Causality detection - Revision history

Admin at 10:40, 26 January 2023

2023-01-26T10:40:55Z

← Older revision		Revision as of 12:40, 26 January 2023
Line 8:		Line 8:
	Thus, causality typically involves at least a temporal ''delay'' between the two events.		Thus, causality typically involves at least a temporal ''delay'' between the two events.

	In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956, ISBN 0486497461</ref> It states:		In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956, {{ISBN\|0486497461}}</ref> It states:
	* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.		* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.

Admin: /* Traditional approaches */

2014-10-22T13:28:56Z

Traditional approaches

← Older revision		Revision as of 15:28, 22 October 2014
Line 19:		Line 19:
	* Quantify parameters related to system evolution (growth rates, damping rates).		* Quantify parameters related to system evolution (growth rates, damping rates).
	* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additional reasoning (based on physical insight or models) may allow drawing conclusions.		* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additional reasoning (based on physical insight or models) may allow drawing conclusions.
	In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks'',[[doi:10.1063/1.873728\|Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.		In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks'', [[doi:10.1063/1.873728\|Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.

	== Analysis techniques ==		== Analysis techniques ==

Admin: /* Traditional approaches */

2014-10-22T13:28:42Z

Traditional approaches

← Older revision		Revision as of 15:28, 22 October 2014
Line 19:		Line 19:
	* Quantify parameters related to system evolution (growth rates, damping rates).		* Quantify parameters related to system evolution (growth rates, damping rates).
	* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additional reasoning (based on physical insight or models) may allow drawing conclusions.		* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additional reasoning (based on physical insight or models) may allow drawing conclusions.
	In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks,[[doi:10.1063/1.873728\|'' Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.		In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks'',[[doi:10.1063/1.873728\|Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.

	== Analysis techniques ==		== Analysis techniques ==

Admin: /* Traditional approaches */

2014-03-21T09:53:54Z

Traditional approaches

← Older revision		Revision as of 11:53, 21 March 2014
Line 18:		Line 18:
	* Predict the system evolution from a (numerical) model. If successful, the model equations may reveal causal relations.		* Predict the system evolution from a (numerical) model. If successful, the model equations may reveal causal relations.
	* Quantify parameters related to system evolution (growth rates, damping rates).		* Quantify parameters related to system evolution (growth rates, damping rates).
	* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but ~~additioal~~ reasoning (based on physical insight or models) may allow drawing conclusions.		* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additional reasoning (based on physical insight or models) may allow drawing conclusions.
	In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks,[[doi:10.1063/1.873728\|'' Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.		In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks,[[doi:10.1063/1.873728\|'' Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.

Admin: /* Traditional approaches */

2014-03-21T09:53:20Z

Traditional approaches

← Older revision		Revision as of 11:53, 21 March 2014
Line 15:		Line 15:
	Traditional approaches to the determination of causal relationships between various (fluctuating) variables include a wide range of methods.		Traditional approaches to the determination of causal relationships between various (fluctuating) variables include a wide range of methods.
	* If intervention in the system is possible, one may control (modulate) one variable and observe the (delayed) effect on other variables.		* If intervention in the system is possible, one may control (modulate) one variable and observe the (delayed) effect on other variables.
	* Observe systematic time delays between characteristic events or observe systematic precursors to ~~charactaristic~~ events.		* Observe systematic time delays between characteristic events or observe systematic precursors to characteristic events.
	* Predict the system evolution from a (numerical) model. If successful, the model equations may reveal causal relations.		* Predict the system evolution from a (numerical) model. If successful, the model equations may reveal causal relations.
	* Quantify parameters related to system evolution (growth rates, damping rates).		* Quantify parameters related to system evolution (growth rates, damping rates).

Admin at 09:52, 21 March 2014

2014-03-21T09:52:10Z

← Older revision		Revision as of 11:52, 21 March 2014
Line 3:		Line 3:
	== Definition of causality ==		== Definition of causality ==

	To start with, it is not even easy to ''define'' what causality means exactly. <ref>[[Wikipedia:Causality]]</ref><ref>[[Wikipedia:Causality_(physics)]]</ref> In philosophy, causality typically refers to a relation between two events X and Y such that:		To start with, it is not even easy to ''define'' what causality means exactly. <ref>[[Wikipedia:Causality\|Causality]]</ref><ref>[[Wikipedia:Causality_(physics)\|Causality_(physics)]]</ref> In philosophy, causality typically refers to a relation between two events X and Y such that:
	* if Y occurs, then X will occur; or		* if Y occurs, then X will occur; or
	* if X occurs, then Y must have occured.		* if X occurs, then Y must have occured.
Line 26:		Line 26:
	<ref>K. Hlaváková-Schindler, M. Palus, M. Vejmelka, and J. Bhattacharya. ''Causality detection based on information-theoretic approaches in time series analysis'', [[doi:10.1016/j.physrep.2006.12.004\|Phys. Reports, '''441'''(1):1, 2007]]</ref>		<ref>K. Hlaváková-Schindler, M. Palus, M. Vejmelka, and J. Bhattacharya. ''Causality detection based on information-theoretic approaches in time series analysis'', [[doi:10.1016/j.physrep.2006.12.004\|Phys. Reports, '''441'''(1):1, 2007]]</ref>

	Recently, a specific technique taken from Information Theory (the 'Transfer Entropy')<ref>T. Schreiber, ''Measuring information transfer'', [[doi:10.1103/PhysRevLett.85.461\|Phys. Rev. Lett., '''85'''(2):461, 2000]]</ref> was applied succesfully to fluctuation data from fusion devices.		Recently, a specific technique taken from Information Theory (the [[:Wikipedia:Transfer entropy\|Transfer Entropy]])<ref>T. Schreiber, ''Measuring information transfer'', [[doi:10.1103/PhysRevLett.85.461\|Phys. Rev. Lett., '''85'''(2):461, 2000]]</ref> was applied succesfully to fluctuation data from fusion devices.
	<ref>B.Ph. van Milligen, G. Birkenmeier, M. Ramisch, T. Estrada, C. Hidalgo, and A. Alonso, ''Causality detection and turbulence in fusion plasmas'', [[doi:10.1088/0029-5515/54/2/023011\|Nucl. Fusion 54 (2014), 023011]]</ref>		<ref>B.Ph. van Milligen, G. Birkenmeier, M. Ramisch, T. Estrada, C. Hidalgo, and A. Alonso, ''Causality detection and turbulence in fusion plasmas'', [[doi:10.1088/0029-5515/54/2/023011\|Nucl. Fusion 54 (2014), 023011]]</ref>

	== References ==		== References ==
	<references />		<references />

Admin: Added Traditional Approaches

2014-03-21T09:48:05Z

Added Traditional Approaches

← Older revision		Revision as of 11:48, 21 March 2014
Line 10:		Line 10:
	In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956, ISBN 0486497461</ref> It states:		In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956, ISBN 0486497461</ref> It states:
	* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.		* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.

			== Traditional approaches ==

			Traditional approaches to the determination of causal relationships between various (fluctuating) variables include a wide range of methods.
			* If intervention in the system is possible, one may control (modulate) one variable and observe the (delayed) effect on other variables.
			* Observe systematic time delays between characteristic events or observe systematic precursors to charactaristic events.
			* Predict the system evolution from a (numerical) model. If successful, the model equations may reveal causal relations.
			* Quantify parameters related to system evolution (growth rates, damping rates).
			* Use techniques such as correlations, conditional averages; these linear analysis techniques by themselves cannot reveal causality, but additioal reasoning (based on physical insight or models) may allow drawing conclusions.
			In the fusion context, see <ref>K.H. Burrell, ''Tests of causality: Experimental evidence that sheared <math>E \times B</math> flow alters turbulence and transport in tokamaks,[[doi:10.1063/1.873728\|'' Phys. Plasmas, '''6'''(12):4418, 1999]]</ref>.

	== Analysis techniques ==		== Analysis techniques ==

	Several techniques have been elaborated to quantify ~~this statement~~ on the basis of measured time series.		Several techniques have been elaborated to quantify Wiener's causality on the basis of measured time series.
	<ref>K. Hlaváková-Schindler, M. Palus, M. Vejmelka, and J. Bhattacharya. ''Causality detection based on information-theoretic approaches in time series analysis'', [[doi:10.1016/j.physrep.2006.12.004\|Phys. Reports, '''441'''(1):1, 2007]]</ref>		<ref>K. Hlaváková-Schindler, M. Palus, M. Vejmelka, and J. Bhattacharya. ''Causality detection based on information-theoretic approaches in time series analysis'', [[doi:10.1016/j.physrep.2006.12.004\|Phys. Reports, '''441'''(1):1, 2007]]</ref>

Admin: ISBN added

2014-03-21T09:32:38Z

ISBN added

← Older revision		Revision as of 11:32, 21 March 2014
Line 8:		Line 8:
	Thus, causality typically involves at least a temporal ''delay'' between the two events.		Thus, causality typically involves at least a temporal ''delay'' between the two events.

	In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956</ref> It states:		In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener\|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956, ISBN 0486497461</ref> It states:
	* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.		* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.

Admin: New page on causality

2014-03-21T09:17:14Z

New page on causality

New page

The determination of a causal interaction between fluctuating variables in a complex system, such as a fusion-grade plasma, is not straightforward.

== Definition of causality ==

To start with, it is not even easy to ''define'' what causality means exactly. <ref>[[Wikipedia:Causality]]</ref><ref>[[Wikipedia:Causality_(physics)]]</ref> In philosophy, causality typically refers to a relation between two events X and Y such that:
* if Y occurs, then X will occur; or
* if X occurs, then Y must have occured.
Thus, causality typically involves at least a temporal ''delay'' between the two events.

In the context of data analysis, it is more productive to adopt [[Wikipedia:Norbert_Wiener|Wiener]]'s 'quantifiable causality'. <ref>N. Wiener. ''The theory of prediction.'' Modern Mathematics for Engineers, Mc-Graw Hill, New York, 1956</ref> It states:
* if we can predict X better by using the past information from Y than without it, then we call Y causal to X.

== Analysis techniques ==

Several techniques have been elaborated to quantify this statement on the basis of measured time series.
<ref>K. Hlaváková-Schindler, M. Palus, M. Vejmelka, and J. Bhattacharya. ''Causality detection based on information-theoretic approaches in time series analysis'', [[doi:10.1016/j.physrep.2006.12.004|Phys. Reports, '''441'''(1):1, 2007]]</ref>

Recently, a specific technique taken from Information Theory (the 'Transfer Entropy')<ref>T. Schreiber, ''Measuring information transfer'', [[doi:10.1103/PhysRevLett.85.461|Phys. Rev. Lett., '''85'''(2):461, 2000]]</ref> was applied succesfully to fluctuation data from fusion devices.
<ref>B.Ph. van Milligen, G. Birkenmeier, M. Ramisch, T. Estrada, C. Hidalgo, and A. Alonso, ''Causality detection and turbulence in fusion plasmas'', [[doi:10.1088/0029-5515/54/2/023011|Nucl. Fusion 54 (2014), 023011]]</ref>

== References ==
<references />