Higher-Order Least Squares: Assessing Partial Goodness of Fit of Linear Causal Models

被引：2

作者：

Schultheiss, Christoph ^{[1
]}

Buhlmann, Peter ^{[1
]}

Yuan, Ming ^{[2
]}

机构：

[1] Swiss Fed Inst Technol, Seminar Stat, Zurich, Switzerland

[2] Columbia Univ, Dept Stat, New York, NY USA

来源：

JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION | 2024年 / 119卷 / 546期

基金：

欧洲研究理事会;

关键词：

Causal inference; Latent confounding; Model misspecification; Nodewise regression; Structural equation models; INFERENCE; IDENTIFICATION; DISCOVERY; TESTS;

D O I：

10.1080/01621459.2022.2157728

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

We introduce a simple diagnostic test for assessing the overall or partial goodness of fit of a linear causal model with errors being independent of the covariates. In particular, we consider situations where hidden confounding is potentially present. We develop a method and discuss its capability to distinguish between covariates that are confounded with the response by latent variables and those that are not. Thus, we provide a test and methodology for partial goodness of fit. The test is based on comparing a novel higher-order least squares principle with ordinary least squares. In spite of its simplicity, the proposed method is extremely general and is also proven to be valid for high-dimensional settings. for this article are available online.

引用

页码：1019 / 1031

页数：13

共 50 条

[21] Goftte: A R package for assessing goodness-of-fit in proportional (sub) distributions hazards regression models
Sfumato, P.
Filleron, T.
Giorgi, R.
Cook, R. J.
Boher, J. M.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2019, 177 : 269 - 275
[22] Hybrid Partial Least Squares Models for Batch Processes: Integrating Data with Process Knowledge
Ghosh, Debanjan
Mhaskar, Prashant
MacGregor, John F.
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2021, 60 (26) : 9508 - 9520
[23] Comparing generalised maximum entropy and partial least squares methods for structural equation models
Ciavolino, Enrico
Al-Nasser, Amjad D.
JOURNAL OF NONPARAMETRIC STATISTICS, 2009, 21 (08) : 1017 - 1036
[24] Tilted Least-Squares Parameter Estimation of Linear Regression Models in the Presence of Outliers
Mu, Biqiang
Bai, Er-Wei
Zheng, Wei Xing
2023 62ND IEEE CONFERENCE ON DECISION AND CONTROL, CDC, 2023, : 2464 - 2470
[25] Identification of DSGE models-The effect of higher-order approximation and pruning
Mutschler, Willi
JOURNAL OF ECONOMIC DYNAMICS & CONTROL, 2015, 56 : 34 - 54
[26] SIMULTANEOUS EQUATIONS MODELS WITH HIGHER-ORDER SPATIAL OR SOCIAL NETWORK INTERACTIONS
Drukker, David M.
Egger, Peter H.
Prucha, Ingmar R.
ECONOMETRIC THEORY, 2023, 39 (06) : 1154 - 1201
[27] Influence of variable selection on partial least squares discriminant analysis models for explosive residue classification
De Lucia, Frank C., Jr.
Gottfried, Jennifer L.
SPECTROCHIMICA ACTA PART B-ATOMIC SPECTROSCOPY, 2011, 66 (02) : 122 - 128
[28] Exact and higher-order properties of the MLE in spatial autoregressive models, with applications to inference
Hillier, Grant
Martellosio, Federico
JOURNAL OF ECONOMETRICS, 2018, 205 (02) : 402 - 422
[29] Assessing the Overall and Partial Causal Well-Specification of Nonlinear Additive Noise Models
Schultheiss, Christoph
Buhlmann, Peter
JOURNAL OF MACHINE LEARNING RESEARCH, 2024, 25 : 1 - 41
[30] Least-squares independence regression for non-linear causal inference under non-Gaussian noise
Makoto Yamada
Masashi Sugiyama
Jun Sese
Machine Learning, 2014, 96 : 249 - 267

← 1 2 3 4 5 →