Jon Huang

@jon_y_huang

Epidemiologist. Husband. Dad | ā: , | Causal inf, birth cohorts, & biomarkers | Biostatistics Lead @ SICS | He/him | Views mine.

Singapore
Vrijeme pridruživanja: travanj 2015.

Tweetovi

Blokirali ste korisnika/cu @jon_y_huang

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

  1. proslijedio/la je Tweet
    prije 13 sati

    I am a Wuhan girl living in Hong Kong. Right now, all my close family is under lock-down back in my hometown, at the epicenter of this epidemic.

    Prikaži ovu nit
    Poništi
  2. proslijedio/la je Tweet

    See, people think Anscombe's quartet is all artificial extreme cases and no one would actually make such a stupid mistake with regression, and then you get figures like Fig 8C

    Prikaži ovu nit
    Poništi
  3. proslijedio/la je Tweet
    prije 13 sati

    Full recipe 1. install.packages("xaringan") 2. devtools::install_github("EvaMaeRey/flipbookr") 3. restart RStudio 4. File -> New File -> RMarkdown -> From Template -> A Minimal Flipbook 5. Use template or your own pipelines 6. "Knit" 7. Explore flipbook!

    Poništi
  4. proslijedio/la je Tweet
    prije 8 sati

    I’m just going to say it again. Start building relationships with senior people, bc when you eventually do need letters, they’ll be there to write them. I hate to make it so transactional sounding, and I don’t mean it that way. But that’s the hidden curriculum. 1/n

    Prikaži ovu nit
    Poništi
  5. proslijedio/la je Tweet
    prije 20 sati

    We engaged with many women with higher BMIs in pregnancy. Many had been aware that obesity in pregnancy carried additional risks and had lost considerable weight before conceiving - yet they remained overweight. No-one took this into account.

    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    31. sij

    Stats advice needed! I have seen the experts argue that instead of testing change scores, one ought to test the end points and add the baselines as a covariate. Did I misunderstand? More importantly, what are the key papers on this topic?

    Poništi
  7. proslijedio/la je Tweet
    30. sij

    Just had a paper rejected that develops and internally validates 2 variants of a prediction model. Rev #1 has 4 key points: 1. Compare AUCs with p-values 2. Show ROC curves 3. Show calibration 4. Show net reclassification index All nonsensical. Let’s go through.

    Prikaži ovu nit
    Poništi
  8. proslijedio/la je Tweet

    Being in academia for the past three years has made me feel bad for desiring a 40 hour set work week. So many people spend all their time doing science even if they have other hobbies and interests. Why is this the norm and what can we do to change it?

    Poništi
  9. 31. sij
    Poništi
  10. proslijedio/la je Tweet
    30. sij
    Odgovor korisniku/ci

    Sure. Look at PROBAST and univariable selection

    Poništi
  11. proslijedio/la je Tweet
    29. sij

    airline gate attendant: I understand that your little boy is difficult and hard to keep track of, but no, airline policy strictly forbids checking children in the cargo hold. you’ll have to— members of the band Kansas: <deep breath>

    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    30. sij

    New preprint w/ my sib “Truer facts through stronger values: confronting science’s sociopolitical realities”. Plz read & provide feedback! Relevant to recent discussions about political beliefs/values in epi. Summary below: 1/8

    Prikaži ovu nit
    Poništi
  13. proslijedio/la je Tweet
    30. sij

    This seems important to discuss . Most reviewers from the are from a small handful of countries (and I'm sure is the case for many many other journals), mirroring authorship.

    Poništi
  14. 31. sij

    Too true: Someone who thinks they're so smart they can burn social capital by being a jerk has clearly overvalued their intellect. Don't need such out-of-touch people in your life. I♥️ takes 🤗

    Poništi
  15. proslijedio/la je Tweet
    29. sij

    Hooray! 5 years' work, some great reviewers and 'Best practice guidance for linear mixed-effects models in psychological science' is in press at Journal of Memory and Language. 50 free copies: TLDR: FOR GOODNESS SAKE REPORT MODELS & RESULTS IN FULL. 1/

    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    28. sij

    Interested in doing a PhD with Ian White and me on missing data in RCTs? Couple of days left to register interest!

    Poništi
  17. proslijedio/la je Tweet
    29. sij

    Nice thread on the various meanings of the idea of ‘mechanisms’ in social science. Similar ideas apply in eg biology, or even engineering, I think.

    Prikaži ovu nit
    Poništi
  18. 29. sij

    Thought provoking thread on 2 (complementary?) concepts of "mechanism" and how they're studied in the social sciences. 🤔

    Poništi
  19. proslijedio/la je Tweet
    29. sij

    Was thrilled to take the 💯⭐️⭐️⭐️⭐️⭐️ workshop “Deep Learning with Keras and TensorFlow in R” from Observation: So much term rebranding in deep learning. I have a section of notes of the form: {ye olde stats term} -> {fancy-pants deep learning term}

    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    28. sij

    One thing I’ll throw out there. If you’re in an area, contact a dept in the area and ask if you can come present. Definitely reach out to schools in your driving distance. Advocate constantly for yourself; don’t be passive, no matter how awkward it makes you feel.

    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:

    ·