An Information Theoretic Measure of Judea Pearl's Identifiability and Causal Influence

07/21/2013
by   Robert R. Tucci, et al.
0

In this paper, we define a new information theoretic measure that we call the "uprooted information". We show that a necessary and sufficient condition for a probability P(s|do(t)) to be "identifiable" (in the sense of Pearl) in a graph G is that its uprooted information be non-negative for all models of the graph G. In this paper, we also give a new algorithm for deciding, for a Bayesian net that is semi-Markovian, whether a probability P(s|do(t)) is identifiable, and, if it is identifiable, for expressing it without allusions to confounding variables. Our algorithm is closely based on a previous algorithm by Tian and Pearl, but seems to correct a small flaw in theirs. In this paper, we also find a necessary and sufficient graphical condition for a probability P(s|do(t)) to be identifiable when t is a singleton set. So far, in the prior literature, it appears that only a sufficient graphical condition has been given for this. By "graphical" we mean that it is directly based on Judea Pearl's 3 rules of do-calculus.

READ FULL TEXT

page 1

page 2

page 3

page 4

02/20/2021

Necessary and sufficient conditions for optimal adjustment sets in causal graphical models with hidden variables

The problem of selecting optimal valid backdoor adjustment sets to estim...
05/28/2020

On Functions of Markov Random Fields

We derive two sufficient conditions for a function of a Markov random fi...
10/16/2012

Causal Inference by Surrogate Experiments: z-Identifiability

We address the problem of estimating the effect of intervening on a set ...
06/01/2018

Partial correlation hypersurfaces in Gaussian graphical models

We derive a combinatorial sufficient condition for a partial correlation...
02/04/2021

Undecidability of Underfitting in Learning Algorithms

Using recent machine learning results that present an information-theore...
11/04/2015

Quantification of observed prior and likelihood information in parametric Bayesian modeling

Two data-dependent information metrics are developed to quantify the inf...