Analysis of ordinal outcomes with longitudinal covariates subject to missingness

Melody Goodman, Yi Li, Anne M. Stoddard, Glorian Sorensen

Research output: Contribution to journalArticle

Abstract

We propose a mixture model for data with an ordinal outcome and a longitudinal covariate that is subject to missingness. Data from a tailored telephone delivered, smoking cessation intervention for construction laborers are used to illustrate the method, which considers as an outcome a categorical measure of smoking cessation, and evaluates the effectiveness of the motivational telephone interviews on this outcome. We propose two model structures for the longitudinal covariate, for the case when the missing data are missing at random, and when the missing data mechanism is non-ignorable. A generalized EM algorithm is used to obtain maximum likelihood estimates.

Original languageEnglish (US)
Pages (from-to)1040-1052
Number of pages13
JournalJournal of Applied Statistics
Volume41
Issue number5
DOIs
StatePublished - May 2014

Fingerprint

Covariates
Smoking
Missing Data Mechanism
Missing at Random
EM Algorithm
Maximum Likelihood Estimate
Missing Data
Mixture Model
Categorical
Evaluate
Smoking cessation
Missing data
Telephone
Model
EM algorithm
Mixture model
Maximum likelihood

Keywords

  • longitudinal covariates
  • missingness
  • ordinal outcomes

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Analysis of ordinal outcomes with longitudinal covariates subject to missingness. / Goodman, Melody; Li, Yi; Stoddard, Anne M.; Sorensen, Glorian.

In: Journal of Applied Statistics, Vol. 41, No. 5, 05.2014, p. 1040-1052.

Research output: Contribution to journalArticle

Goodman, Melody ; Li, Yi ; Stoddard, Anne M. ; Sorensen, Glorian. / Analysis of ordinal outcomes with longitudinal covariates subject to missingness. In: Journal of Applied Statistics. 2014 ; Vol. 41, No. 5. pp. 1040-1052.
@article{1f84394b034c4de5b399063da9469ce6,
title = "Analysis of ordinal outcomes with longitudinal covariates subject to missingness",
abstract = "We propose a mixture model for data with an ordinal outcome and a longitudinal covariate that is subject to missingness. Data from a tailored telephone delivered, smoking cessation intervention for construction laborers are used to illustrate the method, which considers as an outcome a categorical measure of smoking cessation, and evaluates the effectiveness of the motivational telephone interviews on this outcome. We propose two model structures for the longitudinal covariate, for the case when the missing data are missing at random, and when the missing data mechanism is non-ignorable. A generalized EM algorithm is used to obtain maximum likelihood estimates.",
keywords = "longitudinal covariates, missingness, ordinal outcomes",
author = "Melody Goodman and Yi Li and Stoddard, {Anne M.} and Glorian Sorensen",
year = "2014",
month = "5",
doi = "10.1080/02664763.2013.859236",
language = "English (US)",
volume = "41",
pages = "1040--1052",
journal = "Journal of Applied Statistics",
issn = "0266-4763",
publisher = "Routledge",
number = "5",

}

TY - JOUR

T1 - Analysis of ordinal outcomes with longitudinal covariates subject to missingness

AU - Goodman, Melody

AU - Li, Yi

AU - Stoddard, Anne M.

AU - Sorensen, Glorian

PY - 2014/5

Y1 - 2014/5

N2 - We propose a mixture model for data with an ordinal outcome and a longitudinal covariate that is subject to missingness. Data from a tailored telephone delivered, smoking cessation intervention for construction laborers are used to illustrate the method, which considers as an outcome a categorical measure of smoking cessation, and evaluates the effectiveness of the motivational telephone interviews on this outcome. We propose two model structures for the longitudinal covariate, for the case when the missing data are missing at random, and when the missing data mechanism is non-ignorable. A generalized EM algorithm is used to obtain maximum likelihood estimates.

AB - We propose a mixture model for data with an ordinal outcome and a longitudinal covariate that is subject to missingness. Data from a tailored telephone delivered, smoking cessation intervention for construction laborers are used to illustrate the method, which considers as an outcome a categorical measure of smoking cessation, and evaluates the effectiveness of the motivational telephone interviews on this outcome. We propose two model structures for the longitudinal covariate, for the case when the missing data are missing at random, and when the missing data mechanism is non-ignorable. A generalized EM algorithm is used to obtain maximum likelihood estimates.

KW - longitudinal covariates

KW - missingness

KW - ordinal outcomes

UR - http://www.scopus.com/inward/record.url?scp=84897628288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84897628288&partnerID=8YFLogxK

U2 - 10.1080/02664763.2013.859236

DO - 10.1080/02664763.2013.859236

M3 - Article

AN - SCOPUS:84897628288

VL - 41

SP - 1040

EP - 1052

JO - Journal of Applied Statistics

JF - Journal of Applied Statistics

SN - 0266-4763

IS - 5

ER -