Abstract
A new information matrix [F] with elements F mn = 〈 (y m - a m )(y n - a n) (∂ ln p(y | a)/∂a m ) (∂ ln p(y | a)/∂a n ) 〉 is analyzed. The PDF p(y | a) is the usual likelihood law. [F] differs from the Fisher information matrix by the presence of the first two factors in the given expectation. These factors make F mn unitless, in contrast with the Fisher information. This lack of units allows F mn values from entirely different phenomena to be compared as, for example, Shannon information values can be compared. Each element F mn defines an error inequality analogous to the Cramer-Rao inequality. In the scalar case F mn ≡ F, for a normal p(y|a) law F = 3, while for an exponential law F = 9. A variational principle F = min (called FMIN) allows an unknown PDF p(x) to be estimated in the presence of weak information. Under certain conditions F obeys a “Boltzmann F-theorem” ∂F/∂t ⩽ 0, indicating that F is a physical entropy. Finally, the trace ℱ of [F] may be used as the scalar information quantity in an information-based principle for deriving distribution laws p of physics.
Similar content being viewed by others
REFERENCES
H. L. Van Trees, Detection, Estimation, and Modulation Theory, Part I (Wiley, New York, 1968).
B. R. Frieden and R. J. Hughes, Phys. Rev. E 49, 2644–2649 (1994).
B. R. Frieden, in Advances in Imaging and Electron Physics, Vol. 90, P. W. Hawkes, ed. (Academic, Orlando, FL, 1995), pp. 123–204.
B. R. Frieden and B. H. Soffer, Phys. Rev. E 52, 2274–2286 (1995).
B. R. Frieden and W. J. Cocke, Phys. Rev. E 54, 257–260 (1996).
W. J. Cocke, Phys. Fluids A 8, 1609–1614 (1996).
B. R. Frieden, Physics from Fisher Information (Cambridge University Press, Cambridge, 1998).
A. J. Stam, Inf. Control 2, 101–112 (1959).
B. R. Frieden, Probability, Statistical Optics and Data Testing, 2nd edn. (Springer, New York, 1991).
F. Reza, An Introduction to Information Theory (McGraw-Hill, New York, 1961).
Ref. 4, Appendices A and C.
G. A. Korn and T. M. Korn, Mathematical Handbook, 2nd edn. (McGraw-Hill, New York, 1968).
E. Kamke, Differentialgleichungen Losungsmethoden und Losungen (Chelsea, New York, 1948).
B. R. Frieden, Found. Phys. 16, 883–906 (1986).
F. Benford, Proc. Am. Philos. Soc. 78, 551–572 (1938).
H. H. Jeffreys, Theory of Probability, 3rd edn. (Oxford University Press, London, 1961).
A. R. Plastino and A. Plastino, Phys. Rev. E 54, 4423–4426 (1996).
Ref. 9, p. 50.
Rights and permissions
About this article
Cite this article
Frieden, B.R. F-Information, a Unitless Variant of Fisher Information. Foundations of Physics 29, 1521–1541 (1999). https://doi.org/10.1023/A:1018806603833
Issue Date:
DOI: https://doi.org/10.1023/A:1018806603833