Sufficient Statistics and Split Idempotents in Discrete Probability Theory

by   Bart Jacobs, et al.
Radboud Universiteit

A sufficient statistic is a deterministic function that captures an essential property of a probabilistic function (channel, kernel). Being a sufficient statistic can be expressed nicely in terms of string diagrams, as Tobias Fritz showed recently, in adjoint form. This reformulation highlights the role of split idempotents, in the Fisher-Neyman factorisation theorem. Examples of a sufficient statistic occur in the literature, but mostly in continuous probability. This paper demonstrates that there are also several fundamental examples of a sufficient statistic in discrete probability. They emerge after some combinatorial groundwork that reveals the relevant dagger split idempotents and shows that a sufficient statistic is a deterministic dagger epi.


page 1

page 2

page 3

page 4


On Model Selection with Summary Statistics

Recently, many authors have cast doubts on the validity of ABC model cho...

The Computational Wiretap Channel

We present the computational wiretap channel: Alice has some data x and ...

On statistics which are almost sufficient from the viewpoint of the Fisher metrics

We introduce a quantitatively weak version of sufficient statistics such...

Moderate deviation theorem for the Neyman-Pearson statistic in testing uniformity

We show that for local alternatives to uniformity which are determined b...

Some notes on ergodic theorem for U-statistics of order m for stationary and not necessarily ergodic sequences

In this note, we give sufficient conditions for the almost sure and the ...

Minimal Achievable Sufficient Statistic Learning

We introduce Minimal Achievable Sufficient Statistic (MASS) Learning, a ...

Please sign up or login with your details

Forgot password? Click here to reset