A measure of statistical complexity based on predictive information

Details A measure of statistical complexity based on predictive information A measure of statistical complexity based on predictive information

2010-12-08

arxiv.org/abs/1012.1890v1

Mathematics

Statistics Theory

4 pages, 3 figures

Scientific paper

We introduce an information theoretic measure of statistical structure, called 'binding information', for sets of random variables, and compare it with several previously proposed measures including excess entropy, Bialek et al.'s predictive information, and the multi-information. We derive some of the properties of the binding information, particularly in relation to the multi-information, and show that, for finite sets of binary random variables, the processes which maximises binding information are the 'parity' processes. Finally we discuss some of the implications this has for the use of the binding information as a measure of complexity.

Affiliated with

Also associated with

No associations

Rating

A measure of statistical complexity based on predictive information does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with A measure of statistical complexity based on predictive information, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A measure of statistical complexity based on predictive information will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-76313