Estimating interaction effects with incomplete predictor variables

Craig K. Enders, Amanda N. Baraldi, Heining Cham

Research output: Contribution to journalArticle

28 Citations (Scopus)

Abstract

The existing missing data literature does not provide a clear prescription for estimating interaction effects with missing data, particularly when the interaction involves a pair of continuous variables. In this article, we describe maximum likelihood and multiple imputation procedures for this common analysis problem. We outline 3 latent variable model specifications for interaction analyses with missing data. These models apply procedures from the latent variable interaction literature to analyses with a single indicator per construct (e.g., a regression analysis with scale scores). We also discuss multiple imputation for interaction effects, emphasizing an approach that applies standard imputation procedures to the product of 2 raw score predictors. We thoroughly describe the process of probing interaction effects with maximum likelihood and multiple imputation. For both missing data handling techniques, we outline centering and transformation strategies that researchers can implement in popular software packages, and we use a series of real data analyses to illustrate these methods. Finally, we use computer simulations to evaluate the performance of the proposed techniques.

Original languageEnglish (US)
Pages (from-to)39-55
Number of pages17
JournalPsychological Methods
Volume19
Issue number1
DOIs
StatePublished - 2014

Fingerprint

Computer Simulation
Prescriptions
Software
Regression Analysis
Research Personnel
Interaction
Predictors
Incomplete
Maximum Likelihood
Prescription

Keywords

  • Centering
  • Interaction effects
  • Maximum likelihood estimation
  • Missing data
  • Multiple imputation

ASJC Scopus subject areas

  • Psychology (miscellaneous)
  • History and Philosophy of Science

Cite this

Estimating interaction effects with incomplete predictor variables. / Enders, Craig K.; Baraldi, Amanda N.; Cham, Heining.

In: Psychological Methods, Vol. 19, No. 1, 2014, p. 39-55.

Research output: Contribution to journalArticle

Enders, Craig K. ; Baraldi, Amanda N. ; Cham, Heining. / Estimating interaction effects with incomplete predictor variables. In: Psychological Methods. 2014 ; Vol. 19, No. 1. pp. 39-55.
@article{2b9f65e93ac74c069878dc9c7a588250,
title = "Estimating interaction effects with incomplete predictor variables",
abstract = "The existing missing data literature does not provide a clear prescription for estimating interaction effects with missing data, particularly when the interaction involves a pair of continuous variables. In this article, we describe maximum likelihood and multiple imputation procedures for this common analysis problem. We outline 3 latent variable model specifications for interaction analyses with missing data. These models apply procedures from the latent variable interaction literature to analyses with a single indicator per construct (e.g., a regression analysis with scale scores). We also discuss multiple imputation for interaction effects, emphasizing an approach that applies standard imputation procedures to the product of 2 raw score predictors. We thoroughly describe the process of probing interaction effects with maximum likelihood and multiple imputation. For both missing data handling techniques, we outline centering and transformation strategies that researchers can implement in popular software packages, and we use a series of real data analyses to illustrate these methods. Finally, we use computer simulations to evaluate the performance of the proposed techniques.",
keywords = "Centering, Interaction effects, Maximum likelihood estimation, Missing data, Multiple imputation",
author = "Enders, {Craig K.} and Baraldi, {Amanda N.} and Heining Cham",
year = "2014",
doi = "10.1037/a0035314",
language = "English (US)",
volume = "19",
pages = "39--55",
journal = "Psychological Methods",
issn = "1082-989X",
publisher = "American Psychological Association Inc.",
number = "1",

}

TY - JOUR

T1 - Estimating interaction effects with incomplete predictor variables

AU - Enders, Craig K.

AU - Baraldi, Amanda N.

AU - Cham, Heining

PY - 2014

Y1 - 2014

N2 - The existing missing data literature does not provide a clear prescription for estimating interaction effects with missing data, particularly when the interaction involves a pair of continuous variables. In this article, we describe maximum likelihood and multiple imputation procedures for this common analysis problem. We outline 3 latent variable model specifications for interaction analyses with missing data. These models apply procedures from the latent variable interaction literature to analyses with a single indicator per construct (e.g., a regression analysis with scale scores). We also discuss multiple imputation for interaction effects, emphasizing an approach that applies standard imputation procedures to the product of 2 raw score predictors. We thoroughly describe the process of probing interaction effects with maximum likelihood and multiple imputation. For both missing data handling techniques, we outline centering and transformation strategies that researchers can implement in popular software packages, and we use a series of real data analyses to illustrate these methods. Finally, we use computer simulations to evaluate the performance of the proposed techniques.

AB - The existing missing data literature does not provide a clear prescription for estimating interaction effects with missing data, particularly when the interaction involves a pair of continuous variables. In this article, we describe maximum likelihood and multiple imputation procedures for this common analysis problem. We outline 3 latent variable model specifications for interaction analyses with missing data. These models apply procedures from the latent variable interaction literature to analyses with a single indicator per construct (e.g., a regression analysis with scale scores). We also discuss multiple imputation for interaction effects, emphasizing an approach that applies standard imputation procedures to the product of 2 raw score predictors. We thoroughly describe the process of probing interaction effects with maximum likelihood and multiple imputation. For both missing data handling techniques, we outline centering and transformation strategies that researchers can implement in popular software packages, and we use a series of real data analyses to illustrate these methods. Finally, we use computer simulations to evaluate the performance of the proposed techniques.

KW - Centering

KW - Interaction effects

KW - Maximum likelihood estimation

KW - Missing data

KW - Multiple imputation

UR - http://www.scopus.com/inward/record.url?scp=84897939402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897939402&partnerID=8YFLogxK

U2 - 10.1037/a0035314

DO - 10.1037/a0035314

M3 - Article

C2 - 24707955

AN - SCOPUS:84897939402

VL - 19

SP - 39

EP - 55

JO - Psychological Methods

JF - Psychological Methods

SN - 1082-989X

IS - 1

ER -