Doubly robust-type estimation for covariate adjustment in Latent variable modeling

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Due to the difficulty in achieving a random assignment, a quasi-experimental or observational study design is frequently used in the behavioral and social sciences. If a nonrandom assignment depends on the covariates, multiple group structural equation modeling, that includes the regression function of the dependent variables on the covariates that determine the assignment, can provide reasonable estimates under the condition of correct specification of the regression function. However, it is usually difficult to specify the correct regression function because the dimensions of the dependent variables and covariates are typically large. Therefore, the propensity score adjustment methods have been proposed, since they do not require the specification of the regression function and have been applied to several applied studies. However, these methods produce biased estimates if the assignment mechanism is incorrectly specified. In order to make a more robust inference, it would be more useful to develop an estimation method that integrates the regression approach with the propensity score methodology. In this study we propose a doubly robust-type estimation method for marginal multiple group structural equation modeling. This method provides a consistent estimator if either the regression function or the assignment mechanism is correctly specified. A simulation study indicates that the proposed estimation method is more robust than the existing methods.

Original languageEnglish
Pages (from-to)535-549
Number of pages15
JournalPsychometrika
Volume72
Issue number4
DOIs
Publication statusPublished - 2007 Dec
Externally publishedYes

Fingerprint

Social Adjustment
Latent Variables
Covariates
Adjustment
Regression Function
Assignment
regression
Modeling
Propensity Score
Structural Equation Modeling
Specifications
Social sciences
Specification
Robust Inference
Behavioral Sciences
Observational Study
behavioral science
Social Sciences
Dependent
Consistent Estimator

Keywords

  • Causal inference
  • Marginal model
  • Monte Carlo method
  • Propensity score
  • Structural equation modeling

ASJC Scopus subject areas

  • Mathematics (miscellaneous)
  • Psychology(all)
  • Psychology (miscellaneous)
  • Social Sciences (miscellaneous)

Cite this

Doubly robust-type estimation for covariate adjustment in Latent variable modeling. / Hoshino, Takahiro.

In: Psychometrika, Vol. 72, No. 4, 12.2007, p. 535-549.

Research output: Contribution to journalArticle

@article{a2b0ee2a1a894529b35440eb962798c6,
title = "Doubly robust-type estimation for covariate adjustment in Latent variable modeling",
abstract = "Due to the difficulty in achieving a random assignment, a quasi-experimental or observational study design is frequently used in the behavioral and social sciences. If a nonrandom assignment depends on the covariates, multiple group structural equation modeling, that includes the regression function of the dependent variables on the covariates that determine the assignment, can provide reasonable estimates under the condition of correct specification of the regression function. However, it is usually difficult to specify the correct regression function because the dimensions of the dependent variables and covariates are typically large. Therefore, the propensity score adjustment methods have been proposed, since they do not require the specification of the regression function and have been applied to several applied studies. However, these methods produce biased estimates if the assignment mechanism is incorrectly specified. In order to make a more robust inference, it would be more useful to develop an estimation method that integrates the regression approach with the propensity score methodology. In this study we propose a doubly robust-type estimation method for marginal multiple group structural equation modeling. This method provides a consistent estimator if either the regression function or the assignment mechanism is correctly specified. A simulation study indicates that the proposed estimation method is more robust than the existing methods.",
keywords = "Causal inference, Marginal model, Monte Carlo method, Propensity score, Structural equation modeling",
author = "Takahiro Hoshino",
year = "2007",
month = "12",
doi = "10.1007/s11336-007-9007-2",
language = "English",
volume = "72",
pages = "535--549",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "4",

}

TY - JOUR

T1 - Doubly robust-type estimation for covariate adjustment in Latent variable modeling

AU - Hoshino, Takahiro

PY - 2007/12

Y1 - 2007/12

N2 - Due to the difficulty in achieving a random assignment, a quasi-experimental or observational study design is frequently used in the behavioral and social sciences. If a nonrandom assignment depends on the covariates, multiple group structural equation modeling, that includes the regression function of the dependent variables on the covariates that determine the assignment, can provide reasonable estimates under the condition of correct specification of the regression function. However, it is usually difficult to specify the correct regression function because the dimensions of the dependent variables and covariates are typically large. Therefore, the propensity score adjustment methods have been proposed, since they do not require the specification of the regression function and have been applied to several applied studies. However, these methods produce biased estimates if the assignment mechanism is incorrectly specified. In order to make a more robust inference, it would be more useful to develop an estimation method that integrates the regression approach with the propensity score methodology. In this study we propose a doubly robust-type estimation method for marginal multiple group structural equation modeling. This method provides a consistent estimator if either the regression function or the assignment mechanism is correctly specified. A simulation study indicates that the proposed estimation method is more robust than the existing methods.

AB - Due to the difficulty in achieving a random assignment, a quasi-experimental or observational study design is frequently used in the behavioral and social sciences. If a nonrandom assignment depends on the covariates, multiple group structural equation modeling, that includes the regression function of the dependent variables on the covariates that determine the assignment, can provide reasonable estimates under the condition of correct specification of the regression function. However, it is usually difficult to specify the correct regression function because the dimensions of the dependent variables and covariates are typically large. Therefore, the propensity score adjustment methods have been proposed, since they do not require the specification of the regression function and have been applied to several applied studies. However, these methods produce biased estimates if the assignment mechanism is incorrectly specified. In order to make a more robust inference, it would be more useful to develop an estimation method that integrates the regression approach with the propensity score methodology. In this study we propose a doubly robust-type estimation method for marginal multiple group structural equation modeling. This method provides a consistent estimator if either the regression function or the assignment mechanism is correctly specified. A simulation study indicates that the proposed estimation method is more robust than the existing methods.

KW - Causal inference

KW - Marginal model

KW - Monte Carlo method

KW - Propensity score

KW - Structural equation modeling

UR - http://www.scopus.com/inward/record.url?scp=38949165075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=38949165075&partnerID=8YFLogxK

U2 - 10.1007/s11336-007-9007-2

DO - 10.1007/s11336-007-9007-2

M3 - Article

VL - 72

SP - 535

EP - 549

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -