New post: "How to get good with R", where I ramble on some ideas on getting better with R - keen to hear what people think I've missed and discuss the topic!
For me, what really helped was learning via Twitter how to use nest_by() to iterate over rows of list-columns. Nesting is such a nifty concept and I find myself using it more often than for loops these days. I still struggle with its subtleties but for the most part I can pull it off.
My current companion as I reply to accumulated emails, pictured. #Catstodon
Came up with a good metaphor in teaching today and could see that it helped students grasp a difficult concept. I love it when their faces register a light bulb going off.
Listened to part of a good podcast on the way home from work today, an episode of If Books Could Kill.
@scheidegger I thought it is the fact that it prompts you to constantly update everything. One of my clients works on a mac and this prompting behaviour is maddening.
@dstephenlindsay The biggest stress is the birth itself, because you can never quite anticipate how it will unfold. A friend of mine gave birth in the hospital elevator as she was being wheeled into the operating room. 🤭 But once that’s out of the way, things will be easier to handle for all involved.
@healthstatsdude The EM algorithm is leaving not much choice for those of us who are still hanging around on the site formerly known as Twitter. We have to take our toys and play somewhere else. For free! 🐘💙
Discover the magic of integrating a serverless #rstats#ahiny app into your #Quarto document using #RShinylive! ✨ Learn step-by-step and elevate your interactive data storytelling game. 🔥
@coatless Ok, then R users like myself will be happy to extend our gratitude not just to yourself, but to George and Lionel. This is the kind of work that will be really impactful on our workflows. I’ve already seen people get really excited about what can be accomplished with these tools! So thank you to all 3 of you! :BlobhajHeart: :BlobhajTinyHeart: :ablobcatheart:
@coatless Thank you also for your thoughtful answer. This WASM thing sounds promising while also very complex for someone like me. But given how prevalent Bayesian methods are now, I think they will have to be accommodated one way or another at some point.
@coatless You’re so kind to call me a fellow Bayesian. I am really a Baby Bayesian hoping to make it to Teenage Bayesian sometime soon. 😁I was born Frequentist, you see…🤣
I will definitely reach out after giving this a try - have to sit down with it this week and get it to work first. Will come handy in both consulting and teaching!
@DM_Ronin The way I read this is that it’s a complicated story and mental health issues may be at play. I hope you’ll manage to find out more about what has transpired since and that the person in question is safe and doing better now.
@hrbrmstr@MatthewBJane Nice answers! In R, loess smoothers can be used with GAM models too (including for count reaponse variables) via the lo() smoother available in packages like gam and gamlss.
coding stuff that has to do with people's money is just about the most terrifying stuff I've ever programmed and I hope I don't end up in jail or bankrupt
Just realizing that the two nicest people I follow on any part of the internet (mainly here and Twitter) are both people with very pretty names, are in tech, and are residents of the less insane part of North America. @isabellaghement@AmeliasBrain
@jerryD@AmeliasBrain Just saw your comment, Jerry! How sweet of you to make it. I try my best to be nice (with various degrees of success) and it’s touching when other people notice that. So many times on Twitter I feel like nobody pays attention to what I have to say - your comment is most validating. ❤️