Sign in

Frank Harrell

@f2harrell.bsky.social
7.9K followers 148 following 1.6K posts

Professor of Biostatistics Vanderbilt University School of Medicine Consultant, clinical trials/drug development hbiostat.org fharrell.com

PostsRepliesMedia
Frank Harrell @f2harrell.bsky.social · 20/08/2026
The more I use @typst.app for producing pdf files (haven't gotten much into html production yet) the more I love it. I'm finishing, with Claude's help, major updates to the #RStats Hmisc and rms packages that add full Typst support.
Typst output of R rms package lrm model fit
2331
Frank Harrell @f2harrell.bsky.social · 07/08/2026
Believe it or not these are all special cases of cumulative probability ordinal regression as discussed at fharrell.com/post/cpm: #Statistics #StatsSky
1263
Frank Harrell @f2harrell.bsky.social · 30/07/2026
Here are some new timings for Bayesian proportional odds models, using 4 cores (4 chains) with cmdstan and my R rmsb package blrm function. Non-Dirichlet priors result in divergences after 300 intercepts, and slowness, so timings for them are not shown for > 300 distinct Y-values. #Statistics
Timings of Bayesian proportional odds models using cmdstan
010
Frank Harrell @f2harrell.bsky.social · 17/06/2026
P-value = P(data MORE extreme than mine | H0). Justification for this is largely missing. See fharrell.com/post/journey
0132
Frank Harrell @f2harrell.bsky.social · 16/05/2026
Computing tool of the day: I've needed to have an elegant way to stitch together pieces of Quarto books to make a unified html file for teaching. In collaboration with Claude I now have a great yaml-driven tool for this. #RStats
Yaml markup for specifying which sections of which books to extract or exclude, for building a course html presentation file.
4333
Frank Harrell @f2harrell.bsky.social · 18/04/2026
There is also an "st" command line option to get a symbol table at the end of the R code listing. #RStats
000
Frank Harrell @f2harrell.bsky.social · 18/04/2026
Python script for pretty-printing of R code files: github.com/harrelfe/rsc...
Color-highlighted pretty-printing of R code
240
Frank Harrell @f2harrell.bsky.social · 02/04/2026
Got a personal email out of the blue for a ghost worker. Shameless.
060
Frank Harrell @f2harrell.bsky.social · 23/02/2026
Goal-Driven Flexible Bayesian Design presentation updated w/comparison of performance of frequentist group sequential designs: hbiostat.org/bayes/design . Frequentist approach takes far too long to make a decision by controlling something that is NOT an error prob. #Statistics #StatsSky
070
Frank Harrell @f2harrell.bsky.social · 15/12/2025
Nice work, and these linear models are special cases of semi parametric ordinal regression with no normality assumption - hbiostat.org/rmsc/ordsurv
051
Frank Harrell @f2harrell.bsky.social · 09/11/2025
I just posted a critique of this paper at discourse.datamethods.org/t/critique-o... where I hope others will add their thoughts #StatsSky #EpiSky #Statistics #rct
1274
Frank Harrell @f2harrell.bsky.social · 06/11/2025
Here’s the example: hbiostat.org/bbr/images/a...
Horizontal dot chart with side effects (adverse events) from a drug and confidence intervals for risk differences.
180
Frank Harrell @f2harrell.bsky.social · 20/10/2025
Ordinal semiparametric cumulative probability models have an amazing variety of statistical methods as special cases, including proportional odds and proportional hazards models - hbiostat.org/rmsc/ordsurv... #Statistics #StatsSky
0243
Frank Harrell @f2harrell.bsky.social · 15/07/2025
#Statistics thought of the day: The Central LIMIT Theorem hbiostat.org/bbr/htest.ht... #StatsSky
0130
Frank Harrell @f2harrell.bsky.social · 13/06/2025
I lost Galben in 2019 and still think about him a lot. We had a deep connection.
Frank Harrell with dog Galben at the beachFrank Harrell and dog Galben looking at distant waters
4310
Frank Harrell @f2harrell.bsky.social · 14/04/2025
The #rstats qreport package for assisting with report writing using Quarto has a new function makegvflow that allows users to easily make graphviz flow diagrams by specifying plain text with indenting to define the hierarchy. An example is at hbiostat.org/rflow/rforma...
Text markup for constructing simple flow diagrams with quarto
0312
Frank Harrell @f2harrell.bsky.social · 10/01/2025
Nashville is a winter wonderland today
3381
Frank Harrell @f2harrell.bsky.social · 14/11/2024
3/3 The third way to make code more readable is to use Quarto's wonderful code annotation syntax. When you hover over one of the circles, the annotation pops up. #rstats
Annotated R code using Quarto's code annotation syntax
2180
Frank Harrell @f2harrell.bsky.social · 14/11/2024
2/3 The second way to make compact code more readable is to include comments providing little diagrams to dissect the code #rstats
R data.table code with comments that annotate it
1100
Frank Harrell @f2harrell.bsky.social · 07/04/2024
I continue to add #rstats how-tos to my online R Workflow e-book at hbiostat.org/rflow
0298
Frank Harrell @f2harrell.bsky.social · 25/03/2024
Lots more yaml that applies site-wide, e.g.
010
Frank Harrell @f2harrell.bsky.social · 28/11/2023
#statistics thought of the day, from hbiostat.org/bbr/change#s...
071
Frank Harrell @f2harrell.bsky.social · 27/11/2023
Spike histograms work for all sample sizes and for extreme frequencies of tied values.
120