@1010is10@fosstodon.org
@1010is10@fosstodon.org avatar

1010is10

@1010is10@fosstodon.org

Helping others to learn from data.
#PyMC #Bayesian #Bayes #statistics #python

This profile is from a federated server and may be incomplete. Browse more on the original instance.

1010is10, to random
@1010is10@fosstodon.org avatar

@kev is fosstodon excluded from https://joinmastodon.org/servers because we're not currently accepting new accounts?

1010is10, to random
@1010is10@fosstodon.org avatar

boygenius is going on "hiatus" :sadmsn:
https://www.rollingstone.com/music/music-news/boygenius-announce-hiatus-1234959868/
@btp

Cmastication, to random
@Cmastication@mastodon.social avatar

Same. Sadly.

1010is10,
@1010is10@fosstodon.org avatar

I assume that is one of a series of photographs, each documenting a thing that man does not have. The collection would make a nice show for some gallery somewhere.
@Cmastication

Cmastication, to random
@Cmastication@mastodon.social avatar

My sister’s house is totally gussied up for the holidays.

1010is10,
@1010is10@fosstodon.org avatar

Really ties the room together.
@Cmastication

btp, to random
@btp@fosstodon.org avatar

Some of these replies are hilarious.
https://mastodon.social/@Gargron/111587088958531028

1010is10,
@1010is10@fosstodon.org avatar

I did manage to find some other accounts that do give me the menu you showed. Not sure why it only comes up with some servers/accounts though.
@btp

Cmastication, to random
@Cmastication@mastodon.social avatar

One of my frustrations with the mandatory IT security training we're all forced to take at work is that most of these punish us for being risk averse. I would not open any of the emails they show me. But I get dinged for that. But my approach is less likely to result in malware infestation.

Of course, given my druthers, I would also disassemble my computer, put the bits in a box, light that box on fire, and walk into the woods in a dramatic scene backlit by the burning box of computer bits.

1010is10,
@1010is10@fosstodon.org avatar

The last security training I completed had you go through and read individual "emails". You had to choose to A) delete the message B) report the message to IT as suspicious or C) click the link/download the attachment. As you noted, sometimes the correct answer as A (B==incorrect) and sometimes the correct answer was B (A==incorrect). I didn't understand. If the training is unsuccessful in improving people's discriminative abilities, it is actively harmful.
@Cmastication

modrak_m, to academicchatter
@modrak_m@fediscience.org avatar

Has anyone seen an implementation of scanning and machine evaluating multiple choice exams that is not terrible for students?

Things I don't like:

  • requiring separate answer sheet (error-prone)
  • unstapling multiple page exams for scanner
  • exam not physically corrected, harder for students to review their exam afterwards

Asking for a friend...
@academicchatter

1010is10,
@1010is10@fosstodon.org avatar

I ditched in-person exams during COVID and I'm never going back. Online testing has its own issues, but it's less crazy than using thousands of sheets of paper to conduct a handful of 1-hour exams.
@modrak_m @academicchatter

codinghorror, to random

Wow, the smiley face Mars crater from Watchmen (1986).. is real?? 🤯 https://en.m.wikipedia.org/wiki/Galle_(Martian_crater)

1010is10,
@1010is10@fosstodon.org avatar

"According to Gibbons, the similarity 'was almost too good to be true. I worried that if we put it in, people would never believe it.'" I guess he was correct!
@codinghorror

JoranJongerling, to academia
@JoranJongerling@mastodon.social avatar

Question for my fellow academics:

How many concurrent projects is a comfortable number for you (i.e., allows you to work without feeling rushed)?

And what is the optimal number of meetings a day (i.e., that allows you to move things along, but also leaves you enough time for other things)?

#AcademicMastodon #Academia @academicchatter

1010is10,
@1010is10@fosstodon.org avatar

The number of projects is entirely dependent on the number of collaborators (including advisees). More collaborators means I can participate in more projects. How thinly you spread yourself juggling multiple things seems to be a matter of taste and (to some extent) experience. I wouldn't know how to count the number of projects I am involved in.
@JoranJongerling @academicchatter

1010is10,
@1010is10@fosstodon.org avatar

It's definitely all about dividing/distributing projects. Once you move into the position to advise/supervise on projects, the idea of juggling more things becomes a lot less insane-sounding. Maybe I'm asked to drop in on a monthly basis (or as-needed). Or maybe I have some meetings to put a grant proposal together, but the effort is time-limited (because of the grant deadline). Do these things count as "projects"? Not sure. But I sure have a lot of them!
@JoranJongerling @academicchatter

1010is10,
@1010is10@fosstodon.org avatar

Yup. And as I have gained experience, I end up "doing" far less and "advising" far more. So I have many more pieces of pie, but each has grown smaller.
@JoranJongerling @academicchatter

1010is10, to random
@1010is10@fosstodon.org avatar

The children didn't take all of my Halloween candy. Now what do I do?

1010is10,
@1010is10@fosstodon.org avatar

Escalate immediately. I like it.
@kierkegaank

petersuber, to random
@petersuber@fediscience.org avatar

Question: If a journal receives a submission within its scope, and has trouble finding referees, how long should it wait, or how long should it keep trying, before it notifies the authors and invites them to submit the manuscript elsewhere?

I'm prompted to ask this question by the case described in this article, which is about "handling editors" rather than referees.
https://jkms.org/DOIx.php?id=10.3346/jkms.2023.38.e354

1010is10,
@1010is10@fosstodon.org avatar

I suspect that this will be a question that becomes increasingly relevant as time goes on. What happens to the traditional journal model if editors can't find reviewers (or quality reviewers)? All evidence suggests that "traditional journals/publishers go away without a fight" isn't likely.
@petersuber

andrew, to random
@andrew@fediscience.org avatar

Q about stuff: I'm finding the probability of direction (proportion of posterior that's >0 or <0), but I never know how to report these, since sometimes they're positive and sometimes they're negative. My current solution is to use a column for each direction—is there a better way tho?

1010is10,
@1010is10@fosstodon.org avatar

@mjskay @andrew I agree with this. These sorts of tests against zero are almost always less intuitive than tests of X>Y. Testing against zero and then seeing "big p values" also has the strong possibility of getting people into an NHST mindset (which causes all sorts of interpretational issues).

1010is10,
@1010is10@fosstodon.org avatar

@mjskay @andrew ... or small p values. I avoid using "p" notation whenever possible when reporting Bayesian analyses. Readers just have too strong a prior (!) that they are about to read an NHST analysis.

Private
1010is10,
@1010is10@fosstodon.org avatar

Definitely been poring over to documentation. I have everything working. I'm just not sure if I can configure the bibliography to appear in a single location within the book instead of appearing at the bottom of each chapter. :blobcatshrug:
@kwalz @rstats

1010is10,
@1010is10@fosstodon.org avatar

@kwalz @rstats Huh. I guess this bit does it. The documentation text here is very mysterious. I had read this multiple times, but didn't know what it was supposed to mean/do. I guess I should have just blindly tried random stuff!
https://quarto.org/docs/books/book-structure#references

1010is10,
@1010is10@fosstodon.org avatar

@andrew @scholzmx Yup, that I found. My solution, which appears to work, is to create a new part (it could be a chapter/part) called references.qmd and fill it with the text found here: https://quarto.org/docs/books/book-structure#references

andrew, to random
@andrew@fediscience.org avatar

mid-2023-era social media is exhausting

1010is10,
@1010is10@fosstodon.org avatar

@andrew I just pulled the GSS (1972-2016) and this was the list of social media platforms they asked about. So quaint!
TWITTER
FACEBOOK
INSTAGRM
LINKEDIN
SNAPCHAT
TUMBLR
WHATSAPP
GOOGLESN
PINTERST
FLICKR
VINE
CLSSMTES

Private
1010is10,
@1010is10@fosstodon.org avatar

@gavintlbrown @rstats Super cool. I will take a look!

1010is10,
@1010is10@fosstodon.org avatar

@twm @rstats Yeah, I had the General Social Survey and the World Values Survey on my list of candidates (as well as some large-scale US surveys). It slightly difficult because I want something big but not too big, complex but not too complex, and messy (e.g., missingness) but not too messy. Basically I need the Goldilocks of data sets. But I will add the European social survey to the list!

Private
1010is10,
@1010is10@fosstodon.org avatar

@rstats Maybe RStudio is only aware of quarto elements in "visual editing mode"? Except that RStudio previews elements such as inline images and LaTex equations just fine in the non-visual markdown editor. Strange.

1010is10, to rstats
@1010is10@fosstodon.org avatar

deleted_by_author

    •
    1010is10,
    @1010is10@fosstodon.org avatar

    @bartlettje @rstats @debruine @HelenaPaterson I actually ran across that package with what feeble googling I tried. It seemed to be capable of much more than what I (think I) need. But maybe it would work.

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • megavids
  • thenastyranch
  • DreamBathrooms
  • ethstaker
  • InstantRegret
  • Youngstown
  • magazineikmin
  • osvaldo12
  • slotface
  • khanakhh
  • rosin
  • kavyap
  • everett
  • tacticalgear
  • JUstTest
  • ngwrru68w68
  • GTA5RPClips
  • cisconetworking
  • mdbf
  • cubers
  • Durango
  • anitta
  • modclub
  • normalnudes
  • tester
  • Leos
  • provamag3
  • lostlight
  • All magazines
    •