DeepAI AI Chat
Log In Sign Up

Direct and Indirect Effects – An Information Theoretic Perspective

by   Gabriel Schamberg, et al.
University of California, San Diego

Information theoretic (IT) approaches to quantifying causal influences have experienced some popularity in the literature, in both theoretical and applied (e.g. neuroscience and climate science) domains. While these causal measures are desirable in that they are model agnostic and can capture non-linear interactions, they are fundamentally different from common statistical notions of causal influence in that they (1) compare distributions over the effect rather than values of the effect and (2) are defined with respect to random variables representing a cause rather than specific values of a cause. We here present IT measures of direct, indirect, and total causal effects. The proposed measures are unlike existing IT techniques in that they enable measuring causal effects that are defined with respect to specific values of a cause, and they are unlike existing statistical measures in that they do not involve comparison with a reference (or baseline) value. In addition to endowing IT approaches with an enhanced "resolution", the proposed framework uniquely elucidates the relationship between the IT and statistical perspectives on causality. We provide an identifiability result and demonstrate application of the proposed measures in estimating the causal effect of the El Niño-Southern Oscillation on temperature anomalies in the North American Pacific Northwest.


page 1

page 2

page 3

page 4


Causal mediation analysis with mediator values below an assay limit

Causal indirect and direct effects provide an interpretable method for d...

Conditional distribution variability measures for causality detection

In this paper we derive variability measures for the conditional probabi...

Can Transfer Entropy Infer Causality in Neuronal Circuits for Cognitive Processing?

Finding the causes to observed effects and establishing causal relations...

On Shapley Credit Allocation for Interpretability

We emphasize the importance of asking the right question when interpreti...

Decomposition of Global Feature Importance into Direct and Associative Components (DEDACT)

Global model-agnostic feature importance measures either quantify whethe...

A New Measure of Conditional Dependence

Measuring conditional dependencies among the variables of a network is o...

Temporal Reasoning with Probabilities

In this paper we explore representations of temporal knowledge based upo...