applications involve a larg...

onlinelibrary.wiley.com

1 6 22

Reposted by Georg Heinze

Maarten van Smeden @maartenvsmeden.bsky.social · Mar 7

Five years ago @laurewynants.bsky.social and I started this living review. Within 1 year we reviewed >700 prediction models for COVID and we found many to be poor and decided to stop reviewing. Many external validation studies followed confirming many indeed were poor

www.bmj.com/content/369/...

7 27

Georg Heinze @georgheinze.bsky.social · Jan 30

Unfortunately, the story took a different turn...