Lightnews — Scholar-powered news

Reposted by Wang minjie

Solomon Kurz

@solomonkurz.bsky.social

www.amazon.com/Doing-Bayesi...

Doing Bayesian Data Analysis: A Tutorial with R, Stan, brms, and the tidyverse

Doing Bayesian Data Analysis: A Tutorial with R, Stan, brms, and the tidyverse - Kindle edition by Kruschke, John, Kurz, Solomon. Download it once and read it on your Kindle device, PC, phones or tablets. Use features like bookmarks, note taking and highlighting while reading Doing Bayesian Data Analysis: A Tutorial with R, Stan, brms, and the tidyverse.

www.amazon.com

October 11, 2025 at 5:07 AM

Reposted by Wang minjie

Jan Broder Engler

@jbengler.de

In case you ever wondered about the differences between magrittr pipe and base pipe 🤔

This table is taken from a great stackoverflow answer by @GeorgKindermann

stackoverflow.com/questions/67...

#rstats #dataviz #phd

January 23, 2025 at 4:59 PM

Reposted by Wang minjie

Crystal Lewis

@cghlewis.bsky.social

Trying out dplyr::consecutive_id() for a project today. #rstats

It generates a unique identifier that increments every time a variable (or combination of variables) changes.

March 18, 2025 at 8:39 PM

Reposted by Wang minjie

Rodrigo Barreiro

@rodrigo404.bsky.social

Just one more week to go 😮‍💨

Finished my #day24 of the #30DayChartChallenge using some WHO data.

Code at: github.com/barreiro-r/3...

#rstats #dataviz

April 25, 2025 at 5:36 PM

Reposted by Wang minjie

Dirk Eddelbuettel

@eddelbuettel.com

The "Getting Started in R - Tinyverse Edition" eight-page pdf guide now has a 2nd edition using, appropriately, `tinyplot` as the plotting package.

See github.com/eddelbuettel... for more.

#rstats

Screenshot of the top parts of pages 5 and 6 of 'Getting Started in R - Tinyverse Edition' at https://github.com/eddelbuettel/gsir-te/

April 20, 2025 at 7:23 PM

Reposted by Wang minjie

Andrew Heiss

@andrew.heiss.phd

Thing I just learned in #rstats: unz() lets you connect to a .zip and load files from inside it without actually unzipping it (great for a file I'm working with that's 30 MB zipped and 1+ GB unzipped, with multiple CSVs in it)

# unz() lets you connect to a .zip and treat it like a mini file system,
# and you can load files from inside it
one_zipped_csv_among_others <- readr::read_csv(
unz("lotsa_zipped_csvs.zip"), "one_csv.csv"
)

# readr::read_csv() can read a .zip with a single CSV in it
one_zipped_csv <- readr::read_csv("big_zipped_file.zip")

April 18, 2025 at 6:19 PM

Reposted by Wang minjie

Nicola Rennie

@nrennie.bsky.social

A quick plot for #TidyTuesday this week - celebrating the addition of the penguins data into base R 🐧 I used {ggdist} to plot the distribution of body weights with four different chart types in one! 📊

I couldn't quite decide whether I prefer the light or dark version💡

#RStats #DataViz #ggplot2

Three box plot/density plot/rainfall plots showing body weight for three penguin species, with Gentoo significantly higher. Colours also show density, and species. Background is light with dark text.

April 16, 2025 at 3:18 PM

Reposted by Wang minjie

Jumping Rivers

@jumpingrivers.com

New version of R is out!

Our Data Scientist, Russ Hyde, has put together a quick review of the key features and changes in R 4.5 — from new language features to graphics updates and more.

📝 Read the full blog post here: www.jumpingrivers.com/blog/whats-n...

#rstats #Rprogramming #opensource

What's new in R 4.5.0?

Here we summarise some of the more interesting changes that have been introduced in R 4.5.0.

www.jumpingrivers.com

April 11, 2025 at 10:34 AM

Reposted by Wang minjie

John Paul Helveston

@jhelvy.bsky.social

Made an app so you can view daily updates of this chart & compare other administrations and metrics like unemployment and inflation 🤓

It updates daily, so check it tomorrow to see today's continued US market collapse 🤠

jhelvy.github.io/potus-econ-s...

Built with #rstats #shinylive #quarto

Screenshot of my POTUS Economic Scorecard app showing S&P 500 performance during the first 100 days following presidential inaugurations. The graph reveals Biden (2021) at +8.5%, Obama (2013) at +7%, Trump (2017) at +5%, and Trump (2025) at -16.1%. The interface includes options to select different economic indicators, adjust time periods, and filter by political party. The data visualizes a significant market decline during the current Trump administration compared to positive performances in previous administrations' early days.

April 7, 2025 at 7:46 PM

Reposted by Wang minjie

tj mahr 🦃

@tjmahr.com

"what if i make a one-off Stat ggproto object?", i thought

$StatRightEnd <- ggproto( "RightEnd", Stat, compute_group = function(data, scales) { data[which.max(data$x), ] } ) ggplot(grid2) + aes(mean_log_prob, plogis(preds)) + geom_line(aes(group = item), linewidth = .5) + geom_text( aes(label = tocs_prompt, group = tocs_prompt), stat = StatRightEnd )$ plot of curves with a label on the right end

plot of curves with a label on the right end

March 20, 2025 at 8:31 PM

Reposted by Wang minjie

Benjamin Hlina, PhD

@benjaminhlina.bsky.social

Trophic Ecologists - new pkg alert - {trps} (pronounced ‘tropes’): Bayesian Trophic Position Models using 'Stan'. Estimates trophic position using equations from Post (2002), Vander Zanden & Vadeboncoeur (2002), & Heuvel et al. (2024).

benjaminhlina.github.io/trps/

#rstats #ecology #foodwebs

Bayesian Trophic Position Models using stan

Bayesian trophic position models using stan by leveraging brms for stable isotope data. Trophic position models are derived by using equations from Post (2002) <doi:10.1890/0012-9658(2002)083[0703:USI...

benjaminhlina.github.io

March 22, 2025 at 7:45 PM

Reposted by Wang minjie

Matthew Kay

@mjskay.com

A wrapper around the builtin #rstats splinefun() function should work with ggplot2::stat_smooth() --- see code in alt text

$df = data.frame(x = -1:10, y = c(-3,2,1,2,5,3,6,7,3,6,10,11)) smooth_spline_x = \(formula, data) { X = model.matrix(formula[-2], data) # this is dumb but good enough for a hack X %*% rep(1, ncol(X)) } smooth_spline = \(formula, data, ..., weights = NULL) { x = smooth_spline_x(formula, data) y = eval(formula[[2]], data, environment(formula)) structure( splinefun(x, y, ...), class = c("smooth_spline", "function"), formula = formula ) } predict.smooth_spline = \(object, newdata, ..., weights = NULL, se.fit = FALSE) { fit = object(smooth_spline_x(attr(object, "formula"), newdata)) if (se.fit) { list(fit = data.frame(fit = fit, lwr = 0, upr = 0), se.fit = NA_real_) } else { fit } } df |> ggplot(aes(x, y)) + stat_smooth(formula = y ~ x, method = smooth_spline) + geom_point()$

March 17, 2025 at 9:59 PM

Reposted by Wang minjie

Michael Friendly

@datavisfriendly.bsky.social

📊 #psy6135 #rstats Today's topic: Visualizing Uncertainty
Topics: Visualizing distributions, Error bars, Bayesian stuff, fitted curves, ...
Thx to @elibryan.bsky.social, @mjskay.com, @clauswilke.com, @cedricscherer.com and other folks I stole from.
💻 Slides-- friendly.github.io/6135/lecture...

March 14, 2025 at 8:26 PM

Reposted by Wang minjie

Nicola Rennie

@nrennie.bsky.social

Code: github.com/nrennie/tidy...

tidytuesday/2025/2025-03-04 at main · nrennie/tidytuesday

This repository contains the R code used to produce my visualisations for the #TidyTuesday challenges. - nrennie/tidytuesday

github.com

March 7, 2025 at 10:49 PM

Reposted by Wang minjie

Federica Gazzelloni

@fgazzelloni.bsky.social

🔔 I'm thrilled to introduce my new series! I've been working hard on this project, and I can't wait for you to see it.

🤿 Check out this clip to get a sneak peek: buff.ly/zUowPHW

Let me know what you think and stay tuned for more updates!

✂️ New Series: Health Data Science: Metrics, AI & Spatial Modelling

38 seconds · Clipped by Federica Gazzelloni · Original video "Health Data Science: Metrics, AI & Spatial Modelling - 01" by Federica Gazzelloni

buff.ly

March 5, 2025 at 8:50 AM

Reposted by Wang minjie

Steven Ponce

@sponce1.bsky.social

📊 #TidyTuesday – 2025 W07 | Agencies from the FBI Crime Data API
.
🔗: stevenponce.netlify.app/data_visuali...
.
#rstats | #r4ds | #dataviz | #ggplot2

Seven small maps of the continental United States show law enforcement agencies' geographic distribution by type. City agencies (11,251) and County agencies (3,023) show the densest coverage across the country. State Police (882) are concentrated in the Northeast. Other State Agencies (715) cluster in the Southeast. University/College agencies (671) are spread across the country, with higher density in the East. Other agencies (430) show scattered distribution. Tribal agencies (185) are primarily located in Western states.

February 14, 2025 at 10:48 AM

Reposted by Wang minjie

Vincent Arel-Bundock

@vincentab.bsky.social

Rdatasets is a collection of 2300 free and documented datasets in CSV format. It's a great resource for teaching and exploration!

The new `get_dataset()` function from the {marginaleffects} 📦 allows you to search and load them directly in #Rstats.

vincentarelbundock.github.io/Rdatasets/ar...

February 14, 2025 at 12:54 PM

Reposted by Wang minjie

Konsta Happonen

@konsta.happonen.eu

Happy Valentine's Day (p<0.05). #rstats

## A scatterplot of a heart tilted 45° to the right with a regression line overlaid. The title says Happy Valentine's Day with p < 0.05

library(tidyverse)
library(ggview)
library(extrafont)

## Sample from a heart curve
t <- seq(0,2*pi,length.out = 400)
x <- 16*sin(t)^3
y <- 13 * cos(t) - 5 * cos(2*t) - 2*cos(3*t) - cos(4*t)

dd <- matrix(c(x,y),ncol=2)

# Rotate 45 degrees
theta <- pi*-0.25
rotmat <- matrix(c(cos(theta),sin(theta),-sin(theta),cos(theta)), ncol = 2)
dd2 <- t(rotmat %*% t(dd))
colnames(dd2) <- c("x","y")
dd2 <- dd2 |> as_tibble()

# Check p-value
lm(y~x, data = dd2) |> summary()

# Publish or perish
p_heart <- dd2 |>
ggplot(aes(x,y)) +
geom_point(size = 0.01) +
stat_smooth(formula = y~x,method = "lm",
color = "firebrick",
fill = "hotpink") +
coord_fixed() +
theme_minimal(base_family = "Karla") +
theme(panel.grid.minor = element_blank()) +
labs(title = "Happy Valentine's Day",
subtitle = "with p < 0.05",
x = NULL, y = NULL) +
canvas(width = 4, height = 4, dpi = 300)

p_heart |> save_ggplot("sydän/sydän.png", device = png)

February 14, 2025 at 11:19 AM

Reposted by Wang minjie

Robert (Bob) Kubinec

@rmkubinec.bsky.social

I asked chatGPT to define a new statistical distribution no one had used before, then write R code to simulate the model and fit it with Stan. It created a "Bimodal Exponential-Beta Distribution" (a mixture on the domain (0,1)).

and... it works 😱

code here:
gist.github.com/saudiwin/081...

#rstats

ChatGPT-created statistical distribution with R and Stan Code:

ChatGPT-created statistical distribution with R and Stan Code: - chatgpt_exponential_beta_mixture.R

gist.github.com

December 4, 2024 at 2:20 AM

Reposted by Wang minjie

Andrew Heiss

@andrew.heiss.phd

New blog post! Probability math is hard, but simulating real world data-generating processes is fun. Here's a neat exploration of how to find the probability that everyone in a household has birthdays in the same 6-months, using CDC day-of-birth statistics #rstats www.andrewheiss.com/blog/2024/05...

Radial plot showing 8 birthdays occurring in the same 6-month span between May and November

Plot showing how the simulated probability that everyone in a household has birthdays in the same 6-month span decreases as household size increases

$These days of the year now match the actual distribution of birthdays in the United States. If we simulated thousands of birthdays, we'd get more in September, fewer on the 13th of each money, and far fewer around Thanksgiving and Christmas. We can now update our simulation to use this more realistic distribution of birthdays: ```{r} #| label: fun-simulate-prob-real simulate_prob_real <- function(n, num_simulations = 1000) { results <- map_lgl(1:num_simulations, ~{ birthdays <- sample( prob_per_day$day_of_year, size = n, replace = TRUE, prob = prob_per_day$prob ) birthdays_doubled <- sort(c(birthdays, birthdays + 366)) any(map_lgl(1:n, ~ birthdays_doubled[.x + n - 1] - birthdays_doubled[.x] <= (366 / 2))) }) mean(results) } ```$ Heatmap plot showing the relative average frequencies of being born in the US

Heatmap plot showing the relative average frequencies of being born in the US

May 3, 2024 at 3:16 PM

Reposted by Wang minjie

Chris Brownlie

@bsky.chrisbrownlie.com

this week in #rstats:
- R 4.4.3 released today! 🎁
- Air: the new superfast R formatter @davisvaughan.bsky.social 💨
- upcoming {rix}/Nix webinar @brodriguesco.bsky.social 📦
- intro to {ellmer} LLM pkg @posit.co 🤖
- tidymodels Q1 2025 update 📊

and more! ✨

www.linkedin.com/pulse/week-r...

This week in R (2025-02-28)

A brand new superfast R formatter; a new version of R; whats new in tidymodels?; useR! deadline extension; get to know {rix}; introducing {ellmer} and more!

www.linkedin.com

February 28, 2025 at 11:21 AM

Reposted by Wang minjie

Ed Hagen Twitter archive

@twitterarchive.edhagen.net

The #rstats #tidyverse tibble function builds columns sequentially, so you can refer to earlier columns when defining later ones, a feature I use all the time.

January 26, 2025 at 9:40 PM

Reposted by Wang minjie

Benjamin Rosenbaum

@benrosenbaum.bsky.social

I completely re-worked my course "Introduction to Bayesian statistics with brms" and taught it for the 1st time this week. It is meant as a tutorial for ecologists, but should be general enough for other sciences as well
github.com/benjamin-ros...
#stats #Rstats #brms #Stan #Bayesian

GitHub - benjamin-rosenbaum/bayesian-intro: Introduction to Bayesian statistics

Introduction to Bayesian statistics. Contribute to benjamin-rosenbaum/bayesian-intro development by creating an account on GitHub.

github.com

February 28, 2025 at 9:19 AM

Reposted by Wang minjie

Travis Dawry

@tdawry.bsky.social

I like @andrew.heiss.phd, because he's insightful and by all accounts is a genuinely nice guy.

With that said, this (building on @grrrck.xyz's work) is invaluable for making students more comfortable with the second-best #rstats library!

Andrew Heiss @andrew.heiss.phd · Nov 18

More helpful (at least for me) resources from the blog archive: Seven (7!) tidyexplain-esque animations (downloadable and CC-licensed) showing how {dplyr}'s mutate(), summarize(), group_by(), and ungroup() all work together #rstats #dataskyence www.andrewheiss.com/blog/2024/04...