Donsker classes

A class of functions is considered a Donsker class if it satisfies Donsker's theorem, a functional generalization of the central limit theorem.

Definition

Let ℱ be a collection of square integrable functions on a probability space (𝒳,𝒜,P). The empirical process 𝔾n is the stochastic process on the set ℱ defined by 𝔾n(f)=n(ℙn−P)(f) where ℙn is the empirical measure based on an iid sample X1,…,Xn from P.

The class of measurable functions ℱ is called a Donsker class if the empirical process (𝔾n)n=1∞ converges in distribution to a tight Borel measurable element in the space ℓ∞(ℱ).

By the central limit theorem, for every finite set of functions f1,f2,…,fk∈ℱ, the random vector (𝔾n(f1),𝔾n(f2),…,𝔾n(fk)) converges in distribution to a multivariate normal vector as n→∞. Thus the class ℱ is Donsker if and only if the sequence (𝔾n)n=1∞ is asymptotically tight in ℓ∞(ℱ)

Examples and Sufficient Conditions

Classes of functions which have finite Dudley's entropy integral are Donsker classes. This includes empirical distribution functions formed from the class of functions defined by 𝕀(−∞,t] as well as parametric classes over bounded parameter spaces. More generally any VC class is also Donsker class.

Properties

Classes of functions formed by taking infima or suprema of functions in a Donsker class also form a Donsker class.

Donsker's Theorem

Donsker's theorem states that the empirical distribution function, when properly normalized, converges weakly to a Brownian bridge—a continuous Gaussian process. This is significant as it assures that results analogous to the central limit theorem hold for empirical processes, thereby enabling asymptotic inference for a wide range of statistical applications.

The concept of the Donsker class is influential in the field of asymptotic statistics. Knowing whether a function class is a Donsker class helps in understanding the limiting distribution of empirical processes, which in turn facilitates the construction of confidence bands for function estimators and hypothesis testing.

See also