Ancestor regression in linear structural equation models

被引:1
作者
Schultheiss, C. [1 ]
Buhlmann, P. [1 ]
机构
[1] Swiss Fed Inst Technol, Seminar Stat, Ramistr 101, CH-8092 Zurich, Switzerland
基金
欧洲研究理事会;
关键词
Causal inference; LiNGAM; Structural equation model;
D O I
10.1093/biomet/asad008
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
We present a new method for causal discovery in linear structural equation models. We propose a simple technique based on statistical testing in linear models that can distinguish between ancestors and non-ancestors of any given variable. Naturally, this approach can then be extended to estimating the causal order among all variables. Unlike with many methods, it is possible to provide explicit error control for false causal discovery, at least asymptotically. This holds even under Gaussianity where various methods fail because of nonidentifiable structures. These Type I error guarantees come at the cost of reduced power. Additionally, we provide an asymptotically valid goodness-of-fit p-value for assessing whether multivariate data stem from a linear structural equation model.
引用
收藏
页码:1117 / 1124
页数:8
相关论文
共 12 条
[1]   AUTONOMY [J].
ALDRICH, J .
OXFORD ECONOMIC PAPERS-NEW SERIES, 1989, 41 (01) :15-34
[2]  
[Anonymous], 2023, R: A Language and Environment for Statistical Computing
[3]  
Chickering D. M., 2003, Journal of Machine Learning Research, V3, P507, DOI 10.1162/153244303321897717
[4]   CAUSAL DISCOVERY IN HEAVY-TAILED MODELS [J].
Gnecco, Nicola ;
Meinshausen, Nicolai ;
Peters, Jonas ;
Engelke, Sebastian .
ANNALS OF STATISTICS, 2021, 49 (03) :1755-1778
[5]   Fast and robust fixed-point algorithms for independent component analysis [J].
Hyvärinen, A .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (03) :626-634
[6]  
Kalisch M, 2012, J STAT SOFTW, V47, P1
[7]  
Mooij J. M., 2013, P 20 9 C UNCERTAINTY, P431
[8]   Identifiability of Gaussian structural equation models with equal error variances [J].
Peters, J. ;
Buehlmann, P. .
BIOMETRIKA, 2014, 101 (01) :219-228
[9]   Causal protein-signaling networks derived from multiparameter single-cell data [J].
Sachs, K ;
Perez, O ;
Pe'er, D ;
Lauffenburger, DA ;
Nolan, GP .
SCIENCE, 2005, 308 (5721) :523-529
[10]  
Shimizu S, 2006, J MACH LEARN RES, V7, P2003