Graphical regression models for polytomous variables

Carolyn J. Anderson, Ulf Böckenholt

Research output: Contribution to journalArticle

Abstract

When modeling the relationship between two nominal categorical variables, it is often desirable to include covariates to understand how individuals differ in their response behavior. Typically, however, not all the relevant covariates are available, with the result that the measured variables cannot fully account for the associations between the nominal variables. Under the assumption that the observed and unobserved variables follow a homogeneous conditional Gaussian distribution, this paper proposes RC(M) regression models to decompose the residual associations between the polytomous variables. Based on Goodman's (1979, 1985) RC(M) association model, a distinctive feature of RC(M) regression models is that they facilitate the joint estimation of effects due to manifest and omitted (continuous) variables without requiring numerical integration. The RC(M) regression models are illustrated using data from the High School and Beyond study (Tatsuoka & Lohnes, 1988).

Original languageEnglish (US)
Pages (from-to)497-509
Number of pages13
JournalPsychometrika
Volume65
Issue number4
DOIs
StatePublished - Dec 2000

Fingerprint

Normal Distribution
Graphical Models
Regression Model
Joints
regression
Categorical or nominal
Covariates
Association Model
Categorical variable
response behavior
Gaussian distribution
Continuous Variables
Conditional Distribution
Numerical integration
Decompose
Modeling
school

Keywords

  • Conditional independence
  • Graphical models
  • Latent continuous variables
  • Marginal maximum likelihood estimation
  • RC(M) association model

ASJC Scopus subject areas

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

Cite this

Graphical regression models for polytomous variables. / Anderson, Carolyn J.; Böckenholt, Ulf.

In: Psychometrika, Vol. 65, No. 4, 12.2000, p. 497-509.

Research output: Contribution to journalArticle

Anderson, Carolyn J. ; Böckenholt, Ulf. / Graphical regression models for polytomous variables. In: Psychometrika. 2000 ; Vol. 65, No. 4. pp. 497-509.
@article{1a3b019ff2e94ec99a8d601a995aa9b5,
title = "Graphical regression models for polytomous variables",
abstract = "When modeling the relationship between two nominal categorical variables, it is often desirable to include covariates to understand how individuals differ in their response behavior. Typically, however, not all the relevant covariates are available, with the result that the measured variables cannot fully account for the associations between the nominal variables. Under the assumption that the observed and unobserved variables follow a homogeneous conditional Gaussian distribution, this paper proposes RC(M) regression models to decompose the residual associations between the polytomous variables. Based on Goodman's (1979, 1985) RC(M) association model, a distinctive feature of RC(M) regression models is that they facilitate the joint estimation of effects due to manifest and omitted (continuous) variables without requiring numerical integration. The RC(M) regression models are illustrated using data from the High School and Beyond study (Tatsuoka & Lohnes, 1988).",
keywords = "Conditional independence, Graphical models, Latent continuous variables, Marginal maximum likelihood estimation, RC(M) association model",
author = "Anderson, {Carolyn J.} and Ulf B{\"o}ckenholt",
year = "2000",
month = "12",
doi = "10.1007/BF02296340",
language = "English (US)",
volume = "65",
pages = "497--509",
journal = "Psychometrika",
issn = "0033-3123",
publisher = "Springer New York",
number = "4",

}

TY - JOUR

T1 - Graphical regression models for polytomous variables

AU - Anderson, Carolyn J.

AU - Böckenholt, Ulf

PY - 2000/12

Y1 - 2000/12

N2 - When modeling the relationship between two nominal categorical variables, it is often desirable to include covariates to understand how individuals differ in their response behavior. Typically, however, not all the relevant covariates are available, with the result that the measured variables cannot fully account for the associations between the nominal variables. Under the assumption that the observed and unobserved variables follow a homogeneous conditional Gaussian distribution, this paper proposes RC(M) regression models to decompose the residual associations between the polytomous variables. Based on Goodman's (1979, 1985) RC(M) association model, a distinctive feature of RC(M) regression models is that they facilitate the joint estimation of effects due to manifest and omitted (continuous) variables without requiring numerical integration. The RC(M) regression models are illustrated using data from the High School and Beyond study (Tatsuoka & Lohnes, 1988).

AB - When modeling the relationship between two nominal categorical variables, it is often desirable to include covariates to understand how individuals differ in their response behavior. Typically, however, not all the relevant covariates are available, with the result that the measured variables cannot fully account for the associations between the nominal variables. Under the assumption that the observed and unobserved variables follow a homogeneous conditional Gaussian distribution, this paper proposes RC(M) regression models to decompose the residual associations between the polytomous variables. Based on Goodman's (1979, 1985) RC(M) association model, a distinctive feature of RC(M) regression models is that they facilitate the joint estimation of effects due to manifest and omitted (continuous) variables without requiring numerical integration. The RC(M) regression models are illustrated using data from the High School and Beyond study (Tatsuoka & Lohnes, 1988).

KW - Conditional independence

KW - Graphical models

KW - Latent continuous variables

KW - Marginal maximum likelihood estimation

KW - RC(M) association model

UR - http://www.scopus.com/inward/record.url?scp=0040805989&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0040805989&partnerID=8YFLogxK

U2 - 10.1007/BF02296340

DO - 10.1007/BF02296340

M3 - Article

AN - SCOPUS:0040805989

VL - 65

SP - 497

EP - 509

JO - Psychometrika

JF - Psychometrika

SN - 0033-3123

IS - 4

ER -