Frank Harrell
@f2harrell
Biostatistician/Professor/Founding Chair of Biostatistics, Vanderbilt U. Blog: Statistical Thinking:https://t.co/2BTEONzsfX @f2harrell on https://t.co/bsPN9JQNOS
ID:821105693948264448
https://hbiostat.org 16-01-2017 21:23:47
18,0K Tweets
29,9K Followers
171 Following
Follow People
These 2 plots, a residuals and a QQ really demonstrate the disaster of change from baseline in ordinal variable - this should be widely emphasized. I can’t unsee that residuals plot 🙈
ht Frank Harrell fharrell.com/post/pop/
New blog article on frequentist power and sample size calculations for ordinal outcomes and mixed continuous/ordinal outcomes, e.g., continuous patient response with clinical event overrides: fharrell.com/post/pop #Statistics #rstats #clinicaltrials
I've greatly expanded my chapter on Bayesian clinical trial design with examples of Bayesian power and sample size simulations for time-to-event and ordinal outcomes, incorporating uncertainty in effect size to detect ... hbiostat.org/bayes/bet/desi… Vanderbilt Department of Biostatistics
#Statistics thought of the day: The Wilcoxon test assumes more than the proportional odds ordinal logistic model, and unlike the PO model does not provide estimates of exceedance probabilities, means, and quantiles. fharrell.com/post/rpo fharrell.com/post/powilcoxon Vanderbilt Department of Biostatistics
Congratulations to PhD candidate and Biostatistics Graduate Student Association secretary Shengxin Tu (MS DukeBiostats) on winning the 2024 Provost Pathbreaking Discovery Award Vanderbilt School of Medicine. medschool.vanderbilt.edu/basic-sciences… #ClusteredData #HIV #AIDS
Proud to be a co-author with Rasha Al-Lamee Matthew Shun-Shin on a 100% Bayesian clinical trial paper that also uses our latest longitudinal ordinal modeling approach, helped by the #rstats rmsb package: thelancet.com/journals/lance… How can cardiologist Matthew Shun-Shin master all this?
What an amazing time together with two of my all-time favorite collaborators, from Imperial College London, Matthew Shun-Shin and Rasha Al-Lamee coupled with fun discussions about clinical trial design, outcome measures, Bayes, and more.
This will be fun Lucy D’Agostino McGowan ! So many analysts are puzzled about inclusion of the outcome variable in imputation. #WebENAR Vanderbilt Department of Biostatistics #Statistics
This is a must-see on many levels. While watching it I became frightened at how things are so similar in my field of #Statistics especially related to Sabine Hossenfelder 's comment 'They just wanted to write papers', plus how fad-driven is #Statistics .
#Statistics throught of the day: If sponsors knew how much money was wasted with fixed sample size designs, and how much earlier Bayesian sequential designs would have bailed out on ineffective treatments, they'd be shocked. hbiostat.org/bayes/bet/desi…
New blog article on why the log-rank test has more assumptions than the Cox proportional hazards model for time-to-event analysis: fharrell.com/post/logrank Vanderbilt Department of Biostatistics #Statistics #clinicaltrials
This blog article has been much improved with several more examples of assumptions made by various #Statistics methods, and making a distinction between faux-nonparametric methods like Wilcoxon and log-rank, and true nonparametric methods like Kolmogorov-Smirnov. Vanderbilt Department of Biostatistics
New blog article attempting to answer 'What does it mean for a statistical method to make a specific assumption?' : fharrell.com/post/assume #Statistics Vanderbilt Department of Biostatistics