Spatial convergent cross mapping to detect causal relationships from short time series

Adam Thomas Clark, Hao Ye, Forest Isbell, Ethan R. Deyle, Jane Cowles, G. David Tilman, George Sugihara, B. D. Inouye

Research output: Contribution to journalArticle

58 Citations (Scopus)

Abstract

Recent developments in complex systems analysis have led to new techniques for detecting causal relationships using relatively short time series, on the order of 30 sequential observations. Although many ecological observation series are even shorter, perhaps fewer than ten sequential observations, these shorter time series are often highly replicated in space (i.e., plot replication). Here, we combine the existing techniques of convergent cross mapping (CCM) and dewdrop regression to build a novel test of causal relations that leverages spatial replication, which we call multispatial CCM. Using examples from simulated and real-world ecological data, we test the ability of multispatial CCM to detect causal relationships between processes. We find that multispatial CCM successfully detects causal relationships with as few as five sequential observations, even in the presence of process noise and observation error. Our results suggest that this technique may constitute a useful test for causality in systems where experiments are difficult to perform and long time series are not available. This new technique is available in the multispatialCCM package for the R programming language.

Original languageEnglish (US)
Pages (from-to)1174-1181
Number of pages8
JournalEcology
Volume96
Issue number5
DOIs
StatePublished - May 1 2015

Fingerprint

time series analysis
time series
systems analysis
testing
methodology
test
experiment

Keywords

  • Causality
  • Convergent cross mapping
  • Dewdrop regression
  • MultispatialCCM
  • Spatial replication
  • Time series

Cite this

Spatial convergent cross mapping to detect causal relationships from short time series. / Clark, Adam Thomas; Ye, Hao; Isbell, Forest; Deyle, Ethan R.; Cowles, Jane; Tilman, G. David; Sugihara, George; Inouye, B. D.

In: Ecology, Vol. 96, No. 5, 01.05.2015, p. 1174-1181.

Research output: Contribution to journalArticle

Clark, AT, Ye, H, Isbell, F, Deyle, ER, Cowles, J, Tilman, GD, Sugihara, G & Inouye, BD 2015, 'Spatial convergent cross mapping to detect causal relationships from short time series', Ecology, vol. 96, no. 5, pp. 1174-1181. https://doi.org/10.1890/14-1479.1
Clark, Adam Thomas ; Ye, Hao ; Isbell, Forest ; Deyle, Ethan R. ; Cowles, Jane ; Tilman, G. David ; Sugihara, George ; Inouye, B. D. / Spatial convergent cross mapping to detect causal relationships from short time series. In: Ecology. 2015 ; Vol. 96, No. 5. pp. 1174-1181.
@article{5a918bddfa5141a1a664f274b56e6a0e,
title = "Spatial convergent cross mapping to detect causal relationships from short time series",
abstract = "Recent developments in complex systems analysis have led to new techniques for detecting causal relationships using relatively short time series, on the order of 30 sequential observations. Although many ecological observation series are even shorter, perhaps fewer than ten sequential observations, these shorter time series are often highly replicated in space (i.e., plot replication). Here, we combine the existing techniques of convergent cross mapping (CCM) and dewdrop regression to build a novel test of causal relations that leverages spatial replication, which we call multispatial CCM. Using examples from simulated and real-world ecological data, we test the ability of multispatial CCM to detect causal relationships between processes. We find that multispatial CCM successfully detects causal relationships with as few as five sequential observations, even in the presence of process noise and observation error. Our results suggest that this technique may constitute a useful test for causality in systems where experiments are difficult to perform and long time series are not available. This new technique is available in the multispatialCCM package for the R programming language.",
keywords = "Causality, Convergent cross mapping, Dewdrop regression, MultispatialCCM, Spatial replication, Time series",
author = "Clark, {Adam Thomas} and Hao Ye and Forest Isbell and Deyle, {Ethan R.} and Jane Cowles and Tilman, {G. David} and George Sugihara and Inouye, {B. D.}",
year = "2015",
month = "5",
day = "1",
doi = "10.1890/14-1479.1",
language = "English (US)",
volume = "96",
pages = "1174--1181",
journal = "Ecology",
issn = "0012-9658",
publisher = "Ecological Society of America",
number = "5",

}

TY - JOUR

T1 - Spatial convergent cross mapping to detect causal relationships from short time series

AU - Clark, Adam Thomas

AU - Ye, Hao

AU - Isbell, Forest

AU - Deyle, Ethan R.

AU - Cowles, Jane

AU - Tilman, G. David

AU - Sugihara, George

AU - Inouye, B. D.

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Recent developments in complex systems analysis have led to new techniques for detecting causal relationships using relatively short time series, on the order of 30 sequential observations. Although many ecological observation series are even shorter, perhaps fewer than ten sequential observations, these shorter time series are often highly replicated in space (i.e., plot replication). Here, we combine the existing techniques of convergent cross mapping (CCM) and dewdrop regression to build a novel test of causal relations that leverages spatial replication, which we call multispatial CCM. Using examples from simulated and real-world ecological data, we test the ability of multispatial CCM to detect causal relationships between processes. We find that multispatial CCM successfully detects causal relationships with as few as five sequential observations, even in the presence of process noise and observation error. Our results suggest that this technique may constitute a useful test for causality in systems where experiments are difficult to perform and long time series are not available. This new technique is available in the multispatialCCM package for the R programming language.

AB - Recent developments in complex systems analysis have led to new techniques for detecting causal relationships using relatively short time series, on the order of 30 sequential observations. Although many ecological observation series are even shorter, perhaps fewer than ten sequential observations, these shorter time series are often highly replicated in space (i.e., plot replication). Here, we combine the existing techniques of convergent cross mapping (CCM) and dewdrop regression to build a novel test of causal relations that leverages spatial replication, which we call multispatial CCM. Using examples from simulated and real-world ecological data, we test the ability of multispatial CCM to detect causal relationships between processes. We find that multispatial CCM successfully detects causal relationships with as few as five sequential observations, even in the presence of process noise and observation error. Our results suggest that this technique may constitute a useful test for causality in systems where experiments are difficult to perform and long time series are not available. This new technique is available in the multispatialCCM package for the R programming language.

KW - Causality

KW - Convergent cross mapping

KW - Dewdrop regression

KW - MultispatialCCM

KW - Spatial replication

KW - Time series

UR - http://www.scopus.com/inward/record.url?scp=85021261674&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021261674&partnerID=8YFLogxK

U2 - 10.1890/14-1479.1

DO - 10.1890/14-1479.1

M3 - Article

C2 - 26236832

AN - SCOPUS:84929119897

VL - 96

SP - 1174

EP - 1181

JO - Ecology

JF - Ecology

SN - 0012-9658

IS - 5

ER -