Francisco Rodriguez-Sanchez
LightNews LightNews
banner
frodsan.bsky.social
Francisco Rodriguez-Sanchez
@frodsan.bsky.social
3.3K followers 150 following 190 posts
Computational Ecologist. Researcher @unisevilla.bsky.social. ecology, biogeography, statistics, rstats, GIS, science.

https://frodriguezsanchez.net
Posts Replies Media Videos
Pinned
frodsan.bsky.social
Francisco Rodriguez-Sanchez @frodsan.bsky.social · Feb 19
1/ New paper @pnas.org on the structure of mutualistic #networks between individuals plants and frugivore species.

Last chapter of @elequintero.bsky.social's PhD thesis

doi.org/10.1073/pnas... #ecopubs
Downscaling mutualistic networks from species to individuals reveals consistent interaction niches and roles within plant populations Species-level networks emerge as the combination of interactions spanning multiple individuals, and their study has received considerable attention over the past 30 y. However, less is known about the structure of interaction configurations within species, even though individuals are the actual interacting units in nature. We compiled 46 empirical, individual-based, interaction networks on plant-animal seed dispersal mutualisms, comprising 1,037 plant individuals across 29 species from various regions. We compared the structure of individual-based networks to that of species-based networks and, by extending the niche concept to interaction assemblages, we explored individual plant specialization. Using a Bayesian framework to account for uncertainty derived from sampling, we examined how plant individuals “explore” the interaction niche of their populations. Both individual-based and species-based networks exhibited high variability in network properties, lacking remarkable structural and topological differences between them. Within populations, frugivores’ interaction allocation among plant individuals was highly heterogeneous, with one to three frugivore species dominating interactions. Regardless of species or bioregion, plant individuals displayed a variety of interaction profiles across populations, with a consistently-small percentage of individuals playing a central role and exhibiting high diversity in their interaction assemblage. Plant populations showed variable mid to low levels of niche specialization; and individuals’ interaction niche “breadth” accounted for 70% of the population interaction diversity, on average. Our results highlight how downscaling from species to individual-based networks helps understanding the structuring of interactions within ecological communities.
Reposted by Francisco Rodriguez-Sanchez
mattansb.msbstats.info
The default prior for the intercept in both {rstanarm} and {brms} are very wide.

Counterintuitively - being on the logit scale, this is actually translates to a **strong** prior that p(y=1) is near 1 or near 0.

Always check your priors!

#rstats
November 18, 2025 at 2:01 PM
Reposted by Francisco Rodriguez-Sanchez
florianhartig.bsky.social
We are hiring: 4 PhD Positions in Ecology / Data Science and one Ecological Data Scientist. For more information, see www.uni-regensburg.de/universitaet...
We are hiring: 4 PhD Positions in Ecology / Data Science and one Ecological Data Scientist
We are looking for 4 PhD Positions and one Scientific Programmer / Ecological Data Scientist to join the AG Hartig (Theoretical Ecology)
www.uni-regensburg.de
November 13, 2025 at 4:14 PM
Reposted by Francisco Rodriguez-Sanchez
simonpcouch.com
To be effective, data science agents need to be able to read plots reliably. @sara-altman.bsky.social and I wrote about some concerning findings on LLMs' ability to interpret plots when the content contradicts their expectations on the @posit.co blog.

posit.co/blog/introdu...
When plotting, LLMs see what they expect to see - Posit
Data science agents need to accurately read plots even when the content contradicts their expectations. Our testing shows today's LLMs still struggle here.
posit.co
November 13, 2025 at 3:07 PM
Reposted by Francisco Rodriguez-Sanchez
hansonmark.bsky.social
We wrote the Strain on scientific publishing to highlight the problems of time & trust. With a fantastic group of co-authors, we present The Drain of Scientific Publishing:

a 🧵 1/n

Drain: arxiv.org/abs/2511.04820
Strain: direct.mit.edu/qss/article/...
Oligopoly: direct.mit.edu/qss/article/...
A table showing profit margins of major publishers. A snippet of text related to this table is below. 1. The four-fold drain 1.1 Money Currently, academic publishing is dominated by profit-oriented, multinational companies for whom scientific knowledge is a commodity to be sold back to the academic community who created it. The dominant four are Elsevier, Springer Nature, Wiley and Taylor & Francis, which collectively generated over US$7.1 billion in revenue from journal publishing in 2024 alone, and over US$12 billion in profits between 2019 and 2024 (Table 1A). Their profit margins have always been over 30% in the last five years, and for the largest publisher (Elsevier) always over 37%. Against many comparators, across many sectors, scientific publishing is one of the most consistently profitable industries (Table S1). These financial arrangements make a substantial difference to science budgets. In 2024, 46% of Elsevier revenues and 53% of Taylor & Francis revenues were generated in North America, meaning that North American researchers were charged over US$2.27 billion by just two for-profit publishers. The Canadian research councils and the US National Science Foundation were allocated US$9.3 billion in that year. A figure detailing the drain on researcher time. 1. The four-fold drain 1.2 Time The number of papers published each year is growing faster than the scientific workforce, with the number of papers per researcher almost doubling between 1996 and 2022 (Figure 1A). This reflects the fact that publishers’ commercial desire to publish (sell) more material has aligned well with the competitive prestige culture in which publications help secure jobs, grants, promotions, and awards. To the extent that this growth is driven by a pressure for profit, rather than scholarly imperatives, it distorts the way researchers spend their time. The publishing system depends on unpaid reviewer labour, estimated to be over 130 million unpaid hours annually in 2020 alone (9). Researchers have complained about the demands of peer-review for decades, but the scale of the problem is now worse, with editors reporting widespread difficulties recruiting reviewers. The growth in publications involves not only the authors’ time, but that of academic editors and reviewers who are dealing with so many review demands. Even more seriously, the imperative to produce ever more articles reshapes the nature of scientific inquiry. Evidence across multiple fields shows that more papers result in ‘ossification’, not new ideas (10). It may seem paradoxical that more papers can slow progress until one considers how it affects researchers’ time. While rewards remain tied to volume, prestige, and impact of publications, researchers will be nudged away from riskier, local, interdisciplinary, and long-term work. The result is a treadmill of constant activity with limited progress whereas core scholarly practices – such as reading, reflecting and engaging with others’ contributions – is de-prioritized. What looks like productivity often masks intellectual exhaustion built on a demoralizing, narrowing scientific vision. A table of profit margins across industries. The section of text related to this table is below: 1. The four-fold drain 1.1 Money Currently, academic publishing is dominated by profit-oriented, multinational companies for whom scientific knowledge is a commodity to be sold back to the academic community who created it. The dominant four are Elsevier, Springer Nature, Wiley and Taylor & Francis, which collectively generated over US$7.1 billion in revenue from journal publishing in 2024 alone, and over US$12 billion in profits between 2019 and 2024 (Table 1A). Their profit margins have always been over 30% in the last five years, and for the largest publisher (Elsevier) always over 37%. Against many comparators, across many sectors, scientific publishing is one of the most consistently profitable industries (Table S1). These financial arrangements make a substantial difference to science budgets. In 2024, 46% of Elsevier revenues and 53% of Taylor & Francis revenues were generated in North America, meaning that North American researchers were charged over US$2.27 billion by just two for-profit publishers. The Canadian research councils and the US National Science Foundation were allocated US$9.3 billion in that year. The costs of inaction are plain: wasted public funds, lost researcher time, compromised scientific integrity and eroded public trust. Today, the system rewards commercial publishers first, and science second. Without bold action from the funders we risk continuing to pour resources into a system that prioritizes profit over the advancement of scientific knowledge.
November 11, 2025 at 11:52 AM
Reposted by Francisco Rodriguez-Sanchez
markuseichhorn.bsky.social
Aside from being cool research on remote-sensing of AGB across Canada, this is an amazing visualisation by Tompalski et al. (2025). Paper here: academic.oup.com/forestry/adv... 🌲🌏🧪
November 12, 2025 at 4:24 PM
frodsan.bsky.social
Important thread 🧵 👇🏼
hausfath.bsky.social Zeke Hausfather @hausfath.bsky.social · 7d
The new 2025 Global Carbon Budget finds that fossil fuel emissions will reach a new high in 2025. Total CO2 emissions (including land use) remain flat at 2024 levels.

While the land sink is up from 2024, carbon sinks are weakening: www.carbonbrief.org/...
November 13, 2025 at 8:04 AM
Reposted by Francisco Rodriguez-Sanchez
billurbektas.bsky.social
Are you involved in ecological forecasting in Europe?
We’re mapping forecasting applications across the continent — from SDMs to observatories with predictive potential.
Our goal: make EU forecasting more connected and identify both immediate and long-term forecasting potential.
November 10, 2025 at 10:49 AM
Reposted by Francisco Rodriguez-Sanchez
jebyrnes.bsky.social
Well now I'm pondering - what is the best Introductory Biostats book out there that folk have had success with. I used to like Whitlock & Schluter, but have come to find it too test-based and not enough thinking-based (to use a term of art?).
rmcelreath.bsky.social Richard McElreath 🐈‍⬛ @rmcelreath.bsky.social · 9d
False. There is no such thing as an introductory statistics textbook
November 11, 2025 at 3:59 PM
Reposted by Francisco Rodriguez-Sanchez
hausfath.bsky.social
There are a lot of things I agree with in Bill Gates' new climate memo, but I think it sets up a false dichotomy between reducing emissions and helping the world's poorest. I've put together a piece with my thoughts over at TCB:
On the Gates climate memo
There is a lot of things I agree with in Bill Gates’ new memo on climate change, but I think it fundamentally sets up a false dichotomy.
www.theclimatebrink.com
November 5, 2025 at 5:25 PM
Reposted by Francisco Rodriguez-Sanchez
openrxiv.bsky.social
Enabling options for review: bioRxiv authors now have the option to send their preprints directly to @qedscience.bsky.social , an authors-centered AI review platform, for automated feedback on their paper.

openrxiv.org/enabling-rev...

#OpenScience #Preprints #openrxiv #qedscience #biorxiv
November 6, 2025 at 2:42 PM
Reposted by Francisco Rodriguez-Sanchez
henrikbengtsson.bsky.social
The detectCores() apocalypse is creeping up on us 👻🐛

As more people are getting access to 128+ CPU cores, code spinning up parallel cluster with detectCores() workers fails - not enough #RStats connections available

Friends, do *not* default to detectCores(), bc www.jottr.org/2022/12/05/a...
Please Avoid detectCores() in your R Packages
The detectCores() function of the parallel package is probably one of the most used functions when it comes to setting the number of parallel workers to use in R. In this blog post, I’ll try to explai...
www.jottr.org
November 5, 2025 at 11:55 PM
frodsan.bsky.social
The next @peercommunityin.bsky.social seminar by @simine.com looks interesting

peercommunityin.org/pci-webinar-...
Recognizing and responding to a replication crisis: Lessons from Psychology The last 15 years have been a turbulent period for the field of psychology. Failures to replicate, fraud, and evidence of questionable research practices have all contributed to a crisis of credibility. What has the field done in response to this crisis, and what lessons can be learned from psychology’s crisis? We often hear the self-correcting mechanisms in science invoked as a reason to trust science, but it is not clear what these mechanisms are, or how they could have prevented psychology’s crisis. Some quality control mechanisms, such as peer review for journals, or vetting for textbooks or for public dissemination, did not to provide much of a safeguard against invalid claims in psychology. Instead, I argue that we should look for visible signs of a scientific community’s commitment to self-correction. These signs include transparency in the research and peer review process, investment in error detection and quality control, and an emphasis on calibration rather than popularization. To regain or bolster trust, scientific fields should invest in these hallmarks of credibility.
November 5, 2025 at 11:48 AM
Reposted by Francisco Rodriguez-Sanchez
wkhuber.bsky.social
I regularly get derailed when someone tries to benchmark clustering methods, trying the find the "best" one or the one that agrees with "ground truth".

Which clustering of the below animals is the best or the true one? By row, or by column?
October 16, 2025 at 9:44 AM
Reposted by Francisco Rodriguez-Sanchez
hormiga.bsky.social
I find there's a huge mismatch between the standard advice that people give about scientific conference talks, and how people actually give talks.

So I picked out the most important pieces of advice that are most often ignored. 🧪
The best scientific talk advice that gets ignored
Here are some prescriptions for a case of UCPS (Unengaging Conference Presentation Syndrome).
scienceforeveryone.science
October 28, 2025 at 9:24 PM
frodsan.bsky.social
Thank you @hormiga.bsky.social for writing this book. Beyond learning what may be right/wrong with current practices and many new tips, it makes you think throughout what kind of teacher you want to be and how to get there. Highly recommend

press.uchicago.edu/ucp/books/bo... #teaching #AcademicSky
Book cover of the Chicago guide to college science teaching
November 2, 2025 at 10:11 AM
frodsan.bsky.social
Interesting. 2 lessons here:

1. Don't use LLM output code uncritically, even if it runs smoothly

2. As developers we can protect our #rstats code from such problems e.g. with rlang.r-lib.org/reference/ch...
tjmahr.com tj mahr 🎃 @tjmahr.com · 21d
student used some AI-assisted code to compute ROC stats with weights and the AI hallucinated pROC::roc(…, weights = weights). (the function doesn’t have a weights argument.) and because the function has a … argument, the fake weights argument was ignored without any warning
November 1, 2025 at 5:01 PM
Reposted by Francisco Rodriguez-Sanchez
nature.com
Funders must recognise that great discoveries often come from studies that seeks to advance knowledge for its own sake

go.nature.com/47zrzYZ
From MRI to Ozempic: breakthroughs that show why fundamental research must be protected
In these financially straitened times, funders must recognize that great discoveries often arise from work that was looking for something completely different.
go.nature.com
October 29, 2025 at 12:11 PM
Reposted by Francisco Rodriguez-Sanchez
yomoseco.bsky.social
Announcing 🍱 Lunchbox Models 🍱
– an online seminar series all about ecological modelling & career insights, hosted by the @gfoesoc.bsky.social AKs Computational Ecology and YoMos 🦊

Find the topics and details as well as access to Zoom on our webpage: www.yomos.org/lunchbox-mod...

Please share!
Image shows a poster for the 'Lunchbox Models' seminar series. It shows a sandwich illustration between green boxes with information regarding the seminar series. The left column has general information and the right side has the schedule for the first 11 talks. All the info can be found on the webpage of the seminar series (linked in posting text and QR Code in poster). Several other food item illustrations are used as decoration, e.g. onigiri, coffee/tea cups, and pasta on a fork.
October 14, 2025 at 10:05 AM
frodsan.bsky.social
Still fascinated with #webR and its potential for teaching stats

Here students can play (even from their phones) and find out themselves how the p-value depends on sample size

pakillo.github.io/LM-GLM-GLMM-... #rstats
A screenshot of a statistics tutorial made with R, quarto and webR
October 22, 2025 at 6:36 AM
Reposted by Francisco Rodriguez-Sanchez
nature.com
Success rates for Europe’s leading research grants are declining as a surge in applications far outweighs the funds available

go.nature.com/479Sni6
Is academic research becoming too competitive? Nature examines the data
Applications for European research grants increased in 2025. Scientists say they’re feeling the competition.
go.nature.com
October 17, 2025 at 10:12 AM
Reposted by Francisco Rodriguez-Sanchez
jakubnowosad.com
🗺️ New blog post: introducing Spatial Data Visualization with tmap, a work-in-progress guide to thematic mapping in #RStats.

Learn about the book, its progress, and how to contribute: geocompx.org/post/2025/tm...

#DataViz #Mapping #tmap #geocompx
A screenshot of the blog post A screenshot of the blog post
October 14, 2025 at 1:03 PM
Reposted by Francisco Rodriguez-Sanchez
ibartomeus.bsky.social
We are offering a 2-year postdoctoral position to join the @valor-project.eu Horizon EU project: Values and dependence of society on pollinators bartomeuslab.com/joining-the-...
Joining the lab
2-year Postdoctoral position on VALOR EU-project: We are offering a 2-year postdoctoral position to join the Horizon EU project: Values and dependence of society on pollinators (VALOR; The candidat…
bartomeuslab.com
October 6, 2025 at 1:31 PM
frodsan.bsky.social
Finally using {pins} #rstats package to share heavy files that can't be shared among collaborators through GitHub, and it works like a breeze! Supports data versioning, cache, etc. Thanks @posit.co

Here using Google Drive to share files, but can use many different servers, see pins.rstudio.com
library("pins") # specify folder in Google Drive to store objects board <- board_gdrive("https://drive.google.com/drive/folders/FOLDER_ID") # upload file board |> pin_write(big_dataset, "big_dataset.csv", type = "csv") # retrieve file (e.g. in another computer) board |> pin_read("big_dataset.csv")
October 2, 2025 at 12:27 PM
Reposted by Francisco Rodriguez-Sanchez
chale9.bsky.social
Help! 🚨 Looking for resources on structural equation models—favorite methods papers, example studies, or guides for building an SEM pipeline. Thinking of using one for a dissertation chapter & not sure where to start. Suggestions? Please share!
September 30, 2025 at 8:28 PM
Reposted by Francisco Rodriguez-Sanchez
rmcelreath.bsky.social
Was asked about collinearity again, so here's Vahove's 2019 post on why it isn't a problem that needs a solution. Design the model(s) to answer a formal question and free your mind janhove.github.io/posts/2019-0...
tl;dr Collinearity is a form of lack of information that is appropriately reflected in the output of your statistical model. When collinearity is associated with interpretational difficulties, these difficulties aren’t caused by the collinearity itself. Rather, they reveal that the model was poorly specified (in that it answers a question different to the one of interest), that the analyst overly focuses on significance rather than estimates and the uncertainty about them or that the analyst took a mental shortcut in interpreting the model that could’ve also led them astray in the absence of collinearity. If you do decide to “deal with” collinearity, make sure you can still answer the question of interest.
October 1, 2025 at 5:29 AM