Let Φ be the standard normal distribution function, and let P be the set of all symmetric probability measures arising from Φ through εcontamination: P = {F : F = (1 − ε)ϕ + εH, H ∈ M}, where M is the...

Let Φ be the standard normal distribution function, and let P be the set of all symmetric probability measures arising from Φ through εcontamination: P = {F : F = (1 − ε)ϕ + εH, H ∈ M}, where M is the set of all symmetric probability measures on R1. Then the Fisher information I(f) is minimized by the probability density