Model-based imputation of latent cigarette counts using data from a calibration study

Sandra D. Griffith, Saul Shiffman, Yimei Li, Daniel F. Heitjan

Research output: Contribution to journalArticle

Abstract

In addition to dichotomous measures of abstinence, smoking studies may use daily cigarette consumption as an outcome variable. These counts hold the promise of more efficient and detailed analyses than dichotomous measures, but present serious quality issues - measurement error and heaping - if obtained by retrospective recall. A doubly-coded dataset with a retrospective recall measurement (timeline followback, TLFB) and a more precise instantaneous measurement (ecological momentary assessment, EMA) serves as a calibration dataset, allowing us to predict EMA given TLFB and baseline factors. We apply this model to multiply impute precise cigarette counts for a randomized, placebo-controlled trial of bupropion with only TLFB measurements available. To account for repeated measurements on a subject, we induce correlation in the imputed counts. Finally, we analyze the imputed data in a longitudinal model that accommodates random subject effects and zero inflation. Both raw and imputed data show a significant drug effect for reducing the odds of non-abstinence and the number of cigarettes smoked among non-abstainers, but the imputed data provide efficiency gains. This method permits the analysis of daily cigarette consumption data previously deemed suspect due to reporting error and is applicable to other self-reported count data sets for which calibration samples are available.

Original languageEnglish (US)
Pages (from-to)112-122
Number of pages11
JournalInternational Journal of Methods in Psychiatric Research
Volume25
Issue number2
DOIs
StatePublished - Jun 1 2016

Fingerprint

Tobacco Products
Calibration
Bupropion
Economic Inflation
Randomized Controlled Trials
Smoking
Placebos
Pharmaceutical Preparations
TimeLine
Datasets
Ecological Momentary Assessment

Keywords

  • Addiction
  • Methodology
  • Nicotine
  • Statistics
  • Tobacco

ASJC Scopus subject areas

  • Psychiatry and Mental health

Cite this

Model-based imputation of latent cigarette counts using data from a calibration study. / Griffith, Sandra D.; Shiffman, Saul; Li, Yimei; Heitjan, Daniel F.

In: International Journal of Methods in Psychiatric Research, Vol. 25, No. 2, 01.06.2016, p. 112-122.

Research output: Contribution to journalArticle

@article{e1b598d04ff14aceb6898d6328340965,
title = "Model-based imputation of latent cigarette counts using data from a calibration study",
abstract = "In addition to dichotomous measures of abstinence, smoking studies may use daily cigarette consumption as an outcome variable. These counts hold the promise of more efficient and detailed analyses than dichotomous measures, but present serious quality issues - measurement error and heaping - if obtained by retrospective recall. A doubly-coded dataset with a retrospective recall measurement (timeline followback, TLFB) and a more precise instantaneous measurement (ecological momentary assessment, EMA) serves as a calibration dataset, allowing us to predict EMA given TLFB and baseline factors. We apply this model to multiply impute precise cigarette counts for a randomized, placebo-controlled trial of bupropion with only TLFB measurements available. To account for repeated measurements on a subject, we induce correlation in the imputed counts. Finally, we analyze the imputed data in a longitudinal model that accommodates random subject effects and zero inflation. Both raw and imputed data show a significant drug effect for reducing the odds of non-abstinence and the number of cigarettes smoked among non-abstainers, but the imputed data provide efficiency gains. This method permits the analysis of daily cigarette consumption data previously deemed suspect due to reporting error and is applicable to other self-reported count data sets for which calibration samples are available.",
keywords = "Addiction, Methodology, Nicotine, Statistics, Tobacco",
author = "Griffith, {Sandra D.} and Saul Shiffman and Yimei Li and Heitjan, {Daniel F.}",
year = "2016",
month = "6",
day = "1",
doi = "10.1002/mpr.1468",
language = "English (US)",
volume = "25",
pages = "112--122",
journal = "International Journal of Methods in Psychiatric Research",
issn = "1049-8931",
publisher = "John Wiley and Sons Ltd",
number = "2",

}

TY - JOUR

T1 - Model-based imputation of latent cigarette counts using data from a calibration study

AU - Griffith, Sandra D.

AU - Shiffman, Saul

AU - Li, Yimei

AU - Heitjan, Daniel F.

PY - 2016/6/1

Y1 - 2016/6/1

N2 - In addition to dichotomous measures of abstinence, smoking studies may use daily cigarette consumption as an outcome variable. These counts hold the promise of more efficient and detailed analyses than dichotomous measures, but present serious quality issues - measurement error and heaping - if obtained by retrospective recall. A doubly-coded dataset with a retrospective recall measurement (timeline followback, TLFB) and a more precise instantaneous measurement (ecological momentary assessment, EMA) serves as a calibration dataset, allowing us to predict EMA given TLFB and baseline factors. We apply this model to multiply impute precise cigarette counts for a randomized, placebo-controlled trial of bupropion with only TLFB measurements available. To account for repeated measurements on a subject, we induce correlation in the imputed counts. Finally, we analyze the imputed data in a longitudinal model that accommodates random subject effects and zero inflation. Both raw and imputed data show a significant drug effect for reducing the odds of non-abstinence and the number of cigarettes smoked among non-abstainers, but the imputed data provide efficiency gains. This method permits the analysis of daily cigarette consumption data previously deemed suspect due to reporting error and is applicable to other self-reported count data sets for which calibration samples are available.

AB - In addition to dichotomous measures of abstinence, smoking studies may use daily cigarette consumption as an outcome variable. These counts hold the promise of more efficient and detailed analyses than dichotomous measures, but present serious quality issues - measurement error and heaping - if obtained by retrospective recall. A doubly-coded dataset with a retrospective recall measurement (timeline followback, TLFB) and a more precise instantaneous measurement (ecological momentary assessment, EMA) serves as a calibration dataset, allowing us to predict EMA given TLFB and baseline factors. We apply this model to multiply impute precise cigarette counts for a randomized, placebo-controlled trial of bupropion with only TLFB measurements available. To account for repeated measurements on a subject, we induce correlation in the imputed counts. Finally, we analyze the imputed data in a longitudinal model that accommodates random subject effects and zero inflation. Both raw and imputed data show a significant drug effect for reducing the odds of non-abstinence and the number of cigarettes smoked among non-abstainers, but the imputed data provide efficiency gains. This method permits the analysis of daily cigarette consumption data previously deemed suspect due to reporting error and is applicable to other self-reported count data sets for which calibration samples are available.

KW - Addiction

KW - Methodology

KW - Nicotine

KW - Statistics

KW - Tobacco

UR - http://www.scopus.com/inward/record.url?scp=84930999494&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930999494&partnerID=8YFLogxK

U2 - 10.1002/mpr.1468

DO - 10.1002/mpr.1468

M3 - Article

C2 - 26081923

AN - SCOPUS:84930999494

VL - 25

SP - 112

EP - 122

JO - International Journal of Methods in Psychiatric Research

JF - International Journal of Methods in Psychiatric Research

SN - 1049-8931

IS - 2

ER -