adam_t_clark

Excited that our paper on measuring stability in systems without static equilibria is finally out!: https://doi.org/10.1002/ecs2.4328

Applies a mix of EDM & state space modelling to separate observation error, process noise, & deterministic variability in timeseries. The EDM backbone can be fit to very complex timeseries with little or no a priori information about underlying processes. The result is akin to a "detrended" coefficient of variation (CV), after accounting for deterministic variability. 1/2

Dec 28, 2022 at 4:07pmWeb
Show threadadam_t_clarkDec 28, 2022

Package currently on GitHub here: https://github.com/adamtclark/pttstability. Soon to be on CRAN too, as pttstability (I hope...).

Hat tip to @hye, A. Compagnoni, F. Hamilton, F. Hartig, C. Lawson, @brosenbaum, and many others for their advice on methods. And many thanks to coauthors Lina Mühlbauer, @hhillebr1, and @planetmicroeco for their patience and support over the 2+ years it took to write this up. 2/2

GitHub - adamtclark/pttstability: Github page for the pttstability package (formatted for devtools deployment)

Github page for the pttstability package (formatted for devtools deployment) - GitHub - adamtclark/pttstability: Github page for the pttstability package (formatted for devtools deployment)

GitHub
Show threadadam_t_clarkJan 10, 2023

And, we're finally live! Many thanks to the volunteers at CRAN for their help and patience!
https://cran.r-project.org/web/packages/pttstability/index.html

@hye @brosenbaum @hhillebr1

pttstability: Particle-Takens Stability

Includes a collection of functions presented in "Measuring stability in ecological systems without static equilibria" by Clark et al. (2022) <<a href="https://doi.org/10.1002%2Fecs2.4328">doi:10.1002/ecs2.4328</a>> in Ecosphere. These can be used to estimate the parameters of a stochastic state space model (i.e. a model where a time series is observed with error). The goal of this package is to estimate the variability around a deterministic process, both in terms of observation error - i.e. variability due to imperfect observations that does not influence system state - and in terms of process noise - i.e. stochastic variation in the actual state of the process. Unlike classical methods for estimating variability, this package does not necessarily assume that the deterministic state is fixed (i.e. a fixed-point equilibrium), meaning that variability around a dynamic trajectory can be estimated (e.g. stochastic fluctuations during predator-prey dynamics).

Show threadGraciela Gil-RomeraDec 28, 2022
Wow @adam_t_clark sounds like a must read for my after-holidays week 😍