@ucfagls Profile picture

🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰

@ucfagls

(Palaeo)[ecologist | limnologist] & #fakeStatistican, #rstats user, wielder of #GAMs. He/him/his. Opinions mine…

Similar User
Ecological Society photo

@ESA_org

Ecological Forecasting Initiative photo

@eco4cast

Ben Bolker @bbolker@fediscience.org photo

@bolkerb

Allison Horst photo

@allison_horst

F Rodriguez-Sanchez photo

@frod_san

William Gosling photo

@palaeolim

Pedro Peres-Neto photo

@com_ecology

Michael Dietze photo

@mcdietze

Alison Hill photo

@apreshill

Will Pearse photo

@willpearse

Florian Hartig photo

@florianhartig

Solomon Kurz photo

@SolomonKurz

Claus Wilke photo

@ClausWilke

Olivier Gimenez 🖖🦦 photo

@oaggimenez

Christopher F Clements photo

@DrChrisClements

Pinned

If you want to fit nonlinear relationships to data where those relationships can vary by groups (eg species) then we have a paper for you: Hierarchical Generalized Additive Models peerj.com/articles/6876/… in @thePeerJ #oa #ecology #rstats w @ericJpedersen @millerdl @noamross

Tweet Image 1
Tweet Image 2
Tweet Image 3
Tweet Image 4

🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

Come do a PhD with me on #statistics for a fun #TropicalEcology system (featuring ants!!!). Data collection and systems expertise form @LukeLPowell and team. Modelling will be done in the amazing @mcmc_stan findaphd.com/phds/project/d…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

I just started using GAMs. Gavin Simpson (@ucfagls ..author of gratia package) has excellent resources to start learning GAMs with R. 1. Youtube tutorials youtu.be/FybiHEjfbhA?si… 2. Blog: fromthebottomoftheheap.net


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

Obviously Simon Wood’s books and papers are great, but @ucfagls has some great blogs on using them fromthebottomoftheheap.net


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

I believe the best resource for getting started and reaching a productive level with GAMs for most researchers is Dr. @ucfagls's Physalia GAM course. Course materials are available here: github.com/gavinsimpson/p…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

🚨 Looking to join a consortium for the latest #Biodiversa call! 🚨 I'm looking to collaborate on a project on forest management or restoration to which I can bring my skills in evidence synthesis. If you're interested, get in touch! Call info: biodiversa.eu/2024/06/11/202…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

🚨 Course Alert🚨 Want to learn how to tackle the complexities of ecological time-series data in R? 📈 Join us to learn the magic of @mcmc_stan #rstats to analyse, visualise, & forecast time series with @nj_clark! 📊✨ Limited spots available physalia-courses.org/courses-worksh…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

This paper was possible due to some fantastic updates in @ucfagls's `gratia` package, allowing us to perform inference on epidemic growth rates while using `mgcv`.


New study estimates the probability that #chess grand master @GMHikaru is *not* cheating is 99.6%! Haven't read this is detail, but passes the sniff test, using the same general idea that was used in evidence to overturn Sally Clark's wrongful conviction arxiv.org/abs/2409.06739


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

Congratulations to David Borchers of @univofstandrews who is the recipient of our 2024 Barnett Award for environmental statistics, for the development of new and accessible methodologies in wildlife monitoring & conservation

Tweet Image 1

🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

I'm looking for examples simple multilevel models [e.g., y ~ 1 + x + (1 + x | group) in lme4 syntax] coded in Stan/rstan/cmdstanr. Good clean code, the kind you'd recommend for learning. Centered and non-centered parameterization are welcome. #RStats #rstan


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

This is just shouty dplyr.

$GOOG introduced new pipeline operator to SQL.

Tweet Image 1


Quite a lot has changed in #GAM and #mgcv land in the 4 years since I did this amid the #darkTimes I should do some updates featuring more gratia 📦 & some other packages that are mgcv-adjacent Don’t worry; I won’t do it as a multi-hour marathon this time though 😅 #rstats

Just sharing this awesome (4-yr old) primer to generalized additive models (GAMs) that I stumbled upon. Thanks @ucfagls for this great resource for us humble ecologists trying to use statistics well. youtube.com/watch?v=sgw4cu…



🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

As an #eLifeAmbassador, Brian set up the Queer STEM Writing Group. It's a supportive community for queer people to connect and share advice, with a special focus on technical writing and SciComm. Invitations are open, we'd love to meet you! 👇 2/2 discord.com/invite/eDaaU74…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

To @brineshrimp2, queerness is about “challenging the binary”. It's this concept that partly drew them to regenerative medicine. For Voices, they explore religion, science and self, and how they’re building community for other queer people in STEM. 1/2 elifesciences.org/community-voic…


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

Still time to apply for this exciting 2-yr postdoc @EconovoAU on #vegetation-climate interactions under rising biosphere novelty - deadline Sep 1 international.au.dk/about/profile/… 🌿🏔️🌤️🛰️🦬🌳#plants #remotesesing #macroecology #megafauna #geodiversity


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

LMFTFY

Tweet Image 1

I really dislike this view of statistics - as a bag of separate tests to be learned or deployed depending on a flow chart. Most of these are just linear models; why learn all these things when one model, a GLM, would do? Also, Continuous != Gaussian, which is implied below

How I pick the right statistical test for my experimental variables

Tweet Image 1


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

Hey folks! Been a while since I posted about it, but our book on practical data science modeling has come a long way since then. Would love to hear some thoughts on GitHub or here. Hopefully we'll get it done soon and out on @CRCPress in the near future! m-clark.github.io/book-of-models/


🇺🇦 Dr Gavin Simpson 😷🇪🇺🇩🇰 Reposted

In celebration of its republication by @CRC_MathStats, we are giving away a signed copy of this classic textbook by Casella and Berger. Just like, repost, and follow me by Thursday 15th August to be in with a chance of winning! Enjoy and learn! #Statistics #DataScience #JSM2024

Tweet Image 1
Tweet Image 2

Loading...

Something went wrong.


Something went wrong.