Latent Class Analysis With Distal Outcomes

A Flexible Model-Based Approach

Stephanie Trea Lanza, Xianming Tan, Bethany Cara Bray

Research output: Contribution to journalArticle

207 Citations (Scopus)

Abstract

Although prediction of class membership from observed variables in latent class analysis is well understood, predicting an observed distal outcome from latent class membership is more complicated. A flexible model-based approach is proposed to empirically derive and summarize the class-dependent density functions of distal outcomes with categorical, continuous, or count distributions. A Monte Carlo simulation study is conducted to compare the performance of the new technique to 2 commonly used classify-analyze techniques: maximum-probability assignment and multiple pseudoclass draws. Simulation results show that the model-based approach produces substantially less biased estimates of the effect compared to either classify-analyze technique, particularly when the association between the latent class variable and the distal outcome is strong. In addition, we show that only the model-based approach is consistent. The approach is demonstrated empirically: latent classes of adolescent depression are used to predict smoking, grades, and delinquency. SAS syntax for implementing this approach using PROC LCA and a corresponding macro are provided.

Original languageEnglish (US)
Pages (from-to)1-26
Number of pages26
JournalStructural Equation Modeling
Volume20
Issue number1
DOIs
StatePublished - Jan 1 2013

Fingerprint

Latent Class Analysis
Latent Class
class membership
Model-based
Classify
simulation
Smoking
delinquency
Density Function
Categorical
syntax
Probability density function
Biased
Macros
smoking
Count
Assignment
Monte Carlo Simulation
Simulation Study
adolescent

All Science Journal Classification (ASJC) codes

  • Decision Sciences(all)
  • Modeling and Simulation
  • Sociology and Political Science
  • Economics, Econometrics and Finance(all)

Cite this

@article{870013979c24474ca62404c7df856981,
title = "Latent Class Analysis With Distal Outcomes: A Flexible Model-Based Approach",
abstract = "Although prediction of class membership from observed variables in latent class analysis is well understood, predicting an observed distal outcome from latent class membership is more complicated. A flexible model-based approach is proposed to empirically derive and summarize the class-dependent density functions of distal outcomes with categorical, continuous, or count distributions. A Monte Carlo simulation study is conducted to compare the performance of the new technique to 2 commonly used classify-analyze techniques: maximum-probability assignment and multiple pseudoclass draws. Simulation results show that the model-based approach produces substantially less biased estimates of the effect compared to either classify-analyze technique, particularly when the association between the latent class variable and the distal outcome is strong. In addition, we show that only the model-based approach is consistent. The approach is demonstrated empirically: latent classes of adolescent depression are used to predict smoking, grades, and delinquency. SAS syntax for implementing this approach using PROC LCA and a corresponding macro are provided.",
author = "Lanza, {Stephanie Trea} and Xianming Tan and Bray, {Bethany Cara}",
year = "2013",
month = "1",
day = "1",
doi = "10.1080/10705511.2013.742377",
language = "English (US)",
volume = "20",
pages = "1--26",
journal = "Structural Equation Modeling",
issn = "1070-5511",
publisher = "Psychology Press Ltd",
number = "1",

}

Latent Class Analysis With Distal Outcomes : A Flexible Model-Based Approach. / Lanza, Stephanie Trea; Tan, Xianming; Bray, Bethany Cara.

In: Structural Equation Modeling, Vol. 20, No. 1, 01.01.2013, p. 1-26.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Latent Class Analysis With Distal Outcomes

T2 - A Flexible Model-Based Approach

AU - Lanza, Stephanie Trea

AU - Tan, Xianming

AU - Bray, Bethany Cara

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Although prediction of class membership from observed variables in latent class analysis is well understood, predicting an observed distal outcome from latent class membership is more complicated. A flexible model-based approach is proposed to empirically derive and summarize the class-dependent density functions of distal outcomes with categorical, continuous, or count distributions. A Monte Carlo simulation study is conducted to compare the performance of the new technique to 2 commonly used classify-analyze techniques: maximum-probability assignment and multiple pseudoclass draws. Simulation results show that the model-based approach produces substantially less biased estimates of the effect compared to either classify-analyze technique, particularly when the association between the latent class variable and the distal outcome is strong. In addition, we show that only the model-based approach is consistent. The approach is demonstrated empirically: latent classes of adolescent depression are used to predict smoking, grades, and delinquency. SAS syntax for implementing this approach using PROC LCA and a corresponding macro are provided.

AB - Although prediction of class membership from observed variables in latent class analysis is well understood, predicting an observed distal outcome from latent class membership is more complicated. A flexible model-based approach is proposed to empirically derive and summarize the class-dependent density functions of distal outcomes with categorical, continuous, or count distributions. A Monte Carlo simulation study is conducted to compare the performance of the new technique to 2 commonly used classify-analyze techniques: maximum-probability assignment and multiple pseudoclass draws. Simulation results show that the model-based approach produces substantially less biased estimates of the effect compared to either classify-analyze technique, particularly when the association between the latent class variable and the distal outcome is strong. In addition, we show that only the model-based approach is consistent. The approach is demonstrated empirically: latent classes of adolescent depression are used to predict smoking, grades, and delinquency. SAS syntax for implementing this approach using PROC LCA and a corresponding macro are provided.

UR - http://www.scopus.com/inward/record.url?scp=84873351058&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84873351058&partnerID=8YFLogxK

U2 - 10.1080/10705511.2013.742377

DO - 10.1080/10705511.2013.742377

M3 - Article

VL - 20

SP - 1

EP - 26

JO - Structural Equation Modeling

JF - Structural Equation Modeling

SN - 1070-5511

IS - 1

ER -