Miguel Hernán

@_MiguelHernan

Health researcher, Harvard professor. Making less casual. Using to learn what works. Free intro course

Boston
Vrijeme pridruživanja: kolovoz 2015.

Tweetovi

Blokirali ste korisnika/cu @_MiguelHernan

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

  1. Prikvačeni tweet
    23. lis 2019.

    For the first time ever, a full draft of the is ready to download. Enjoy it and send us your comments. Please thank our publisher for supporting the free dissemination of the book. A print version (for purchase) is expected to follow in 2020.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet
    29. sij

    Who’s up for a about adherence, per-protocol effects, and randomized trials? and I have a new paper out in collaboration with the trial team. Will this be the one that finally convinces you? 😄 OA Link:

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    27. sij

    Join faculty member José Zubizarreta on February 7 for a panel discussion on estimating the impact of a natural disaster on health outcomes using weighting for causal inference. This event is part of the Kolokotrones Symposium on Data Science at .

    , , i još njih 3
    Poništi
  4. 27. sij

    Competing events are responsible for much confusion in studies. What to do when some individuals die before developing the event of interest? If you were taught that censoring individuals who die is mandatory or that using hazards helps, please read our paper 👇

    Poništi
  5. 21. sij

    An improved version of our can now be *freely* downloaded. Many thanks to all of you who reported typos and other issues. Scoop: This version includes the book cover illustrated by the inimitable Josh McKible ().

    Prikaži ovu nit
    Poništi
  6. 10. sij

    Future authors: Good news. No more intrusive letters from me when submitting to the best health journal. After 12 years, I'm bowing out as Editor of . Congrats to new Editor Sonja Swanson! Thanks to et al for a great ride.

    Poništi
  7. proslijedio/la je Tweet
    5. pro 2019.

    I've seen so many people reference/tweet 's seminal paper The Hazard of Hazard Ratios and, to my shame, only just got to reading it. 1/

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet
    17. svi 2018.
    Odgovor korisnicima

    The idea that observational is an attempt to mimic a hypothetical experiment can be traced back to Dorn 1953 (43: 677-83). Earlier references anyone? Also, Cochran (Rubin's PhD advisor) was explicit about it in the 1960s

    Poništi
  9. 27. stu 2019.
    Poništi
  10. 27. stu 2019.

    4/ Do you—like below—prefer to express your assumptions using causal diagrams? No problem. Led by Issa Dahabreh, here we use graphs to examine the conditions for generalizability of causal inferences from a trial.

    Prikaži ovu nit
    Poništi
  11. proslijedio/la je Tweet
    19. stu 2019.

    As the editors of , and I are thrilled to share this free access multidisciplinary collection of commentaries on machine learning for causal inference. All 5 pieces are linked in our editorial about the series:

    , , i još njih 4
    Poništi
  12. 10. stu 2019.

    3/ Want more? This article in considers estimators to generalize inferences from individuals in randomized trials to all trial-eligible individuals: And this article in clears some confusions:

    Prikaži ovu nit
    Poništi
  13. 10. stu 2019.

    2/ For those interested in methods for extending inferences from randomized trials to a target population: Take a look at our tutorial (soon to appear in Statistics in Medicine) You will find identification conditions AND three estimation approaches.

    Prikaži ovu nit
    Poništi
  14. 10. stu 2019.

    1/ Suppose you want to extend causal inferences from a randomized trial to a target population. Is that or ? Issa Dahabreh and I propose an answer in this brief commentary in the European Journal of Epidemiology:

    Prikaži ovu nit
    Poništi
  15. 16. lis 2019.

    "Draw Your Assumptions Before Your Conclusions" Free Data scientists of the world, registration is open for our online course on Causal Diagrams (version 2). Thanks to Joy Shi, , and the team

    Poništi
  16. proslijedio/la je Tweet
    11. lis 2019.

    My new course "Causal Data Science with Directed Acyclic Graphs" has finally been published at . And I'm super excited to share it with you!

    Prikaži ovu nit
    Poništi
  17. 10. lis 2019.

    While we are on this topic, remember Brandolini's principle 👇

    Prikaži ovu nit
    Poništi
  18. 10. lis 2019.

    Anyone who thinks that criticizing is "Easy work" doesn't know how to criticize. Anyone who thinks that creating is always "Hard work" hasn't seen many human creations. Good science needs teams of creators and criticizers. Privileging either creation or criticism is not wise.

    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    8. lis 2019.

    Excited to share our research in ! Explicitly emulating a target trial reduces bias in analyses of electronic health records. An application to statins and cancer. Roger Logan

    Poništi
  20. 3. lis 2019.

    Please join us in publishing your failures. It is the best way to fight hype in from complex longitudinal data. Algorithms may help but, at the end of the day, either you do or don't have data on treatments, outcomes, and confounders. It is really that simple.

    Prikaži ovu nit
    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:

    ·