Kareem Carr 

@kareem_carr

Statistics PhD student | Follow me for the Data Science Jokes! | formerly , , , |🇰🇳 🇬🇧 🇨🇦

Cambridge, MA
Vrijeme pridruživanja: lipanj 2013.

Tweetovi

Blokirali ste korisnika/cu @kareem_carr

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

  1. Prikvačeni tweet

    me: I discovered a new statistical law that says that all jokes on twitter are based on other jokes on twitter friend: that’s really cool! what do you call it? me: *slowly takes off sun glasses* regression to the meme

    Poništi
  2. Is it just me or are scientific fields prestigious in direct proportion to how useful they are in making money, building weapons or waging wars?

    Poništi
  3. “I have something to confess.” “Yes?” “My null hypothesis is you’re awful.” “I’m confident you’ll reject.” “My threshold is quite stringent.” “Yes, but you don’t know my effect size.”

    Poništi
  4. 5. velj

    them: we have funding me, a grad student:

    Poništi
  5. 5. velj

    Here p is being used as a measure of evidence. So researcher psychology seems relevant. It probably depends on the field and shifts with established conventions. Am I differently confident if p=0.000 vs. p=0.00000318 vs. p < 0.001. Yes. Would others be? I don't know.

    Poništi
  6. 4. velj

    new data scientist jumping into their first analysis

    Poništi
  7. 4. velj

    What's the ethical response to academic misinformation on Twitter? I don't mean bad takes. I mean things that people say that are contradicted by established peer-reviewed research. Should I talk about it or ignore? Should I reference the problematic tweet or speak generally?

    Poništi
  8. 3. velj

    People keep using the term "bad data". There's no such thing! There's only data that's generated by processes *the data analyst* doesn't fully understand. When an analyst fully understands the data-generating process, the worst that can happen is the analysis is uninformative.

    Poništi
  9. 3. velj

    when your data just doesn’t support your hypothesis no matter what you do

    Poništi
  10. 31. sij

    coworker: what's your most controversial statistics opinion? me, a data scientist: *looks around* shhhh. we can talk about it. but not here.

    Poništi
  11. 30. sij

    Some people say it's bad to not follow politics. But I'm vastly more happy since I stopped keeping up with every little controversy, and it allows me to be there emotionally for all of you that get depressed by politics. I don't read politics so you don't don't have to.

    Poništi
  12. 30. sij

    Black box machine learning models may replace traditional science. I would argue that traditional science's authority derives from it's efficacy, not from its explanatory power. Humans like narratives, but modern political experience suggests those narratives need not be true.

    Poništi
  13. 30. sij

    Wow. Kids out here submitting homework via Twitter now. It's true what they say. Either you die a hero or you live long enough to become an old.

    Poništi
  14. 30. sij

    Thanks to everybody that shared their ways of coping with stress. I was really touched that so many of you care about my wellbeing. 🥺 If you’re someone having trouble, the comment section is full of great tips on how to get to a more healthy place. ❤️

    Poništi
  15. 30. sij

    <serious> I'm OK. I had a recent health scare but I'm back to normal. I'm also going through some stuff right now which involves a lot of exhausting decisions. That's been draining. But I'm trying to stay active and avoid unnecessary stress like politics! </serious>

    Prikaži ovu nit
    Poništi
  16. 30. sij

    This was a bad attempt at a joke. The giveaway was supposed to be that git never brings anybody joy. 🙃 I know it's hard to tell when I'm being serious and I apologize for being a bit of sentient performance art piece.

    Prikaži ovu nit
    Poništi
  17. 29. sij

    My wife and I never talk to our kids. We communicate via reproducible notebooks. We require at least enough detail to replicate their analyses with an independent dataset. My daughter isn't even 2 and she rejects string theory as rampant speculation unsupported by available data.

    Poništi
  18. 29. sij

    A former boss once told me that I should document my lab work because what if I was hit by a bus and they couldn’t continue my project. I never documented anything for that job ever again.

    Poništi
  19. 29. sij

    I’ve been having a tough time lately. A severe loss of motivation. Anxiety. I struggle with simple everyday things like assessing the asymptotic properties of estimators and the curse of dimensionality. Even using git brings me no joy. Dear followers, what should I do?

    Poništi
  20. 28. sij

    Survivorship bias would be less of a problem in academia if we didn't have so much that we have to survive.

    Poništi
  21. 28. sij

    The replication crisis in psychology makes it seem like truth in psychology is elusive. Yet Netflix, Spotify, Facebook etc. are all independently doing psychological data analysis at scale and they probably wouldn't be multi-billion dollar companies if it didn't mostly replicate.

    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:

    ·