From 03/31, see below for more!
Outline
Title
On the ability to detect leading indicators of catastrophe in unreplicated time series
Introduction Background on Warning Signals
- literature
- Saddle Node bifurcation
- Detecting decreasing stabilization – gradual vs changepoint estimation
Reasons detection can fail:
- Ergodicity: ensembles vs single instances
- Sufficient statistical power
- Appropriate dynamics
Methods
- Defining an indicator – significant Kendall rank correlation coefficient τ as in doi:10.1073/pnas.0802430105
- Simulation approach
- Analytic limits
- accounting for delay?
Figures
- Saddle node bifurcation example – should discuss difference between stochastic and deterministic edge?
- Single replicates using standard detection statistics
Results/Discussion
- Misleading indicators
- Need for further exploration
### Towards a better approach
- Estimating the linear system directly:
- estimating the exponential coefficient λ of the autocorrelation function directly. Contrast to the autocorrelation. Estimating spectral width.
- estimating variance directly:
Compare to ARMA approach of
- Ziebarth NL, Abbott KC, and Ives AR. . pmid:19849710. PubMed HubMed [Ives2010]
- Changepoint analysis vs gradual trends.
- i.e. web example,
- book,
- Bayesian / Dirchelet Process Prior analysis,
- model selection.
- Examples from software:
- correlation C executable
- R: source(“warning_signals.R”) example.
Other topics
- F1000
- Workstation order
- Adaptive Dynamics manuscript
- Labrids Manuscript
Updated Outline
- Warning Signals intro (Alan)
- Scope & previous work -> 1D (Alan)
- Reasons Detection can fail (Carl)
- Methods -> defining an indicator (Carl)
- Simulation approach (Carl)
- Analytic limits (Carl – still to do)
- Accounting for delay (Carl – still to do)
- Results – saddle node (Carl – still to do)
- Results – single replicate (Carl – still to do)
- Conclusions (Alan / both)