econmaett
@econmaett.github.io
❤️📊 | 🗣️DE|EN|FR | #rstats | #econsky
Reposted by econmaett
Finally got around to reading this and it's a good post except it's odd in my opinion to compare plotting rasters with ggplot2 to plotting rasters with any other package but never mention tidyterra, feels like it's a gamechanger compared to geom_raster #RSpatial
dieghernan.github.io/tidyterra/in...
dieghernan.github.io/tidyterra/in...
November 20, 2025 at 5:25 AM
Finally got around to reading this and it's a good post except it's odd in my opinion to compare plotting rasters with ggplot2 to plotting rasters with any other package but never mention tidyterra, feels like it's a gamechanger compared to geom_raster #RSpatial
dieghernan.github.io/tidyterra/in...
dieghernan.github.io/tidyterra/in...
Reposted by econmaett
After years of working with Quarto, I've refined a set of editor settings that significantly improve document editing efficiency.
My latest blog post shares these battle-tested configurations.
mickael.canouil.fr/posts/2025-1...
#Quarto #VSCode #Positron #Productivity #DataScience
My latest blog post shares these battle-tested configurations.
mickael.canouil.fr/posts/2025-1...
#Quarto #VSCode #Positron #Productivity #DataScience
Optimising VS Code and Positron for Quarto: Essential Settings for Better Editing – MCU
Discover the custom settings I use in VS Code and Positron to enhance my Quarto document editing workflow, from improved Git diffs to better visual guides for nested divs.
mickael.canouil.fr
November 20, 2025 at 9:43 AM
After years of working with Quarto, I've refined a set of editor settings that significantly improve document editing efficiency.
My latest blog post shares these battle-tested configurations.
mickael.canouil.fr/posts/2025-1...
#Quarto #VSCode #Positron #Productivity #DataScience
My latest blog post shares these battle-tested configurations.
mickael.canouil.fr/posts/2025-1...
#Quarto #VSCode #Positron #Productivity #DataScience
Reposted by econmaett
Instead of talking about climate change, politicians should focus on kitchen table issues like the rising price of coffee.
Heavy rain delayes harvesting in Vietnam’s biggest coffee-growing province of Dak Lak, and further downpours risk damaging crops and crimping output in the world’s top producer of robusta beans
Heavy Rain in Vietnam’s Top Coffee-Growing Region Threatens Crop
Heavy rain has delayed harvesting in Vietnam’s biggest coffee-growing province of Dak Lak, and further downpours risk damaging crops and crimping output in the world’s top producer of robusta beans.
bloom.bg
November 20, 2025 at 9:29 AM
Instead of talking about climate change, politicians should focus on kitchen table issues like the rising price of coffee.
Reposted by econmaett
it never ceases to amaze me that I can refer to duckdb functions in R expressions as though they were R functions and everything gets translated to SQL
![dplyr code with duckdb functions in all caps
tbl_files <- tbl(db, "csvs") |>
# CAPS for duckdb functions
mutate(
# $speaker has directory names with the patterns:
# - `[speaker]-[listener]` (listener specific data)
# - `[speaker]` (default version)
# so compute appropriate $speaker, $listener values
dir_parts = speaker |> STRING_SPLIT("-"),
speaker = dir_parts |> LIST_FIRST(),
listener = dir_parts |> LIST_LAST(),
listener = ifelse(listener == speaker, "default", listener)
) |>
select(speaker, listener, file, label, logprob, model_name, model_commit)](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:tpgnsvgqsu5b752uud3wmtja/bafkreiab635ulp5b4jthhnwqu3p7s3pfo4yua7vqkpqfhqtog4sfxkt2jq@jpeg)
November 19, 2025 at 7:47 PM
it never ceases to amaze me that I can refer to duckdb functions in R expressions as though they were R functions and everything gets translated to SQL
Reposted by econmaett
Academic publishing is a lucrative business for a very small number of private academic publishers. For 🇦🇹, this paper estimates: public spending benefits publishing companies with a large amount - 25% of the annual basic funding universities receive from the Ministry of education
November 20, 2025 at 8:25 AM
Academic publishing is a lucrative business for a very small number of private academic publishers. For 🇦🇹, this paper estimates: public spending benefits publishing companies with a large amount - 25% of the annual basic funding universities receive from the Ministry of education
Reposted by econmaett
Our paper on harvest-time changes in conflict, violence, and social unrest has been assigned to a volume and issue (makes it easier to cite). It offers some valuable insights, in my opinion. Luckily, it is also open access, so feel free to check it out: doi.org/10.1177/0022...
Agricultural roots of social conflict in Southeast Asia - Justin V Hastings, David Ubilava, 2025
We examine whether harvest-time transitory shifts in employment and income lead to changes in political violence and social unrest in rice-producing croplands o...
doi.org
November 20, 2025 at 9:04 AM
Our paper on harvest-time changes in conflict, violence, and social unrest has been assigned to a volume and issue (makes it easier to cite). It offers some valuable insights, in my opinion. Luckily, it is also open access, so feel free to check it out: doi.org/10.1177/0022...
Reposted by econmaett
link 📈🤖
Unifying Boxplots: A Multiple Testing Perspective (Gang, Lin, Tong) Tukey's boxplot is a foundational tool for exploratory data analysis, but its classic outlier-flagging rule does not account for the sample size, and subsequent modifications have often been presented as separate, heurist
Unifying Boxplots: A Multiple Testing Perspective (Gang, Lin, Tong) Tukey's boxplot is a foundational tool for exploratory data analysis, but its classic outlier-flagging rule does not account for the sample size, and subsequent modifications have often been presented as separate, heurist
October 24, 2025 at 4:23 PM
link 📈🤖
Unifying Boxplots: A Multiple Testing Perspective (Gang, Lin, Tong) Tukey's boxplot is a foundational tool for exploratory data analysis, but its classic outlier-flagging rule does not account for the sample size, and subsequent modifications have often been presented as separate, heurist
Unifying Boxplots: A Multiple Testing Perspective (Gang, Lin, Tong) Tukey's boxplot is a foundational tool for exploratory data analysis, but its classic outlier-flagging rule does not account for the sample size, and subsequent modifications have often been presented as separate, heurist
Reposted by econmaett
link 📈🤖
flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R (Willer, Ruckdeschel) flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipe
flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R (Willer, Ruckdeschel) flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipe
November 4, 2025 at 4:56 PM
link 📈🤖
flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R (Willer, Ruckdeschel) flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipe
flowengineR: A Modular and Extensible Framework for Fair and Reproducible Workflow Design in R (Willer, Ruckdeschel) flowengineR is an R package designed to provide a modular and extensible framework for building reproducible algorithmic workflows for general-purpose machine learning pipe
Reposted by econmaett
link 📈🤖
spar: Sparse Projected Averaged Regression in R (Parzer, Vana-G\"ur, Filzmoser) Package spar for R builds ensembles of predictive generalized linear models with high-dimensional predictors. It employs an algorithm utilizing variable screening and random projection tools to efficiently han
spar: Sparse Projected Averaged Regression in R (Parzer, Vana-G\"ur, Filzmoser) Package spar for R builds ensembles of predictive generalized linear models with high-dimensional predictors. It employs an algorithm utilizing variable screening and random projection tools to efficiently han
November 8, 2025 at 7:04 PM
link 📈🤖
spar: Sparse Projected Averaged Regression in R (Parzer, Vana-G\"ur, Filzmoser) Package spar for R builds ensembles of predictive generalized linear models with high-dimensional predictors. It employs an algorithm utilizing variable screening and random projection tools to efficiently han
spar: Sparse Projected Averaged Regression in R (Parzer, Vana-G\"ur, Filzmoser) Package spar for R builds ensembles of predictive generalized linear models with high-dimensional predictors. It employs an algorithm utilizing variable screening and random projection tools to efficiently han
Reposted by econmaett
link 📈🤖
rfBLT: Random Feature Bayesian Lasso Takens Model for time series forecasting (Nguyen, Ho) Time series prediction is challenging due to our limited understanding of the underlying dynamics. Conventional models such as ARIMA and Holt's linear trend model experience difficulty in identifyin
rfBLT: Random Feature Bayesian Lasso Takens Model for time series forecasting (Nguyen, Ho) Time series prediction is challenging due to our limited understanding of the underlying dynamics. Conventional models such as ARIMA and Holt's linear trend model experience difficulty in identifyin
November 13, 2025 at 4:15 PM
link 📈🤖
rfBLT: Random Feature Bayesian Lasso Takens Model for time series forecasting (Nguyen, Ho) Time series prediction is challenging due to our limited understanding of the underlying dynamics. Conventional models such as ARIMA and Holt's linear trend model experience difficulty in identifyin
rfBLT: Random Feature Bayesian Lasso Takens Model for time series forecasting (Nguyen, Ho) Time series prediction is challenging due to our limited understanding of the underlying dynamics. Conventional models such as ARIMA and Holt's linear trend model experience difficulty in identifyin
Reposted by econmaett
link 📈🤖
Diagnostics for Semiparametric Accelerated Failure Time Models with R Package afttest (Bae, Choi, Yan et al) The semiparametric accelerated failure time (AFT) model is a useful alternative to the widely used Cox proportional hazard model, which directly links the logarithm of the failure
Diagnostics for Semiparametric Accelerated Failure Time Models with R Package afttest (Bae, Choi, Yan et al) The semiparametric accelerated failure time (AFT) model is a useful alternative to the widely used Cox proportional hazard model, which directly links the logarithm of the failure
November 14, 2025 at 4:50 PM
link 📈🤖
Diagnostics for Semiparametric Accelerated Failure Time Models with R Package afttest (Bae, Choi, Yan et al) The semiparametric accelerated failure time (AFT) model is a useful alternative to the widely used Cox proportional hazard model, which directly links the logarithm of the failure
Diagnostics for Semiparametric Accelerated Failure Time Models with R Package afttest (Bae, Choi, Yan et al) The semiparametric accelerated failure time (AFT) model is a useful alternative to the widely used Cox proportional hazard model, which directly links the logarithm of the failure
Reposted by econmaett
link 📈🤖
nonprobsvy -- An R package for modern methods for non-probability surveys (Chrostowski, Chlebicki, Ber\k{e}sewicz) The following paper presents {nonprobsvy} -- an {R} package for inference based on non-probability samples. The package implements various approaches that can be categorized
nonprobsvy -- An R package for modern methods for non-probability surveys (Chrostowski, Chlebicki, Ber\k{e}sewicz) The following paper presents {nonprobsvy} -- an {R} package for inference based on non-probability samples. The package implements various approaches that can be categorized
November 14, 2025 at 7:05 PM
link 📈🤖
nonprobsvy -- An R package for modern methods for non-probability surveys (Chrostowski, Chlebicki, Ber\k{e}sewicz) The following paper presents {nonprobsvy} -- an {R} package for inference based on non-probability samples. The package implements various approaches that can be categorized
nonprobsvy -- An R package for modern methods for non-probability surveys (Chrostowski, Chlebicki, Ber\k{e}sewicz) The following paper presents {nonprobsvy} -- an {R} package for inference based on non-probability samples. The package implements various approaches that can be categorized
Reposted by econmaett
link 📈🤖
SCoRES: An R Package for Simultaneous Confidence Region Estimates (Yu, Schwartzman, Ren et al) The identification of domain sets whose outcomes belong to predefined subsets can address fundamental risk assessment challenges in climatology and medicine. Existing approaches for inverse doma
SCoRES: An R Package for Simultaneous Confidence Region Estimates (Yu, Schwartzman, Ren et al) The identification of domain sets whose outcomes belong to predefined subsets can address fundamental risk assessment challenges in climatology and medicine. Existing approaches for inverse doma
November 18, 2025 at 5:36 PM
link 📈🤖
SCoRES: An R Package for Simultaneous Confidence Region Estimates (Yu, Schwartzman, Ren et al) The identification of domain sets whose outcomes belong to predefined subsets can address fundamental risk assessment challenges in climatology and medicine. Existing approaches for inverse doma
SCoRES: An R Package for Simultaneous Confidence Region Estimates (Yu, Schwartzman, Ren et al) The identification of domain sets whose outcomes belong to predefined subsets can address fundamental risk assessment challenges in climatology and medicine. Existing approaches for inverse doma
Reposted by econmaett
The Wages of Destruction by Adam Tooze. I have the print edition at home as well which i bought many years ago. Listening to it this time for a refresh as it seems to be an apropos time.
November 19, 2025 at 7:11 PM
The Wages of Destruction by Adam Tooze. I have the print edition at home as well which i bought many years ago. Listening to it this time for a refresh as it seems to be an apropos time.
Reposted by econmaett
Using {mapsf} to create a minimal map showing, hopefully, solidarity with Ukraine.
#30DayMapChallenge | Day 11 - Minimal #rstats
(code in alt)
#30DayMapChallenge | Day 11 - Minimal #rstats
(code in alt)
November 11, 2025 at 9:11 AM
Using {mapsf} to create a minimal map showing, hopefully, solidarity with Ukraine.
#30DayMapChallenge | Day 11 - Minimal #rstats
(code in alt)
#30DayMapChallenge | Day 11 - Minimal #rstats
(code in alt)
Reposted by econmaett
R, Rust, Geospatial "AI", and laughs with @fransvandunne.com and Diego of @ixpantia.com on their Podcast @datalatam.bsky.social
It was a blast! Thanks for having me.
open.spotify.com/episode/6C5L...
#rstats #gischat #rust
It was a blast! Thanks for having me.
open.spotify.com/episode/6C5L...
#rstats #gischat #rust
Josiah Parry, R Developer & Spatial Statistician, on pragmatic AI and the "ggplot gateway drug"
open.spotify.com
November 17, 2025 at 5:29 PM
R, Rust, Geospatial "AI", and laughs with @fransvandunne.com and Diego of @ixpantia.com on their Podcast @datalatam.bsky.social
It was a blast! Thanks for having me.
open.spotify.com/episode/6C5L...
#rstats #gischat #rust
It was a blast! Thanks for having me.
open.spotify.com/episode/6C5L...
#rstats #gischat #rust
Reposted by econmaett
The @kiel.institute’s #Ukraine tracker is something you can lose yourself in forever, so fascinating is its data.
Thankfully Kjeld managed to look away from it to do a write up on NATO’s PURL, “a kind of transaction account” for military aid.
Thankfully Kjeld managed to look away from it to do a write up on NATO’s PURL, “a kind of transaction account” for military aid.
Europeans ponying up to fund US weapons shipments to Ukraine
Europeans ponying up to fund US weapons shipments to Ukraine
Several NATO powers have pledged a total of $1.5 billion to cover the cost of US weapons packages, with European fiscal heavyweight Germany joining this week.
dlvr.it
August 15, 2025 at 8:04 AM
The @kiel.institute’s #Ukraine tracker is something you can lose yourself in forever, so fascinating is its data.
Thankfully Kjeld managed to look away from it to do a write up on NATO’s PURL, “a kind of transaction account” for military aid.
Thankfully Kjeld managed to look away from it to do a write up on NATO’s PURL, “a kind of transaction account” for military aid.
Reposted by econmaett
A Rodríguez-Pose, L Dijkstra, & C Dorati offer new evidence from across 1,166 European regions from 2004 to 2023 that Euroscepticism carries significant economic cost. The more Eurosceptic regions have seen slower GDP per capita, productivity, & employment growth.
cepr.org/voxeu/column...
#EconSky
cepr.org/voxeu/column...
#EconSky
November 13, 2025 at 1:00 PM
A Rodríguez-Pose, L Dijkstra, & C Dorati offer new evidence from across 1,166 European regions from 2004 to 2023 that Euroscepticism carries significant economic cost. The more Eurosceptic regions have seen slower GDP per capita, productivity, & employment growth.
cepr.org/voxeu/column...
#EconSky
cepr.org/voxeu/column...
#EconSky
Reposted by econmaett
🔥 {torchgnn} 🕸️ is a WIP implementation of Graph Neural Networks in R.
- GCN
- GCN (generalized)
- GraphSAGE
- Aggregators
Development based on personal needs, ofc :)
#rstats
github.com/JosiahParry/...
- GCN
- GCN (generalized)
- GraphSAGE
- Aggregators
Development based on personal needs, ofc :)
#rstats
github.com/JosiahParry/...
November 13, 2025 at 8:14 PM
🔥 {torchgnn} 🕸️ is a WIP implementation of Graph Neural Networks in R.
- GCN
- GCN (generalized)
- GraphSAGE
- Aggregators
Development based on personal needs, ofc :)
#rstats
github.com/JosiahParry/...
- GCN
- GCN (generalized)
- GraphSAGE
- Aggregators
Development based on personal needs, ofc :)
#rstats
github.com/JosiahParry/...
Reposted by econmaett
Doesn’t that Bayesian joke need updating 😶?
November 14, 2025 at 5:44 AM
Doesn’t that Bayesian joke need updating 😶?
Reposted by econmaett
I am 457 days clean of frequentism. It’s a long rode to the path of recovery
November 14, 2025 at 5:20 AM
I am 457 days clean of frequentism. It’s a long rode to the path of recovery
Reposted by econmaett
- How do you know someone is a Bayesian?
- Because they can't stop talking about it.
😆
- Because they can't stop talking about it.
😆
November 14, 2025 at 3:56 AM
- How do you know someone is a Bayesian?
- Because they can't stop talking about it.
😆
- Because they can't stop talking about it.
😆
Reposted by econmaett
now raising the important question: what would a Bayesian vegan Crossfitter mention first?
November 14, 2025 at 3:57 AM
now raising the important question: what would a Bayesian vegan Crossfitter mention first?