Modeling Interactions Between Latent Variables in Research on Type D Personality

A Monte Carlo Simulation and Clinical Study of Depression and Anxiety

Paul Lodder, Johan Denollet, Wilco H M Emons, Giesje Nefs, Frans Pouwer, Jane Speight, Jelte M Wicherts

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

9 Downloads (Pure)

Resumé

Several approaches exist to model interactions between latent variables. However, it is unclear how these perform when item scores are skewed and ordinal. Research on Type D personality serves as a good case study for that matter. In Study 1, we fitted a multivariate interaction model to predict depression and anxiety with Type D personality, operationalized as an interaction between its two subcomponents negative affectivity (NA) and social inhibition (SI). We constructed this interaction according to four approaches: (1) sum score product; (2) single product indicator; (3) matched product indicators; and (4) latent moderated structural equations (LMS). In Study 2, we compared these interaction models in a simulation study by assessing for each method the bias and precision of the estimated interaction effect under varying conditions. In Study 1, all methods showed a significant Type D effect on both depression and anxiety, although this effect diminished after including the NA and SI quadratic effects. Study 2 showed that the LMS approach performed best with respect to minimizing bias and maximizing power, even when item scores were ordinal and skewed. However, when latent traits were skewed LMS resulted in more false-positive conclusions, while the Matched PI approach adequately controlled the false-positive rate.

OriginalsprogEngelsk
TidsskriftMultivariate Behavioral Research
Vol/bind54
Udgave nummer5
Sider (fra-til)637-665
ISSN0027-3171
DOI
StatusUdgivet - 13. apr. 2019

Fingeraftryk

Type D Personality
Anxiety
Latent Variables
Structural Equations
Monte Carlo Simulation
Depression
Interaction
Modeling
Research
False Positive
Latent Trait
Interaction Effects
Personality
Clinical Studies
Simulation Study
Model
Predict

Citer dette

@article{e27d3f7af96e447d9e209610a94c6ad2,
title = "Modeling Interactions Between Latent Variables in Research on Type D Personality: A Monte Carlo Simulation and Clinical Study of Depression and Anxiety",
abstract = "Several approaches exist to model interactions between latent variables. However, it is unclear how these perform when item scores are skewed and ordinal. Research on Type D personality serves as a good case study for that matter. In Study 1, we fitted a multivariate interaction model to predict depression and anxiety with Type D personality, operationalized as an interaction between its two subcomponents negative affectivity (NA) and social inhibition (SI). We constructed this interaction according to four approaches: (1) sum score product; (2) single product indicator; (3) matched product indicators; and (4) latent moderated structural equations (LMS). In Study 2, we compared these interaction models in a simulation study by assessing for each method the bias and precision of the estimated interaction effect under varying conditions. In Study 1, all methods showed a significant Type D effect on both depression and anxiety, although this effect diminished after including the NA and SI quadratic effects. Study 2 showed that the LMS approach performed best with respect to minimizing bias and maximizing power, even when item scores were ordinal and skewed. However, when latent traits were skewed LMS resulted in more false-positive conclusions, while the Matched PI approach adequately controlled the false-positive rate.",
keywords = "Latent prediction model, SEM, Type D personality, anxiety, depression, latent interaction, nonnormality, structural equation modeling",
author = "Paul Lodder and Johan Denollet and Emons, {Wilco H M} and Giesje Nefs and Frans Pouwer and Jane Speight and Wicherts, {Jelte M}",
year = "2019",
month = "4",
day = "13",
doi = "10.1080/00273171.2018.1562863",
language = "English",
volume = "54",
pages = "637--665",
journal = "Multivariate Behavioral Research",
issn = "0027-3171",
publisher = "Psychology Press",
number = "5",

}

Modeling Interactions Between Latent Variables in Research on Type D Personality : A Monte Carlo Simulation and Clinical Study of Depression and Anxiety. / Lodder, Paul; Denollet, Johan; Emons, Wilco H M; Nefs, Giesje; Pouwer, Frans; Speight, Jane; Wicherts, Jelte M.

I: Multivariate Behavioral Research, Bind 54, Nr. 5, 13.04.2019, s. 637-665.

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

TY - JOUR

T1 - Modeling Interactions Between Latent Variables in Research on Type D Personality

T2 - A Monte Carlo Simulation and Clinical Study of Depression and Anxiety

AU - Lodder, Paul

AU - Denollet, Johan

AU - Emons, Wilco H M

AU - Nefs, Giesje

AU - Pouwer, Frans

AU - Speight, Jane

AU - Wicherts, Jelte M

PY - 2019/4/13

Y1 - 2019/4/13

N2 - Several approaches exist to model interactions between latent variables. However, it is unclear how these perform when item scores are skewed and ordinal. Research on Type D personality serves as a good case study for that matter. In Study 1, we fitted a multivariate interaction model to predict depression and anxiety with Type D personality, operationalized as an interaction between its two subcomponents negative affectivity (NA) and social inhibition (SI). We constructed this interaction according to four approaches: (1) sum score product; (2) single product indicator; (3) matched product indicators; and (4) latent moderated structural equations (LMS). In Study 2, we compared these interaction models in a simulation study by assessing for each method the bias and precision of the estimated interaction effect under varying conditions. In Study 1, all methods showed a significant Type D effect on both depression and anxiety, although this effect diminished after including the NA and SI quadratic effects. Study 2 showed that the LMS approach performed best with respect to minimizing bias and maximizing power, even when item scores were ordinal and skewed. However, when latent traits were skewed LMS resulted in more false-positive conclusions, while the Matched PI approach adequately controlled the false-positive rate.

AB - Several approaches exist to model interactions between latent variables. However, it is unclear how these perform when item scores are skewed and ordinal. Research on Type D personality serves as a good case study for that matter. In Study 1, we fitted a multivariate interaction model to predict depression and anxiety with Type D personality, operationalized as an interaction between its two subcomponents negative affectivity (NA) and social inhibition (SI). We constructed this interaction according to four approaches: (1) sum score product; (2) single product indicator; (3) matched product indicators; and (4) latent moderated structural equations (LMS). In Study 2, we compared these interaction models in a simulation study by assessing for each method the bias and precision of the estimated interaction effect under varying conditions. In Study 1, all methods showed a significant Type D effect on both depression and anxiety, although this effect diminished after including the NA and SI quadratic effects. Study 2 showed that the LMS approach performed best with respect to minimizing bias and maximizing power, even when item scores were ordinal and skewed. However, when latent traits were skewed LMS resulted in more false-positive conclusions, while the Matched PI approach adequately controlled the false-positive rate.

KW - Latent prediction model

KW - SEM

KW - Type D personality

KW - anxiety

KW - depression

KW - latent interaction

KW - nonnormality

KW - structural equation modeling

U2 - 10.1080/00273171.2018.1562863

DO - 10.1080/00273171.2018.1562863

M3 - Journal article

VL - 54

SP - 637

EP - 665

JO - Multivariate Behavioral Research

JF - Multivariate Behavioral Research

SN - 0027-3171

IS - 5

ER -