Andrea Arfè

@ArfeAndrea

Statistician at the Harvard-MIT Center for Regulatory Science. Bayesian analysis. Decision theory. Machine Learning. Clinical trials in oncology.

Vrijeme pridruživanja: lipanj 2014.

Tweetovi

Blokirali ste korisnika/cu @ArfeAndrea

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

  1. proslijedio/la je Tweet
    3. velj

    The Role of Academia in Data Science Education is now published. We argue that data science is not a discipline but an umbrella term for a complex process involving a team with complementary skills. We then provide recs for designing academic programs.

    Poništi
  2. proslijedio/la je Tweet
    30. sij

    Pro of academia: I have friends all around the world! Con of academia: My friends are scattered all around the world.

    Poništi
  3. proslijedio/la je Tweet
    29. sij

    Pleased to announce that v2.0 (SLABS FOR DAYS edition) hit CRAN today. Lots of new stuff in this version: A THREAD

    Prikaži ovu nit
    Poništi
  4. proslijedio/la je Tweet

    Happy ! Today we spotlight another terrific fellow, ! Dr. Avalos Pacheco completed her PhD from OxWaSP and works with Dr. at

    Poništi
  5. proslijedio/la je Tweet
    23. sij

    Patients can speak for themselves. And they have. They want easier access to THEIR OWN data. They want the CMS and ONC rules finalized. Epic, it's fine to represent your own interests. But please don't claim to speak for patients.

    Poništi
  6. 22. sij

    I don't usually boast but in the last 2 weeks I got my PhD, 2 accepted papers, and 2 invitations to revise. Pretty satisfied with how the year started!

    Poništi
  7. proslijedio/la je Tweet
    22. stu 2019.

    All Biostatistics for Biomedical Research sessions to date are now available at the YouTube BBRcourse channel at - If you watch, please register for the course at if you haven't already

    Poništi
  8. 21. stu 2019.
    Poništi
  9. proslijedio/la je Tweet

    Non-randomized studies using causal-modelling may give different answers than RCTs: a meta-epidemiological study

    Prikaži ovu nit
    Poništi
  10. proslijedio/la je Tweet
    22. lis 2019.
    Poništi
  11. proslijedio/la je Tweet
    17. lis 2019.
    Odgovor korisnicima

    Here I am channeling Morey and Senn for our trials class. Their stuff has been really helpful for communicating these ideas and this move away from the language of "a study's power" is a really important one imo.

    Poništi
  12. proslijedio/la je Tweet
    13. lis 2019.

    Data scientists take note. Big JAMA paper retracted because treatment variable coded [1,2] recoded in error to [1,0]. Results of analysis reversed. Lung disease self-management program actually harmed patients. Check recoding carefully! via

    Prikaži ovu nit
    Poništi
  13. 12. lis 2019.
    Poništi
  14. proslijedio/la je Tweet
    11. lis 2019.

    Some great tips here for promoting your research and its policy implications on Twitter 👇

    Poništi
  15. proslijedio/la je Tweet
    9. lis 2019.

    New PI Lesson #508 - be very clear when providing the title of your seminar. 🤦‍♂️

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    27. ruj 2019.
    Poništi
  17. proslijedio/la je Tweet
    29. ruj 2019.

    Yes. Here's one from a narrower angle: I view "frequentist" vs "Bayesian" as an antiquated, misleading dichotomy best replaced by talking of tools for data description, information summarization and merging, prediction, calibration, and decision/inference.

    Poništi
  18. proslijedio/la je Tweet
    28. ruj 2019.

    Pie charts: not totally useless.

    Poništi
  19. proslijedio/la je Tweet

    Probability theory is just a mathematical language for writing down the stories of how your data could have been generated. Learning how to model isn’t much different from learning a new language.

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    20. ruj 2019.

    When you finish a PhD in statistics they take you into a special room and show you what raw data really looks like. After you recover, you're sworn to secrecy. For decades, statistics educators kept this secret safe, but it's starting to get out into courses.

    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:

    ·