Mridul K. Thomas
@mridulkthomas.bsky.social
ecology, temperature, multiple drivers, plankton, experimental design, statistics | www.mridulkthomas.com | University of Geneva
A new release of the mgcv #RStats 📦 is out on CRAN and Simon Wood (U Edinburgh) has added some significant new features despite the small bump in version number:
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
🌟 scasm() for estimating GAMs with shape constrained smooths. Can be used with any family & smoothness selection is via the EFS method
November 12, 2025 at 2:04 PM
library(manipulate)
manipulate(
curve(
arnoldi(x, T_opt, E, Pf_max),
0, 40, ylim = c(0, 2)),
T_opt = slider(0.1, 40, 20),
E= slider(0.1, 20, 5),
Pf_max = slider(0.01, 3, 1)
)
manipulate(
curve(
arnoldi(x, T_opt, E, Pf_max),
0, 40, ylim = c(0, 2)),
T_opt = slider(0.1, 40, 20),
E= slider(0.1, 20, 5),
Pf_max = slider(0.01, 3, 1)
)
October 24, 2025 at 11:05 AM
library(manipulate)
manipulate(
curve(
arnoldi(x, T_opt, E, Pf_max),
0, 40, ylim = c(0, 2)),
T_opt = slider(0.1, 40, 20),
E= slider(0.1, 20, 5),
Pf_max = slider(0.01, 3, 1)
)
manipulate(
curve(
arnoldi(x, T_opt, E, Pf_max),
0, 40, ylim = c(0, 2)),
T_opt = slider(0.1, 40, 20),
E= slider(0.1, 20, 5),
Pf_max = slider(0.01, 3, 1)
)
# Arnoldi et al. (2025) function
arnoldi <- function(x, T_opt, E, Pf_max){
exp((x-T_opt)/E)*(1-((x-T_opt)/E))*Pf_max
}
# T_opt = optimum temperature
# E= upper critical temperature (i.e. Tmax) minus t_opt
# Pf_max = max performance (e.g. max growth rate)
curve(arnoldi(x, 20, 10, 2), 0, 35)
arnoldi <- function(x, T_opt, E, Pf_max){
exp((x-T_opt)/E)*(1-((x-T_opt)/E))*Pf_max
}
# T_opt = optimum temperature
# E= upper critical temperature (i.e. Tmax) minus t_opt
# Pf_max = max performance (e.g. max growth rate)
curve(arnoldi(x, 20, 10, 2), 0, 35)
October 24, 2025 at 11:05 AM
# Arnoldi et al. (2025) function
arnoldi <- function(x, T_opt, E, Pf_max){
exp((x-T_opt)/E)*(1-((x-T_opt)/E))*Pf_max
}
# T_opt = optimum temperature
# E= upper critical temperature (i.e. Tmax) minus t_opt
# Pf_max = max performance (e.g. max growth rate)
curve(arnoldi(x, 20, 10, 2), 0, 35)
arnoldi <- function(x, T_opt, E, Pf_max){
exp((x-T_opt)/E)*(1-((x-T_opt)/E))*Pf_max
}
# T_opt = optimum temperature
# E= upper critical temperature (i.e. Tmax) minus t_opt
# Pf_max = max performance (e.g. max growth rate)
curve(arnoldi(x, 20, 10, 2), 0, 35)
Our thanks to @gleonetwork.bsky.social for hosting this as part of its Limnoseries. And for this impressive catalogue of past workshops & talks on youtube - an excellent resource:
www.youtube.com/@gleonetwork...
www.youtube.com/@gleonetwork...
GLEONetwork
www.youtube.com
October 15, 2025 at 9:58 AM
Our thanks to @gleonetwork.bsky.social for hosting this as part of its Limnoseries. And for this impressive catalogue of past workshops & talks on youtube - an excellent resource:
www.youtube.com/@gleonetwork...
www.youtube.com/@gleonetwork...
If you watch this video and go through the scripts (or attended live), we'd be happy to have your feedback!
docs.google.com/forms/d/e/1F...
docs.google.com/forms/d/e/1F...
Feedback for GLEON experimental design workshop
Thank you for attending the GLEON workshop on 'How to design better experiments' by Mridul K. Thomas & Ravi Ranjan on 23/09/2025! This is a quick survey about your experience at the workshop. We are h...
docs.google.com
October 15, 2025 at 9:52 AM
If you watch this video and go through the scripts (or attended live), we'd be happy to have your feedback!
docs.google.com/forms/d/e/1F...
docs.google.com/forms/d/e/1F...
R scripts and presentation:
github.com/mridulkthoma...
No need to be familiar with Github, just download two files at the link.
github.com/mridulkthoma...
No need to be familiar with Github, just download two files at the link.
GitHub - mridulkthomas/experimental-design-limnoseries-workshop: Materials for workshop "How to Design Better Experiments"
Materials for workshop "How to Design Better Experiments" - mridulkthomas/experimental-design-limnoseries-workshop
github.com
October 15, 2025 at 9:50 AM
R scripts and presentation:
github.com/mridulkthoma...
No need to be familiar with Github, just download two files at the link.
github.com/mridulkthoma...
No need to be familiar with Github, just download two files at the link.
Sure thing! And it's great that you're developing this - I think there's a real need that's broadly felt. Ravi and I taught a short online workshop on this just a couple of days ago and there was a fair amount of interest.
September 26, 2025 at 6:22 PM
Sure thing! And it's great that you're developing this - I think there's a real need that's broadly felt. Ravi and I taught a short online workshop on this just a couple of days ago and there was a fair amount of interest.
On pseudoreplication, I remember the Hurlbert - Oksanen exchanges in the early 2000s being useful.
And following Cottingham et al. 2005, there's @jaytlennon.bsky.social 2011 enviromicro-journals.onlinelibrary.wiley.com/doi/abs/10.1... & Kreyling et al. 2018: onlinelibrary.wiley.com/doi/abs/10.1...
And following Cottingham et al. 2005, there's @jaytlennon.bsky.social 2011 enviromicro-journals.onlinelibrary.wiley.com/doi/abs/10.1... & Kreyling et al. 2018: onlinelibrary.wiley.com/doi/abs/10.1...
To replicate, or not to replicate – that is the question: how to tackle nonlinear responses in ecological experiments
A fundamental challenge in experimental ecology is to capture nonlinearities of ecological responses to interacting environmental drivers. Here, we demonstrate that gradient designs outperform replic...
onlinelibrary.wiley.com
September 26, 2025 at 6:15 PM
On pseudoreplication, I remember the Hurlbert - Oksanen exchanges in the early 2000s being useful.
And following Cottingham et al. 2005, there's @jaytlennon.bsky.social 2011 enviromicro-journals.onlinelibrary.wiley.com/doi/abs/10.1... & Kreyling et al. 2018: onlinelibrary.wiley.com/doi/abs/10.1...
And following Cottingham et al. 2005, there's @jaytlennon.bsky.social 2011 enviromicro-journals.onlinelibrary.wiley.com/doi/abs/10.1... & Kreyling et al. 2018: onlinelibrary.wiley.com/doi/abs/10.1...
On this one aspect of experimental design (multiple driver studies), I'm part a working group that has written a couple of relevant papers in addition to the one Ravi mentioned:
pubmed.ncbi.nlm.nih.gov/29476630/ &
www.sciencedirect.com/science/arti...
pubmed.ncbi.nlm.nih.gov/29476630/ &
www.sciencedirect.com/science/arti...
The need for unrealistic experiments in global change biology
Climate change is an existential threat, and our ability to conduct experiments on how organisms will respond to it is limited by logistics and resour…
www.sciencedirect.com
September 26, 2025 at 6:15 PM
On this one aspect of experimental design (multiple driver studies), I'm part a working group that has written a couple of relevant papers in addition to the one Ravi mentioned:
pubmed.ncbi.nlm.nih.gov/29476630/ &
www.sciencedirect.com/science/arti...
pubmed.ncbi.nlm.nih.gov/29476630/ &
www.sciencedirect.com/science/arti...
This looks great! Looking forward to trying it out.
September 15, 2025 at 8:24 PM
This looks great! Looking forward to trying it out.
Thanks! There isn't a page specifically for this workshop or the series, but the general GLEON page is here: gleon.org
Perhaps more usefully, here are recordings of all previous workshops in the series:
www.youtube.com/@gleonetwork...
Perhaps more usefully, here are recordings of all previous workshops in the series:
www.youtube.com/@gleonetwork...
GLEONetwork
www.youtube.com
September 15, 2025 at 2:05 PM
Thanks! There isn't a page specifically for this workshop or the series, but the general GLEON page is here: gleon.org
Perhaps more usefully, here are recordings of all previous workshops in the series:
www.youtube.com/@gleonetwork...
Perhaps more usefully, here are recordings of all previous workshops in the series:
www.youtube.com/@gleonetwork...
Thanks, Thomas!
September 15, 2025 at 1:15 PM
Thanks, Thomas!
This @gleonetwork.bsky.social workshop series is aimed at limnologists but it's open to all. We are targetting PhD students and postdocs across the environmental sciences.
September 15, 2025 at 11:20 AM
This @gleonetwork.bsky.social workshop series is aimed at limnologists but it's open to all. We are targetting PhD students and postdocs across the environmental sciences.