Latent class regression: Inference and estimation with two-stage multiple imputation

Ofer Harel, Hwan Chung, Diana L Miglioretti

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Latent class regression (LCR) is a popular method for analyzing multiple categorical outcomes. While nonresponse to the manifest items is a common complication, inferences of LCR can be evaluated using maximum likelihood, multiple imputation, and two-stage multiple imputation. Under similar missing data assumptions, the estimates and variances from all three procedures are quite close. However, multiple imputation and two-stage multiple imputation can provide additional information: estimates for the rates of missing information. The methodology is illustrated using an example from a study on racial and ethnic disparities in breast cancer severity.

Original languageEnglish (US)
Pages (from-to)541-553
Number of pages13
JournalBiometrical Journal
Volume55
Issue number4
DOIs
StatePublished - Jul 2013

Fingerprint

Latent Class
Multiple Imputation
Regression
Breast Neoplasms
Non-response
Complications
Missing Data
Breast Cancer
Categorical
Estimate
Maximum Likelihood
Multiple imputation
Latent class
Inference
Methodology

Keywords

  • Latent class regression
  • Missing data
  • Missing information
  • Multiple imputation

ASJC Scopus subject areas

  • Statistics and Probability
  • Medicine(all)
  • Statistics, Probability and Uncertainty

Cite this

Latent class regression : Inference and estimation with two-stage multiple imputation. / Harel, Ofer; Chung, Hwan; Miglioretti, Diana L.

In: Biometrical Journal, Vol. 55, No. 4, 07.2013, p. 541-553.

Research output: Contribution to journalArticle

@article{fdd4129e45ef4b558ad87cbfd5399de1,
title = "Latent class regression: Inference and estimation with two-stage multiple imputation",
abstract = "Latent class regression (LCR) is a popular method for analyzing multiple categorical outcomes. While nonresponse to the manifest items is a common complication, inferences of LCR can be evaluated using maximum likelihood, multiple imputation, and two-stage multiple imputation. Under similar missing data assumptions, the estimates and variances from all three procedures are quite close. However, multiple imputation and two-stage multiple imputation can provide additional information: estimates for the rates of missing information. The methodology is illustrated using an example from a study on racial and ethnic disparities in breast cancer severity.",
keywords = "Latent class regression, Missing data, Missing information, Multiple imputation",
author = "Ofer Harel and Hwan Chung and Miglioretti, {Diana L}",
year = "2013",
month = "7",
doi = "10.1002/bimj.201200020",
language = "English (US)",
volume = "55",
pages = "541--553",
journal = "Biometrical Journal",
issn = "0323-3847",
publisher = "Wiley-VCH Verlag",
number = "4",

}

TY - JOUR

T1 - Latent class regression

T2 - Inference and estimation with two-stage multiple imputation

AU - Harel, Ofer

AU - Chung, Hwan

AU - Miglioretti, Diana L

PY - 2013/7

Y1 - 2013/7

N2 - Latent class regression (LCR) is a popular method for analyzing multiple categorical outcomes. While nonresponse to the manifest items is a common complication, inferences of LCR can be evaluated using maximum likelihood, multiple imputation, and two-stage multiple imputation. Under similar missing data assumptions, the estimates and variances from all three procedures are quite close. However, multiple imputation and two-stage multiple imputation can provide additional information: estimates for the rates of missing information. The methodology is illustrated using an example from a study on racial and ethnic disparities in breast cancer severity.

AB - Latent class regression (LCR) is a popular method for analyzing multiple categorical outcomes. While nonresponse to the manifest items is a common complication, inferences of LCR can be evaluated using maximum likelihood, multiple imputation, and two-stage multiple imputation. Under similar missing data assumptions, the estimates and variances from all three procedures are quite close. However, multiple imputation and two-stage multiple imputation can provide additional information: estimates for the rates of missing information. The methodology is illustrated using an example from a study on racial and ethnic disparities in breast cancer severity.

KW - Latent class regression

KW - Missing data

KW - Missing information

KW - Multiple imputation

UR - http://www.scopus.com/inward/record.url?scp=84879997250&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84879997250&partnerID=8YFLogxK

U2 - 10.1002/bimj.201200020

DO - 10.1002/bimj.201200020

M3 - Article

C2 - 23712802

AN - SCOPUS:84879997250

VL - 55

SP - 541

EP - 553

JO - Biometrical Journal

JF - Biometrical Journal

SN - 0323-3847

IS - 4

ER -