The Standard Normal Distribution Has Finite Fisher Information, Score Minus the Identity, and Fisher Information One
lemmaAnalysisProbabilitylem:standard-normal-score-2026aThe standard normal distribution on the real line is the measure with density exp(-x^2/2)/c with respect to Lebesgue measure, a positive continuously differentiable density whose derivative is -x times the density; it has second moment one, finite Fisher information, score equal to minus the identity map and Fisher information equal to one.
In the setting of Square-Integrable Vector Fields Against a Probability Measure on Euclidean Space, and Test Functions: Standing Notation, in dimension , with the real line identified with as in One-Dimensional Test Functions: Scalars, Derivatives, and the Difference Quotient of the Derivative, whose reading of differentiability, of and of continuity, and whose identification of with , are in force. Let be Lebesgue measure on , which is the Lebesgue measure of the real line by Lebesgue Measure on . Let be the standard normal distribution, with the function and the positive real number as there, and define by . Class on and the partial derivative are those of Differential Calculus and Convexity on Euclidean Open Sets: Standing Notation §derivatives, being open by claim 1 of Euclidean Space is Open in Itself, and Maps are Continuous. Let be the second moment of , let be the identity map of , and, having finite second moment by claim 2, let finite Fisher information, the set , the score and the Fisher information be as defined there.
1. (Density)¶ The function is of class on , hence continuous and Borel, it is differentiable at every point of , and for every
and is the measure with density with respect to , that is, for every .
2. (Second moment)¶ ; in particular .
3. (Score)¶ , the score of is , and .
Loading…
Prerequisites
No prerequisites tracked.
Dependents
No dependents yet.
Dependent proofs
No dependent proofs yet.
No relations recorded yet.