F Rodriguez-Sanchez Profile picture
Computational Ecologist. PhD in Biology. R, stats, GIS, ecology, biogeography, science. Also https://t.co/9S9XDX6yW7 @_SevillaR @ecoinf_aeet
Jul 21, 2023 7 tweets 2 min read
ICYMI this paper really is a must read:

Comparing and choosing best models based on AIC etc, then interpret coefficients causally (what's the effect of X on Y?) is flawed, yet so common.

We must draw causal assumptions first (eg. DAG)

1/7 https://t.co/icU4g8ipNJdoi.org/10.1111/ele.14…
Image "Model selection is not a valid method for inferring causal relationships.

Model selection is appropriate for predictive inference (i.e. which model best predicts Y?), which is fundamentally distinct from causal inference (i.e. what is the effect of X on Y?)"
Apr 24, 2023 6 tweets 2 min read
{grateful} is now on CRAN!

{grateful} makes it very easy to cite #Rstats packages, so that software authors get their deserved credit



Thread 1/ pakillo.github.io/grateful/
The goal of grateful is to make it very easy to cite R and the R packages used in any analyses, so that package authors receive their deserved credit. By calling a single function, grateful will scan the project for R packages used and generate a BibTeX file containing all citations for those packages.  grateful can then generate a new document with citations in the desired output format (Word, PDF, HTML, Markdown). These references can be formatted for a specific journal, so that we can just paste them directly into our manuscript or report.  Alternatively, we can use grateful directly wit... 2/ Just run

grateful::cite_packages()

and you'll get a report with formatted citations and references for all the #rstats packages used in your analysis, ready to paste into your manuscript or report Image
Jul 11, 2022 17 tweets 7 min read
I wish academics were much more cautious when using authors' order in papers to infer contribution & leadership

Many committees use this too lightly (eg. ranking by number or % of papers as corresponding author)

Many scientists' careers depend on this, so a few thoughts 👇🏽 First, there are no universal rules regarding the first/last/corresponding author thing: doi.org/10.1002/ece3.3… @duffy_ma

Sometimes authors are sorted in decreasing order of contribution, so 2nd author is important. Sometimes last author is more important
Feb 7, 2022 6 tweets 3 min read
New version of {grateful}, the package that makes it very easy to cite #Rstats packages, so that #software authors get their deserved credit.

pakillo.github.io/grateful/

Major changes: 1/6 2/ To get a document with formatted citations for all the #rstats packages used in your analysis, just run

library(grateful)
cite_packages()

Now includes pkg versions and all their citations, ready to paste into your manuscript or report Image
Jun 22, 2019 10 tweets 4 min read
So many scientific results rely on code written by an inexperienced programmer and is NEVER EVER seen by anyone else. We can surely do better.

Thread 1/n First, data and code behind published papers must be public (except for justified reasons). It's unbelievable that we have to blindly trust what is said in a paper without being able to look inside. And yes, that happens so often pnas.org/content/115/11… 2/n