-
One of my 2019 goals was to start a blog. So, here’s the first of a series of tutorials on how to fit and evaluate Bayesian logistic regression models. Brought to you by
#rstats +#brms +@mcmc_stan +#tidybayes +#tidyverse +#ggplot2 +#LaplacesDemon.https://www.jamesrrae.com/post/bayesian-logistic-regression-using-brms-part-1/ …Prikaži ovu nit -
5/N: More documentation showing how to use
#tidybayes with#gganimate to construct hypothetical outcome plots (HOPs): http://mjskay.github.io/tidybayes/articles/tidy-brms.html#fitprediction-curves …pic.twitter.com/fvO6RlbpQOPrikaži ovu nit -
Alright
#tidybayes#rstats#bayes folks! I *finally* got around to overhauling the geoms in the {tidybayes} r pkg. I built a META-GEOM to do it: meet geom_slabinterval, stat_slabinterval, and a pile of handy shortcut geoms... [THREAD] (NB: this is not on the CRAN version yet!)Prikaži ovu nit -
Congrats and thank you for the updates
#tidybayes! I can’t wait to try out the new features. pic.twitter.com/oCkj8XgbQp -
That, friends, is a fine example of the great customer service you get from
@mjskay and his#tidybayes package. -
The biggest thing is the new slab+interval meta-geom, generalizing old
#tidybayes geoms and enabling a bunch of new ones. This is a flexible FAMILY of#ggplot geoms for visualizing probability distributions and uncertainty using slabs (densities, cdfs, etc), points, and intervalspic.twitter.com/G3eOpiKZO9
Prikaži ovu nit -
Pleased to announce that
#tidybayes v2.0 (SLABS FOR DAYS edition) hit CRAN today.#rstats Lots of new stuff in this version: A THREADPrikaži ovu nit -
The real question is
#tidybayes talk/workshop at#rstudioconf when? -
So, I love CRAN
#rstats for the consistency it brings to package quality, but restricting package documentation to less than 5MB *actively discourages* high-quality docs, especially for visualization packages. (currently preparing a#tidybayes update...)Prikaži ovu nit -
My
#rweekly_highlights this week: 1. What can social media do for academics by@statsgen. Looking forward to showing to colleagues. https://emitanaka.org/slides/ISIWSC2019/#1 … 2. {#tidybayes} update. Reminded me to look at adding {rbi} (i.e LibBi) support. http://mjskay.github.io/tidybayes/#rstatspic.twitter.com/1Iy4hl6WCo
Prikaži ovu nit -
Did you use
#tidybayes with geom_slabinterval and fisheye? -
This analysis uses a straightforward
@mcmc_stan model, implemented in#rstats with brms and#tidybayes. Will I become a Bayesian?!?!?????
https://twitter.com/StackOverflow/status/1164574943411146759 …Prikaži ovu nit -
Thurs 8:30AM at
#JSM2019 in CC-205 I'm on a panel with@JessicaHullman@LacePadilla & Mike Kirby talking uncertainty vis from the human perspective (how can we communicate uncertainty in ways people actually understand?) I'll also have#tidybayes hex stickers if anyone wants 'em pic.twitter.com/4ZNaPSdeay
-
An improved alternative to
@rlmcelreath's coeftab() function Better use of the#tidyverse, particularly purrr functions Greater emphasis on the#tidybayes package Updated workflow for defining custom distributions in#brms 2/nPrikaži ovu nit -
These are oversimplifications and basic simulations, but I found them really useful for building some intuition on these concepts. Thanks to
@rlmcelreath for such a great book and course! Models fit using#brms, plots with#ggplot2,#tidybayes and#ggdag. 5/6Prikaži ovu nit -
A HUGE thank you to
@mjskay for#tidybayes! You have no idea how much I appreciate this package... pic.twitter.com/Booy0jfip6 -
So, 3 yr old loves this sticker on my laptop. When she sees it, she says it’s time to ‘do rocketship things!’ Which mean plotting things in
#rstats with#ggplot. It started with sine waves, but now she’s really into crazy posterior visualizations with#tidybayes and#brms.pic.twitter.com/wppwjP6UAv
-
Once I've got the awesome model built, I've got tons of Qs I'd like to answer. That's where
#tidybayes comes in handy. Instead of working with averages, I can breath life into the model via realistic scenarios. 'tidybayes' lets me flexibly adjst to different conditions.
-
An alternative to correlation heatmaps, but with uncertainty. Estimated using
@mcmc_stan +#brms, munged and visualized with#tidybayes +#ggplot2 +#ggridges#rstats. cc@paulbuerkner@ClausWilke. See bottom of https://github.com/mjskay/uncertainty-examples/blob/master/multivariate-regression.md …pic.twitter.com/7Un5HT0r0e
Prikaži ovu nit -
ZOMG - Posthoc contrasts posteriors with
#emmeans,#tidybayes, and#brms - https://gist.github.com/jebyrnes/d1bdea4ad4c8736c4b9e7ac290e8c940 …#rstatsPrikaži ovu nit
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.