Scholarlink

In this work we study a causal framework for linear structural equation models that can be represented by a Gaussian regression chain graph typically used to model multivariate regressions. We propose a methodology based on invariance causal prediction for the identification of the causal parents of a given multivariate response variable and the estimation of the causal effects. Preliminary simulation studies show that, under suitable assumptions, the methodology is able to correctly identify the true causal parents.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Invariant Causal Prediction for Gaussian Multivariate Regression Graphs

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Marco Borriero,
  • Monia Lupparelli,
  • Giovanni M. Marchetti,
  • Veronica Vinciotti

摘要

In this work we study a causal framework for linear structural equation models that can be represented by a Gaussian regression chain graph typically used to model multivariate regressions. We propose a methodology based on invariance causal prediction for the identification of the causal parents of a given multivariate response variable and the estimation of the causal effects. Preliminary simulation studies show that, under suitable assumptions, the methodology is able to correctly identify the true causal parents.