benschneider

@benschneider@mastodon.social

Stats, data science, R, and survey methods. Sometimes posts about politics and dogs.

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

grimalkina, to random
@grimalkina@mastodon.social avatar

Some comments on survey response rates and recruiting for anyone wondering about that:

https://mastodon.social/@grimalkina/111846251573308426

benschneider,

@grimalkina like you say, a 10% response rate is unsurprising for a typical business survey. So beyond reporting response rates, a nonresponse bias analysis would be helpful for judging the data quality. This R package and included lit references are useful for that:
https://cran.r-universe.dev/nrba

davidbraze, to random
@davidbraze@mstdn.social avatar

within the last year or so @Posit has taken a big tranche of venture capital. VC wants one thing: a massive return, 10x minimum. there are two ways to get that. first is to take a company public. I don't think that's likely here. second is a buy out by a major player like Oracle, Microsoft, Amazon, or another of that ilk. I guess this is what posit's sugar daddy is likely angling for. this isn't unprecedented in the world. who else remembers Revolution R?

https://mastodon.social/@awong234/111751453549394950

benschneider,

@davidbraze @Posit how did you hear/read about Posit and VC funding? I just assumed that Posit was doing layoffs because of the common tech story right now of higher interest rates + having overhired during the low interest rates in 2020 and the economic recovery period

andrew, to random
@andrew@fediscience.org avatar

I've been using Make.com to run automated stuff for a while, but didn't realize that it can work with branches, so now my Goodreads RSS feed magically gets fed to a Google sheet and gets autoposted to Mastodon

It's like modern version of Yahoo! Pipes!

benschneider,

@smach @andrew I was curious after reading your question Sharon and looked through Andrew’s Quarto book and found this, which you might find interesting:

https://www.andrewheiss.com/blog/2024/01/12/diy-api-plumber-quarto-ojs/_book/deploying.html

mattcowgill, to random
@mattcowgill@mastodon.social avatar

am I right to think there's way fewer interesting new R packages emerging lately?

If not: link pls

If so: why? Is it that the ecosystem is just more stable/mature now? Or energy has moved to Python and/or LLMs?

benschneider,

@mattcowgill I would guess that a big part of that impression is because Posit is focusing less on releasing brand new R packages and focusing more on improving existing packages and adding interfaces to its general tools like Quarto or Shiny. Lots of exciting stuff going on with Quarto and Shiny right now.

andrew, to random
@andrew@fediscience.org avatar

5 of 5 stars to Artificial Condition (The Murderbot Diaries, #2) by Martha Wells https://www.goodreads.com/review/show/6037319241?utm_medium=api&utm_source=rss

benschneider,

@andrew I actually just finished this one too and really enjoyed it. Really enjoying this series so far.

mmaechler, to random

r-project.org TLD needed registration renewal... and we found out considerably later than we should have, i.e. several hours after it stopped working ;-(( Finally solved by paying online w/ my own CC... -- hooray!

benschneider,

@hrbrmstr @mmaechler I’m grateful the issue is fixed, but this is one of many signs that CRAN’s organizational model and processes need some serious improvements to better serve the massive R community. Or maybe just the community shouldn’t be so dependent on CRAN.

hrbrmstr, to random
@hrbrmstr@mastodon.social avatar

The cowards in the GOP just handed ‘Murica over to fascists.

benschneider,

@hrbrmstr It’s pretty infuriating seeing Republicans agree on the speakership of a fascist who worked his hardest to overturn our democratic elections

andrew, to random
@andrew@fediscience.org avatar

Now that my new starter is alive and warm and healthy, it's time to re-break out my 2020-era package: {sourrr}

https://github.com/andrewheiss/sourrr

benschneider,

@andrew This is awesome! I was actually thinking of doing some sourdough recipe planning in R this weekend. Currently reading the section of Bread Bible on percentages, and I like the idea of an R function that helps with all this.

gvwilson, to random
@gvwilson@mastodon.social avatar

Do any of my friends have pointers to resources on statistical generation of synthetic data? Assume the reader/user is comfortable with Python and R but hasn't done a stats course in…a while. thanks

benschneider,

@gvwilson The “synthpop” R package is excellent for when you have an existing dataset and you want to create a synthetic version (e.g., for sharing data while protecting research participants’ confidentiality)

benschneider, to random

After days of headaches with hard-to-reproduce checks, I really couldn't agree more with the points made here by @omearabrian

https://brianomeara.info/posts/phylotasticruniverse/

benschneider, to random

Any advice from the hivemind on how to debug and test the ATLAS and MKL tests on CRAN? How on earth can someone outside CRAN reproduce that environment?

https://cran.r-project.org/web/checks/check_results_svrep.html

benschneider,

@gaborcsardi I'm really grateful for this suggestion and for this resource. It's filling a big gap caused by some of CRAN's more unfortunate policies.

benschneider,

@gaborcsardi Thanks so much. This is really impressive how quickly you turned this into a new rhub feature.

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