Construct · 1 fields · 3 citations

Granger causality: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaningcausationcompare the meanings
How to read this

Every construct on the map is compared with every other by the meaning of its definitions, and the closest one is surfaced here. The nearest construct to Granger causality is causation.

Hold this as a prompt, not a verdict. Two constructs sitting close in meaning is a reason to read them side by side and decide for yourself whether they are one idea under two names. It is not proof that they are. Compare the meanings in the Collider.

Grangercausality1 CONSTRUCTGranger causalityGRANGER · CAUSALITY

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

Econometrics

one time series Granger-causes another if its past values predict the second better than the second's own past alone.

Clive Granger's 1969 paper in Econometrica defined what is now called Granger causality: one time series is said to Granger-cause a second if the past values of the first help predict the second more accurately than the second's own past values alone. A time series here is just a variable recorded repeatedly over time, such as monthly money supply or quarterly output, and the definition asks a narrow question about prediction rather than about true cause and effect. Granger himself, in his 1980 restatement Testing for causality, stressed that the relation is about predictability given a chosen set of information and a time ordering, so it can appear even when no genuine causal mechanism links the two variables, and can be absent even when one does exist but acts through omitted variables or through effects that are simultaneous rather than lagged. What makes the construct a landmark is that it gave researchers an operational, testable definition of directional influence between variables when controlled experiments are impossible, and it remains the standard framing for lead-lag analysis across econometrics, neuroscience, and climate science. Later work such as Toda and Yamamoto's 1995 procedure extended the test to variables that trend or drift over time.[1][2][3]

Unit
A directional predictive relation between two time series, present or absent given a specified information set and time ordering
Recovery means
Not applicable
Measured by
Tested with an F-test on the lagged values of the candidate predictor in a vector autoregression; extended by the Toda and Yamamoto (1995) procedure for series that trend or drift

Next

Run it through the Collider, or take the citations with you.

See how Granger causality sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this entry

Nearby constructs

causation6 fields · 15 citationsjingle · one name, six constructsprediction3 fields · 4 citationsjingle · one word, three constructscorrelation4 fields · 4 citationsjingle · one word, four constructs

References

  1. Granger, C. W. J. (1969). Investigating causal relations by econometric models and cross-spectral methods. Econometrica, 37(3), 424–438. https://doi.org/10.2307/1912791
  2. Granger, C. W. J. (1980). Testing for causality: A personal viewpoint. Journal of Economic Dynamics and Control, 2, 329–352. https://doi.org/10.1016/0165-1889(80)90069-X
  3. Toda, H. Y., & Yamamoto, T. (1995). Statistical inference in vector autoregressions with possibly integrated processes. Journal of Econometrics, 66(1–2), 225–250. https://doi.org/10.1016/0304-4076(94)01616-8

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct