Will Hulme

@wjchulme

Stats n that. Post-doc with . Currently on pat leave 🥜

wjchulme.github.io
Vrijeme pridruživanja: prosinac 2014.
43 fotografije ili videozapisa Fotografije i videozapisi

Tweetovi

Blokirali ste korisnika/cu @wjchulme

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

  1. proslijedio/la je Tweet
    27. sij

    Conducting a literature review of analytical methods? Here is a preprint of our commentary on their design, implementation and reporting, collating our group's experiences of conducting such reviews. Comments and wider discussion most welcome.

    , , i još njih 5
    21 proslijeđeni tweet 38 korisnika označava da im se sviđa
    Poništi
  2. 28. lis 2019.

    this mini-thread was brought to you by the tired father of an 8-week old currently expected to produce [squints at graph and extrapolates] 150 wet nappies per day

    1 reply 7 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  3. 28. lis 2019.

    parent: and how many wet nappies half way between day 3 and 4? graph: between 3.1 and 5.3 wet nappies parent: on top of the nappies expected on day 3 and 4? graph: ...yes parent: and after day 6 there's just more and more wet naapies each day? graph: it would appear so yes

    1 reply 3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  4. 28. lis 2019.

    a credulous new parent: so there's a dip from days four to five? graph: yes parent: and there should be exactly 2 wet nappies on day 2? graph: no more, no less parent: and, just to be clear, the minimum should _exceed_ the maximum between days 1 and 2? graph: that's right!

    1 reply 2 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  5. 28. lis 2019.

    Just because you can apply smooth interpolation between data points doesn't mean you should source:

    1 reply 8 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  6. proslijedio/la je Tweet
    14. lis 2019.

    Hey there queer allies: this is really one of those times when we need you to step up. It’s not an exaggeration to say that lives are riding on this

    13 replies 174 proslijeđena tweeta 138 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  7. proslijedio/la je Tweet
    14. lis 2019.

    You could spend this week doing the same as usual - or you could learn a new skill and do your bit for equality! You don't have to be a physiologist, wikieditor, computer scientist or even a member of - everyone is welcome

    Learn to edit Wikipedia this Thursday at the University of Manchester
    1 reply 6 proslijeđenih tweetova 5 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  8. 20. ruj 2019.

    ✊

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

    ‘AI in government is like teenage sex: everyone is talking about it but no one is really doing it. That will continue unless we can solve some old data problems.’ My piece in

    20 replies 143 proslijeđena tweeta 254 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  10. 12. kol 2019.

    This handy pre-print on using the synthpop package gave me the kick up the arse needed to write it. Thanks, !

    NEW PREPRINT 🎉 Synthetic datasets: A primer By sharing synthetic datasets that mimic original datasets that could not otherwise be made open, researchers can ensure the reproducibility of their results while maintaining participant privacy [THREAD]
    Prikaži ovu nit
    3 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  11. 12. kol 2019.

    I wrote a quick blog post on synthetic datasets in health research. No exciting new ideas — just expressing frustration that synthetic datasets are often pitched as a way to replace real datasets, rather than to complement them

    1 reply 4 proslijeđena tweeta 20 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  12. proslijedio/la je Tweet
    18. srp 2019.
    Odgovor korisniku/ci

    No idea where you got that from, but it’s entirely and spectacularly false. 52 people were killed in the 2005 attacks. In the five years before 2005, an annual average of 16 cyclists died on London’s roads. In the five years after 2005, that *fell* to 14.

    5 replies 4 proslijeđena tweeta 150 korisnika označava da im se sviđa
    Poništi
  13. proslijedio/la je Tweet
    16. srp 2019.

    if we judge doctors on how many publications (not quality) (see ) it's our fault for predatory / fake science journals thriving. we need to sort this upstream.

    12 replies 49 proslijeđenih tweetova 171 korisnik označava da mu se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  14. proslijedio/la je Tweet
    28. lip 2019.

    Researcher volunteers needed in for half hour usability test of catalogue: Part of an study with .

    3 proslijeđena tweeta 1 korisnik označava da mu se sviđa
    Poništi
  15. proslijedio/la je Tweet
    21. lip 2019.

    After the group highlighted the need for more funding to train future biostatisticians yesterday, Peter Diggle ended his great talk this morning with his views on what an MSc for biostatisticians/health data scientists should look like 👇

    1 reply 2 proslijeđena tweeta 4 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  16. proslijedio/la je Tweet
    12. lip 2019.

    Here (with some trepidation) are 3 examples of a new unconventional map I've been working on. It's a cartogram/population-based map of local authorities+small areas (MSOAs) in Eng & Wales. Keen to hear your thoughts. I'll share the geo data in due course.

    Ethnicity in England & Wales - population-based map
    Chronic lung diseases in England - population-based map
    Broadband speeds in England & Wales - population-based map
    29 replies 92 proslijeđena tweeta 392 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  17. proslijedio/la je Tweet
    18. svi 2019.

    Absolutely. And better shared platforms, allowing standardized/automated analytics. So the effort goes into scientific validity/clinical importance issues, not the drudgery.

    Odgovor korisniku/ci @RichardLehman1
    On the flip side - why not keep the gain but reduce the pain? IPD MAs are inferentially superior, so we should be making them easier to do. Eg data-sharing as a condition of funding
    2 proslijeđena tweeta 6 korisnika označava da im se sviđa
    Poništi
  18. proslijedio/la je Tweet
    17. svi 2019.

    We had great contributions - new chapters and new eyes on old chapters - from () () ( for ) and (responsible use of ). 📚💨💨

    1 reply 3 proslijeđena tweeta 11 korisnika označava da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  19. proslijedio/la je Tweet
    29. tra 2019.

    Ideally, neither party would campaign on misleading claims like these. But realistically you’re likely to hear them more and more in the next few days. Next time you do, it’s worth remembering just how meaningless they really are. [10/10]

    14 proslijeđenih tweetova 22 korisnika označavaju da im se sviđa
    Prikaži ovu nit
    Prikaži ovu nit
    Poništi
  20. proslijedio/la je Tweet
    24. tra 2019.

    The resistance among the older generation that highlights remains highly problematic. It has at times affected my job satisfaction, my mental health, and my career trajectory. If you are senior, please express your support openly. It really helps

    7 replies 51 proslijeđeni tweet 139 korisnika označava da im se sviđa
    Poništi

@wjchulme još nije objavio nijedan Tweet.

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:

    ·