There are new videos for Bayesian and frequentist side-by-side.
Eero Liski, a statistician at the Natural Resources Institute Finland, has made tutorial videos that introduce Bayesian and frequentist data analysis, side-by-side. The first of the video series is available here.
Thank you, Eero, for making these videos!
The videos were composed entirely independently from me, but they feature the R Shiny App I created a few years ago. The written (no-video) tutorial for that Shiny App is here.
StanCon 2023 is happening June 20-23 (2023).
Submit talks, tutorials, or sessions by April 30:
We are interested in a broad range of topics ... including:
- Applications of Bayesian statistics using Stan in all domains
- Software development to support or complement the Stan ecosystem
- Methods for Bayesian modeling, relevant to a broad range of users
- Theoretical insights on common Bayesian methods and models
- Visualization techniques
- Tools for teaching Bayesian modeling
See details at the convention website: https://mc-stan.org/events/stancon2023/
A recent post pointed out three changes to DBDA2E programs; now there is one more. You can get the updated versions by downloading the entire new zip file from the bottom of the software page at https://sites.google.com/site/doingbayesiandataanalysis/software-installation
The most recent change affects the openGraph() function in the script, DBDA2E-utilities.R. This function for opening graphics windows has been updated to work for recent versions of MacOS and Unix. However, I have not personally tested the new function on MacOS and Linux, instead relying on the kind suggestion of reader Joseph Skudlarek. Thank you, Joseph!
Three R scripts within the set of DBDA2E programs have been updated to work properly with R4.0+. You can get the updated versions by downloading the entire new zip file from the bottom of the software page at https://sites.google.com/site/doingbayesiandataanalysis/software-installation
The three changes:
Thanks to Tom Busey for noticing and fixing the class() issue, thanks to Han Diesfeldt for pointing out a problem when running -MpoissonExp.R, and thanks to Artur Araujo for noticing and fixing the issue in -MnormalHet.
These three changes follow a raft of changes previously made to accommodate R4.1, as previously posted at http://doingbayesiandataanalysis.blogspot.com/2021/07/dbda2e-r-scripts-updated-for-r-41.html
ChatGPT is fun to play with but is (for now at least) terrible at creating poems, including poems about Bayesian statistics. Here are my attempts to have ChatGPT produce poems like those that begin each chapter of DBDA2E. Or in any other style.
My prompt: Write a single poetic quatrain about Bayesian statistics. Use dactylic tetrameter and an AABB rhyme scheme.
ChatGPT's reply:
Bayesian stats have come to stay
They help us make predictions, hooray!
From probabilities and data sets
They estimate and make forecasts
They start with a prior belief
And update it with new relief
The posterior is then retrieved
A revised view, it's not deceived
While this is cute and is on topic, it is not a single quatrain and it is not dactylic tetrameter. And it lucked out with AABB rhyme scheme, because that's all it does. Here I ask for an ABAB rhyme scheme:
Write a single poetic quatrain about Bayesian statistics. Use dactylic tetrameter and be sure to use an ABAB rhyme scheme.
ChatGPT's reply:
Bayesian stats are here to stay
In fields of science, they convey
A flexible method, one that adapts
To changing evidence, it reacts
It deals with uncertainty and doubt
In a logical way, it sorts it out
It starts with a prior belief
And updates it with new relief
Sound familiar? It's essentially the same as before.
When I ask ChatGPT to "Write a poem about Bayesian statistics in free verse style" it again replied with pairs of rhyming couplets.
I've found that ChatGPT's current concept of a poem is merely this: every stanza consists of a pair of rhyming couplets (i.e., AABB rhyme scheme), usually but not always with four stressed syllables per line (i.e., tetrameter), and with varying metrical feet (i.e., could be iambic, trochaic, anapestic, dactylic, etc., at random).
To turn the tables, I gave myself a prompt and allowed myself only a few minutes and a single try to respond. Prompt to self: Write a single poetic quatrain about ChatGPT. Use dactylic tetrameter and be sure to use an ABAB rhyme scheme.
Self's reply:
ChatGPT is a wonderous interface
giving us couplets that pique and amuse (sometimes).
I still prefer the delights of a human face
smiling at doggies that play and confuse (but rhyme).
