Invariant Causal Prediction for Sequential Data

By Niklas Pfister, Peter Buhlmann, Jan Peters. 2017

150 citations recorded by the source corpus.

ABSTRACT We investigate the problem of inferring the causal predictors of a response Y from a set of d explanatory variables (X1, …, Xd). Classical ordinary least-square regression includes all predictors that reduce the variance of Y. Using only the causal predictors instead leads to models that have the advantage of remaining invariant under interventions; loosely speaking they lead to invariance across different “environments” or “heterogeneity patterns.” More precisely, the conditional distribution of Y given its causal predictors is the same for all observations, provided that there are no interventions on Y. Recent work exploits such a stability to infer causal relations from data with different but known environments. We show that even without having knowledge of the environments or heterogeneity pattern, inferring causal relations is possible for time-ordered (or any other type of sequentially ordered) data. In particular, this allows detecting instantaneous causal relations in multivariate linear time series, which is usually not the case for Granger causality. Besides novel methodology, we provide statistical confidence bounds and asymptotic detection results for inferring causal predictors, and present an application to monetary policy in macroeconomics. Supplementary materials for this article are available online.

Subfields: Economics and Econometrics, Statistics and Probability, Representation & Self-Supervised Learning, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

In Statistics and Probability

In Representation & Self-Supervised Learning

In Probabilistic & Bayesian Methods

Citations in the corpus

Differentiable Causal Discovery from Interventional Data (2020, background): “One direction is to extend DCDI to time-series data, where non-stationarities can be modeled as unknown interventions [29].”
Toward Causal Representation Learning (2021, background): “These contexts can come from interventions [187], [191], [220], nonstationary time series [101], [116], [192], or multiple views [90], [114].”
Towards Causal Representation Learning (2021, background): “These contexts can come from interventions [218, 189, 192], non-stationary time series [117, 100, 193] or multiple views [89, 115].”
Towards Out-Of-Distribution Generalization: A Survey (2021, methodology): “…naively estimating the environments from data and then applying ICP may yield less powerful results, so instead of using static data, Pﬁster et al. [106] propose to leverage the sequential data from non-stationary environment to detect instantaneous causal relations in multivariate linear time…”