Daniel E. Weeks

@StatGenDan

Statistical geneticist. Professor of Human Genetics and Biostatistics at the University of Pittsburgh.

Pittsburgh, PA
Vrijeme pridruživanja: srpanj 2016.

Tweetovi

Blokirali ste korisnika/cu @StatGenDan

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

  1. 3. velj

    Is there some way to efficiently find Twitter threads that discuss a given pre-print or paper? I learn a lot from certain Twitter threads but if I fail to bookmark them, they are rather hard to find later. Need a PubPeer-like index to relevant Twitter threads.

    Poništi
  2. 2. velj

    “The most serious consequence of this array of P-value misconceptions is the false belief that the prob. of a conclusion being in error can be calculated from the data in a single experiment without reference to external evidence or the plausibility of the underlying mechanism.”

    Poništi
  3. proslijedio/la je Tweet
    30. sij

    Document your code. Sometimes your collaborator is you, two years in the future. And you from two years in the past is really bad about replying to emails.

    Poništi
  4. 29. sij

    “Science is built on trust. Trust that your experiments will work. Trust in your collaborators to pull their weight. But most importantly, trust that the data we so painstakingly collect are accurate and as representative of the real world as they can be.”

    Poništi
  5. 26. sij

    Important data and analyses presented very clearly, with graphics and explanatory narrative side by side.

    Poništi
  6. 25. sij

    “AI prefers that radiologists be consistent like sheep and the report be dogmatic like the Old Testament, so that it can better understand the ground truth even if the ground truth is really ground truthiness.”

    Poništi
  7. 21. sij

    “This was the most intellectually engaging course and particularly relevant to my research work I ever attended.” Join us this July!

    Poništi
  8. 18. sij

    I fear detecting anomalies too late - they can be hard to find. “Unfortunately, the anomalies in the raw data cannot be sufficiently explained nor corrected. As such, the results drawn from these data can no longer be considered reliable. We regretfully retract this article”

    Poništi
  9. 18. sij

    “The world of a statistician is simple because the null hypothesis is either true or false.”

    Poništi
  10. 17. sij

    An escaped space “\ “ after the ![]() will keep the included figure in place. ![SourceTree commit message](images/sourcetree-commit-message.png)\

    Poništi
  11. 17. sij

    “If you design a study that has 90% power for a medium d = 0.5, the sample size you decide to use means effects smaller than d = 0.3 will never be statistically significant. We can use to infer what your smallest effect size of interest, or SESOI will be”

    Poništi
  12. proslijedio/la je Tweet
    16. sij

    Congratulations to Kathryn Roeder for being selected to give the 2020 RA Fisher Award Lecture at ! Very prestigious recognition of high achievement and scholarship in statistical science and much deserved. Mark your calendars!

    Poništi
  13. 16. sij

    Join us - Feedback from our 2019 course: “This is an excellent course covering a wide range of topics and taught by inspirational instructors. I have learnt so much and am now buzzing with new ways I can possibly analyze my data.”

    Poništi
  14. proslijedio/la je Tweet
    13. sij

    Imagine you made a sandcastle. It gets shown to expert builders One says it's nice but maybe add some towers One says it should've been a farm from the start One asks why you didn't use cement Eventually it's good enough, so someone fences it off and charges money to see it

    Poništi
  15. proslijedio/la je Tweet
    11. sij

    Total NIH funding by institution in Pennsylvania for 2019.

    Poništi
  16. 10. sij

    “in sound bites dummy: Interactions are hard to detect because the uncertainty is larger than you might expect effects: Interactions are hard to detect because the coefficient is smaller than you might expect”

    Poništi
  17. proslijedio/la je Tweet
    10. sij

    Convert your NIH percentile score into a rough estimate of probability of funding. (Select your Institute/Center first though.)

    Prikaži ovu nit
    Poništi
  18. proslijedio/la je Tweet
    7. sij

    Scammers got my info from the SMBE2020 speakers list. Tried to pretend they were with the conference trying to book my hotel. Beware.

    Poništi
  19. 5. sij

    “This ruile of thumb should not be used if the statistician can think of anything better to do” - I. J. Good.

    Poništi
  20. 3. sij

    This thread describes several wonderful medical advances that were built upon a foundation of extensive basic research.

    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:

    ·