The Locally Gaussian Partial Correlation

by   Håkon Otneim, et al.

It is well known that the dependence structure for jointly Gaussian variables can be fully captured using correlations, and that the conditional dependence structure in the same way can be described using partial correlations. The partial orrelation does not, however, characterize conditional dependence in many non-Gaussian populations. This paper introduces the local Gaussian partial correlation (LGPC), a new measure of conditional dependence. It is a local version of the partial correlation coefficient that characterizes conditional dependence in a large class of populations. It has some useful and novel properties besides: The LGPC reduces to the ordinary partial correlation for jointly normal variables, and it distinguishes between positive and negative conditional dependence. Furthermore, the LGPC can be used to study departures from conditional independence in specific parts of the distribution. We provide several examples of this, both simulated and real, and derive estimation theory under a local likelihood framework. Finally, we indicate how the LGPC can be used to construct a powerful test for conditional independence, which, again, can be used to detect Granger causality in time series.


Dependence in elliptical partial correlation graphs

The Gaussian model is equipped with strong properties that facilitate st...

On relationships between Chatterjee's and Spearman's correlation coefficients

In his seminal work, Chatterjee (2021) introduced a novel correlation me...

Using the structure of d-connecting paths as a qualitative measure of the strength of dependence

Pearls concept OF a d - connecting path IS one OF the foundations OF the...

Positive dependence in qualitative probabilistic networks

Qualitative probabilistic networks (QPNs) combine the conditional indepe...

Local Expression Languages for Probabilistic Dependence: a Preliminary Report

We present a generalization of the local expression language used in the...

Conditional Finite Mixtures of Poisson Distributions for Context-Dependent Neural Correlations

Parallel recordings of neural spike counts have revealed the existence o...

A general approach to the assessment of uncertainty in volumes by using the multi-Gaussian model

The goal of this research is to derive an approach to assess uncertainty...

Please sign up or login with your details

Forgot password? Click here to reset