Frank HarrellMay 2, 2023
Biostatistics for Biomedical Research has a new section showing how to compute the sample size needed to characterize an entire distribution (e.g., all its quantiles). http://hbiostat.org/bbr/nonpar.html#sec-nonpar-ecdf #bbrcourse @VUMCbiostat #statistics #biostatistics
Biostatistics for Biomedical Research - 7  Nonparametric Statistical Tests

Frank HarrellJan 26, 2023
New blog article in Statistical Thinking: Grant proposal template for developing and validating predictive biostatistical models: https://fharrell.com/post/modplan #StatThink #rmscourse #bbrcourse @VUMCbiostat
Statistical Thinking - Biostatistical Modeling Plan

This is an example statistical plan for project proposals where the goal is to develop a biostatistical model for prediction, and to do external or strong internal validation of the model.

Frank HarrellDec 5, 2022
Case study on invalidity of change from baseline in which a strong nonlinear effect of baseline makes average change from baseline uninterpretable: http://hbiostat.org/bbr/change.html#sec-change-ex #bbrcourse #statistics #biostatistics
@VUMCbiostat
@EdgeforScholars
Biostatistics for Biomedical Research - 14  Transformations, Measuring Change, and Regression to the Mean

Marcel Ribeiro-Dantas, PhDπŸ”ŽπŸ“ŠJul 22, 2020

RT @[email protected]

#Statistics question of the day: Why criticize a Bayesian's choice of prior and never question your own choice of the ratio of type II assertion probability to type I assertion probability Ξ²/Ξ± being set to 4.0? (Ξ±=0.05, Ξ²=0.2) #Bayes #bbrcourse @[email protected]

πŸ¦πŸ”—: https://twitter.com/f2harrell/status/1285900436533317634

Frank Harrell on Twitter

β€œ#Statistics question of the day: Why criticize a Bayesian's choice of prior and never question your own choice of the ratio of type II assertion probability to type I assertion probability Ξ²/Ξ± being set to 4.0? (Ξ±=0.05, Ξ²=0.2) #Bayes #bbrcourse @vandy_biostat”

Twitter