4.3. Best estimate – conditional expectation

We are seeking to improve the result by considering as estimation of XK not only the linear functions images of r.v. Y1, …, YK−1 but the general functions images

PROPOSITION.– The family of r.v. images Borel functions; images is a closed vector subspace of L2.


Let us note again images = Hilbert space equipped with a scalar product: images.

Furthermore, fY (y1, …, yK − 1) designating the density of the vector Y = (Y1, …, YK − 1), in order to simplify its expression let us state:


and let us introduce the new Hilbert space:


This is equipped with the scalar product: ∀g1, g2L2 ()

Thus finally the linear mapping:

We notice that ψ conserves the scalar product (and the ...

Get Discrete Stochastic Processes and Optimal Filtering now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.