Novel approach distinguishes cause-and-effect from misleading correlation

Sep 28, 2012 by Mario Aguilera
A new technique called convergent cross mapping tests for causation in time series data.

(—Is fishing alone responsible for stock collapses, or are there other dominant factors? Determining the causes driving changes in complex networks such as ecosystems is especially challenging. Until recently, scientists had a limited toolbox for detecting causation. Often they would correlate two variables and suggest it implied causation. Yet as long ago as 1710, Irish philosopher Bishop Berkeley remarked "correlation does not imply causation."

George Sugihara of Scripps Institution of Oceanography at UC San Diego and colleagues from around the world have developed a new approach to help ecologists distinguish true causal interactions from misleading correlations.

Published in the most recent online issue of the journal Science, the method described in the paper, "Detecting Causality in Complex Ecosystems," extracts the "signature" left by causes embedded in ecological observations—historical records known as time series. The new deduces causes from the affects.

For example, their technique, called "convergent cross mapping," was applied to time series records of anchovy and sardine populations to determine whether the species are interacting and responsible for the ups and downs of the other. Using a combination of data from the California Department of Fish and Game and CalCOFI (the Scripps-based California Cooperative Oceanic Fisheries Investigations program), one of the world's longest marine monitoring efforts, the researchers confirmed that even though the booms and busts of sardines and anchovies move lock step in opposite directions, they were not affecting each other (a spurious correlation much like the numbers of Republicans in the Senate and sunspots). However, the tool was able to uncover that , though not correlated with either , are a hidden force driving changes for both stocks.

"The major novelty of this method is that it is based on a dynamic and interconnected view of nature," said Sugihara, the McQuown Chair Distinguished Professor of Natural Science at Scripps. "Ice cream sales and rates of violent crime might rise and fall at the same time, but our method is able to determine whether this is due to cause-and-effect, or whether both are simply more common during hot summer months."

The new tool is distinct from methods developed by UC San Diego economists Clive Granger and Robert Engle for financial and economic data, which earned them the Nobel Prize in Economic Sciences. Granger's technique is aimed at purely random systems rather than those having rules governing how the parts move. Sugihara and his colleagues developed their tool specifically for complex ecosystem analysis, yet its applications could have far-ranging implications across multiple areas of science. For example, "one could imagine using it with epidemiological data to see if different diseases interact with each other or have environmental causes," said Sugihara.

Sugihara and other Scripps scientists are now applying this tool to study specific ocean phenomena, such as the seemingly unpredictable harmful algal blooms that occur in various coastal regions from time to time.

Explore further: Invasive vines swallow up New York's natural areas

Related Stories

Scripps Oceanography Research pegs ID of red tide killer

May 01, 2008

Researchers at Scripps Institution of Oceanography at UC San Diego have identified a potential “red tide killer.” Red tides and related phenomena in which microscopic algae accumulate rapidly in dense ...

Fish collection moves into the digital age

Mar 21, 2006

University of California-San Diego scientists say the same technology used to image brain tumors is taking the field of marine biology to new dimensions.

Recommended for you

Invasive vines swallow up New York's natural areas

3 hours ago

( —When Antonio DiTommaso, a Cornell weed ecologist, first spotted pale swallow-wort in 2001, he was puzzled by it. Soon he noticed many Cornell old-field edges were overrun with the weedy vines. ...

Citizen scientists match research tool when counting sharks

18 hours ago

Shark data collected by citizen scientists may be as reliable as data collected using automated tools, according to results published April 23, 2014, in the open access journal PLOS ONE by Gabriel Vianna from The University of Wes ...

Researchers detail newly discovered deer migration

Apr 23, 2014

A team of researchers including University of Wyoming scientists has documented the longest migration of mule deer ever recorded, the latest development in an initiative to understand and conserve ungulate ...

How Australia got the hump with one million feral camels

Apr 23, 2014

A new study by a University of Exeter researcher has shed light on how an estimated one million-strong population of wild camels thriving in Australia's remote outback have become reviled as pests and culled ...

Former Iron Curtain still barrier for deer

Apr 23, 2014

The Iron Curtain was traced by an electrified barbed-wire fence that isolated the communist world from the West. It was an impenetrable Cold War barrier—and for some inhabitants of the Czech Republic it ...

Humpback protections downgrade clears way for pipeline

Apr 22, 2014

Environmentalist activists on Tuesday decried Canada's downgrading of humpback whale protections, suggesting the decision was fast-tracked to clear a major hurdle to constructing a pipeline to the Pacific ...

User comments : 9

Adjust slider to filter visible comments by rank

Display comments: newest first

1 / 5 (2) Sep 28, 2012
Where does this fail - for both the authors and the Nobel winners methods.

Infallibility is not an option.
4 / 5 (1) Sep 28, 2012
I'm not sure I understand the article. How does this differ from a multivariate discriminant analysis?
4 / 5 (1) Sep 28, 2012
Just a guess is that it somehow uses signal phase to infer causation. Disappointing lack of detail in the article.
4 / 5 (1) Sep 28, 2012
As always.
1 / 5 (1) Sep 28, 2012
Just a guess is that it somehow uses signal phase to infer causation. Disappointing lack of detail in the article.

This video explains it in a bit more detail http://www.youtub...7udsPKms
The paper itself is locked up in one of those outrageously priced journals from the 19th century.
not rated yet Sep 28, 2012
"The new mathematical approach deduces causes from the affects"

'Affects' is a verb.
1 / 5 (1) Sep 29, 2012
"The new mathematical approach deduces causes from the affects"
'Affects' is a noun in psychological jargon.

The graphics provided with the press release resemble attractors. I doubt Karl Popper would have anything supportive to say about this paper.

This is the first time I have seen the quote attributed to Bishop George Berkeley. Edward R. Tufte fleshed it out nicely, and he is a favorite, let's credit him.
1 / 5 (1) Sep 29, 2012
Great extra points from Meyer and DrHoo.

'Near neighboring points can be used to infer causation.'
The nearer the neighboring points are the greater the inference?

The authors assert this. What led to that assertion?
1 / 5 (1) Sep 29, 2012
MDA supports classification.
The article is more akin to Ray Solomonoff's work - A Formal Theory of Inductive Inference, Part 1 and Part 2 in Information and Control.

More news stories

New breast cancer imaging method promising

The new PAMmography method for imaging breast cancer developed by the University of Twente's MIRA research institute and the Medisch Spectrum Twente hospital appears to be a promising new method that could ...

Research proves nanobubbles are superstable

The intense research interest in surface nanobubbles arises from their potential applications in microfluidics and the scientific challenge for controlling their fundamental physical properties. One of the ...

Using antineutrinos to monitor nuclear reactors

When monitoring nuclear reactors, the International Atomic Energy Agency has to rely on input given by the operators. In the future, antineutrino detectors may provide an additional option for monitoring. ...