Time-varying coefficient models for joint modeling binary and continuous outcomes in longitudinal data

Esra Kürüm, Runze Li, Saul Shiffman, Weixin Yao

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Motivated by an empirical analysis of ecological momentary assessment data (EMA) collected in a smoking cessation study, we propose a joint modeling technique for estimating the time-varying association between two intensively measured longitudinal responses: a continuous one and a binary one. A major challenge in joint modeling these responses is the lack of a multivariate distribution. We suggest introducing a normal latent variable underlying the binary response and factorizing the model into two components: a marginal model for the continuous response, and a conditional model for the binary response given the continuous response. We develop a two-stage estimation procedure and establish the asymptotic normality of the resulting estimators. We also derived the standard error formulas for estimated coefficients. We conduct a Monte Carlo simulation study to assess the finite sample performance of our procedure. The proposed method is illustrated by an empirical analysis of smoking cessation data, in which the question of interest is to investigate the association between urge to smoke, continuous response, and the status of alcohol use, the binary response, and how this association varies over time.

Original languageEnglish (US)
Pages (from-to)979-1000
Number of pages22
JournalStatistica Sinica
Volume26
Issue number3
DOIs
StatePublished - Jul 2016

Fingerprint

Time-varying Coefficients
Varying Coefficient Model
Joint Modeling
Longitudinal Data
Binary Response
Binary
Smoking
Empirical Analysis
Two-stage Estimation
Marginal Model
Conditional Model
Multivariate Distribution
Latent Variables
Alcohol
Standard error
Asymptotic Normality
Time-varying
Monte Carlo Simulation
Modeling
Time-varying coefficient model

All Science Journal Classification (ASJC) codes

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Kürüm, Esra ; Li, Runze ; Shiffman, Saul ; Yao, Weixin. / Time-varying coefficient models for joint modeling binary and continuous outcomes in longitudinal data. In: Statistica Sinica. 2016 ; Vol. 26, No. 3. pp. 979-1000.
@article{75ad7a34ae4243538edb780c4a8c2130,
title = "Time-varying coefficient models for joint modeling binary and continuous outcomes in longitudinal data",
abstract = "Motivated by an empirical analysis of ecological momentary assessment data (EMA) collected in a smoking cessation study, we propose a joint modeling technique for estimating the time-varying association between two intensively measured longitudinal responses: a continuous one and a binary one. A major challenge in joint modeling these responses is the lack of a multivariate distribution. We suggest introducing a normal latent variable underlying the binary response and factorizing the model into two components: a marginal model for the continuous response, and a conditional model for the binary response given the continuous response. We develop a two-stage estimation procedure and establish the asymptotic normality of the resulting estimators. We also derived the standard error formulas for estimated coefficients. We conduct a Monte Carlo simulation study to assess the finite sample performance of our procedure. The proposed method is illustrated by an empirical analysis of smoking cessation data, in which the question of interest is to investigate the association between urge to smoke, continuous response, and the status of alcohol use, the binary response, and how this association varies over time.",
author = "Esra K{\"u}r{\"u}m and Runze Li and Saul Shiffman and Weixin Yao",
year = "2016",
month = "7",
doi = "10.5705/ss.2014.213",
language = "English (US)",
volume = "26",
pages = "979--1000",
journal = "Statistica Sinica",
issn = "1017-0405",
publisher = "Institute of Statistical Science",
number = "3",

}

Time-varying coefficient models for joint modeling binary and continuous outcomes in longitudinal data. / Kürüm, Esra; Li, Runze; Shiffman, Saul; Yao, Weixin.

In: Statistica Sinica, Vol. 26, No. 3, 07.2016, p. 979-1000.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Time-varying coefficient models for joint modeling binary and continuous outcomes in longitudinal data

AU - Kürüm, Esra

AU - Li, Runze

AU - Shiffman, Saul

AU - Yao, Weixin

PY - 2016/7

Y1 - 2016/7

N2 - Motivated by an empirical analysis of ecological momentary assessment data (EMA) collected in a smoking cessation study, we propose a joint modeling technique for estimating the time-varying association between two intensively measured longitudinal responses: a continuous one and a binary one. A major challenge in joint modeling these responses is the lack of a multivariate distribution. We suggest introducing a normal latent variable underlying the binary response and factorizing the model into two components: a marginal model for the continuous response, and a conditional model for the binary response given the continuous response. We develop a two-stage estimation procedure and establish the asymptotic normality of the resulting estimators. We also derived the standard error formulas for estimated coefficients. We conduct a Monte Carlo simulation study to assess the finite sample performance of our procedure. The proposed method is illustrated by an empirical analysis of smoking cessation data, in which the question of interest is to investigate the association between urge to smoke, continuous response, and the status of alcohol use, the binary response, and how this association varies over time.

AB - Motivated by an empirical analysis of ecological momentary assessment data (EMA) collected in a smoking cessation study, we propose a joint modeling technique for estimating the time-varying association between two intensively measured longitudinal responses: a continuous one and a binary one. A major challenge in joint modeling these responses is the lack of a multivariate distribution. We suggest introducing a normal latent variable underlying the binary response and factorizing the model into two components: a marginal model for the continuous response, and a conditional model for the binary response given the continuous response. We develop a two-stage estimation procedure and establish the asymptotic normality of the resulting estimators. We also derived the standard error formulas for estimated coefficients. We conduct a Monte Carlo simulation study to assess the finite sample performance of our procedure. The proposed method is illustrated by an empirical analysis of smoking cessation data, in which the question of interest is to investigate the association between urge to smoke, continuous response, and the status of alcohol use, the binary response, and how this association varies over time.

UR - http://www.scopus.com/inward/record.url?scp=85011846028&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011846028&partnerID=8YFLogxK

U2 - 10.5705/ss.2014.213

DO - 10.5705/ss.2014.213

M3 - Article

AN - SCOPUS:85011846028

VL - 26

SP - 979

EP - 1000

JO - Statistica Sinica

JF - Statistica Sinica

SN - 1017-0405

IS - 3

ER -