SSR_check_signal {multispatialCCM}

Test process for auto-predictability.

Description

Predict elements of a process based historical observations of that process using cross-validation. Tests whether past observations are able to make good estimates of future elements of the time series.

Usage

SSR_check_signal(A, E, tau = 1,
predsteplist = 1:10, matchSugi = 0)

Arguments

A

Process to be predicted. Should be a single vector. If data come from multiple time series, gaps between these should be marked with an "NA".

E

Embedding dimension to use for the analysis. Should be based on dimension that provides the best prediction of process A against itself using function "SSR_pred_boot" (state space reconstruction).

tau

Number of time steps to use for lagged components in the attractor space. Defaults to 1.

predsteplist

Vector of time step lengths for prediction.

matchSugi

Set to 1 to match results in Sugihara et al. publication described below, which removes only point i in cross validation - if 0, then removes all points within X(t-(E-1)):X(t+1)

Value

predatout=predatout, rho_pre_slope=rho_pre_slope, rho_predmaxCI=rho_predmaxCI

predatout

Vector of rho values describing predictive ability of process against itself for each prediction time step length

rho_pre_slope

Slope of rho values as a function of prediction distance

rho_predmaxCI

95% confidence interval for rho value corresponding to the longest prediction interval tested

Author(s)

Adam Clark

References

Sugihara, G., R. May, H. Ye, C. Hsieh, E. Deyle, M. Fogarty, and S. Munch. 2012. Detecting Causality in Complex Ecosystems. Science 338.

Adam T. Clark, H. Ye, Forest Isbell, Ethan R. Deyle, Jane Cowles, David Tilman, and George Sugihara. 2015. Spatial ’convergent cross mapping’ to detect causal relationships from short time-series. Ecology, 96(6):1174–1181.

See Also

CCM_boot, SSR_pred_boot, ccmtest

Examples

#Simulate data to use for multispatial CCM test
#See function for details - A is causally forced by B,
#but the reverse is not true.
ccm_data_out<-make_ccm_data()
Accm<-ccm_data_out$Accm
Bccm<-ccm_data_out$Bccm

#Set optimal E - see multispatialCCM for details
E_A<-2
E_B<-3

#Check data for nonlinear signal that is not dominated by noise
#Checks whether predictive ability of processes declines with
#increasing time distance
#See manuscript and R code for details
signal_A_out<-SSR_check_signal(A=Accm, E=E_A, tau=1,
  predsteplist=1:10)
signal_B_out<-SSR_check_signal(A=Bccm, E=E_B, tau=1,
  predsteplist=1:10)