Frank Harrell

@f2harrell

Prof, Founding Chair of Biostatistics, Vanderbilt U. Expert Statistical Advisor, Office of Biostatistics, FDA CDER. Blog: Statistical Thinking -fharrell.com

Vrijeme pridruživanja: siječanj 2017.

Tweetovi

Blokirali ste korisnika/cu @f2harrell

Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @f2harrell

  1. proslijedio/la je Tweet
    1. velj
    Odgovor korisnicima

    1/2: Consideration of intent and utility (psychology)may be illuminating for the issue of change-from-baseline (CfB) vs models for response conditional on baseline (mRcB). Humans intuitively construe effect as systematic change. But this intuition may make mischief for analysis.

    Poništi
  2. proslijedio/la je Tweet
    29. sij

    RStudio announces today that we are a Certified B-Corp! As a Public Benefit Corp, our long-term mission of creating free & open-source software for data science & scientific research is now part of our corporate charter. Read more at

    RStudio, a Certified B Corporation
    Poništi
  3. 30. sij

    thought of the day: Developing predictions from observational data such as informs one about PREVAILING outcomes of PREVAILING treatment strategies and has almost nothing to do with what happens if a DIFFERENT treatment were given to a patient.

    Poništi
  4. 30. sij

    Enjoying . Here are the slides from the talk I gave yesterday:

    Poništi
  5. 30. sij

    It was so much fun creating this podcast on parts of my philosophy of statistics with and Richard for

    Poništi
  6. proslijedio/la je Tweet
    20. kol 2019.

    This is a historic moment .... ISI, IBS, IMS, ASA and RSS all have female presidents! It will be so for just a few more days until John Bailer takes over as ISI president. ⁦⁩ ⁦⁩ ⁦⁩ ⁦

    Prikaži ovu nit
    Poništi
  7. 28. sij

    Biostatistics for Biomedical Research Session 12 Friday at 10am US ET: correlation coefficients and how to maintain perspective when you examine many of them; also sample size for r:

    Poništi
  8. proslijedio/la je Tweet
    28. sij
    Poništi
  9. 28. sij

    Excellent paper arguing that hypotheses are not necessary ingredients for scientific advancement

    Poništi
  10. proslijedio/la je Tweet
    27. sij

    Howard Zinn Wisdom Sampler: "The most revolutionary act is to tell the truth" "There's no flag large enough to cover the shame of killing innocent people" "Dissent is the highest form of patriotism" "Capitalism always failed the lower classes- now its failing the middle class"

    Poništi
  11. 27. sij

    Terrific commentary by on ANDROMEDA study, raising serious questions about how Hardwicke and Ioannidis handled their survey of signatories to the 'end of significance' letter.

    Poništi
  12. proslijedio/la je Tweet
    25. sij

    Another classic! Forge Wednesday Roundup - January 22, 2020

    Poništi
  13. 24. sij

    & treatment comparison thought of the day: The fundamental therapeutic question (which motivates ANCOVA) is: Do 2 patients starting at the same point except for treatment assignment end up at the same point? Master conditioning & you'll optimize power+interpretation

    Poništi
  14. 24. sij

    11 starts in <2.5 hrs. Learn how to do power calculations explicitly for the Wilcoxon test and how to replace that test and the Kruskal-Wallis rank ANOVA with a more general statistical model that also allows estimation of means and quantiles.

    Poništi
  15. 24. sij

    This trial published in got lucky despite using an outcome variable with tragic statistical properties. But a proper outcome variable could have resulted in FAR fewer women being randomized while getting the same power:

    Poništi
  16. 24. sij

    Huge misinterpretation of results in . If you can make that conclusion you only need to randomize 2 patients:

    Poništi
  17. proslijedio/la je Tweet
    23. sij

    This week’s episode of Stats+Stories features ' President-elect and @UrbanInstitue’s Rob Santos who is here to discuss what is going on with the 2020 Census.

    Poništi
  18. proslijedio/la je Tweet
    23. sij

    Greta restores my flagging faith in human nature. She is the conscience of our time & a lonely voice of sanity in a world spinning out of control.

    Poništi
  19. 21. sij

    Biostatistics for Biomedical Research Friday morning 10am US ET: model approach to the Wilcoxon test + power/sample size calculations for Wilcoxon

    Poništi
  20. 20. sij

    Wonderful discussion of problems with naked point estimates by Stephen Senn, with very interesting history about uncertainty in point estimates

    Poništi

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.

    Možda bi vam se svidjelo i ovo:

    ·