Statistical analysis of randomized trials in tobacco treatment: Longitudinal designs with dichotomous outcome

S. M. Hall, K. L. Delucchi, W. F. Velicer, C. W. Kahler, J. Ranger-Moor, D. Hedeker, J. Y. Tsoh, R. Niaura

Research output: Contribution to journalArticle

147 Citations (Scopus)

Abstract

This article considers two important issues in the statistical treatment of data from tobacco-treatment clinical trials: (1) data analysis strategies for longitudinal studies and (2) treatment of missing data. With respect to data analysis strategies, methods are classified as 'time-naïve' or longitudinal. Time-naïve methods include tests of proportions and logistic regression. Longitudinal methods include Generalized Estimating Equations and Generalized Linear Mixed Models. It is concluded that, despite some advantages accruing to 'time-naïve' methods, in most situations, longitudinal methods are preferable. Longitudinal methods allow direct effects of the tests of time and the interaction of treatment with time, and allow model estimates based on all available data. The discussion of missing data strategies examines problems accruing to complete-case analysis, last observation carried forward, mean substitution approaches, and coding participants with missing data as using tobacco. Distinctions between different cases of missing data are reviewed. It is concluded that optimal missing data analysis strategies include a careful description of reasons for data being missing, along with use of either pattern mixture or selection modeling. A standardized method for reporting missing data is proposed. Reference and software programs for both data analysis strategies and handling of missing data are presented.

Original languageEnglish (US)
Pages (from-to)193-202
Number of pages10
JournalNicotine and Tobacco Research
Volume3
Issue number3
StatePublished - 2001

Fingerprint

Tobacco
Longitudinal Studies
Linear Models
Research Design
Software
Logistic Models
Observation
Clinical Trials

ASJC Scopus subject areas

  • Public Health, Environmental and Occupational Health

Cite this

Hall, S. M., Delucchi, K. L., Velicer, W. F., Kahler, C. W., Ranger-Moor, J., Hedeker, D., ... Niaura, R. (2001). Statistical analysis of randomized trials in tobacco treatment: Longitudinal designs with dichotomous outcome. Nicotine and Tobacco Research, 3(3), 193-202.

Statistical analysis of randomized trials in tobacco treatment : Longitudinal designs with dichotomous outcome. / Hall, S. M.; Delucchi, K. L.; Velicer, W. F.; Kahler, C. W.; Ranger-Moor, J.; Hedeker, D.; Tsoh, J. Y.; Niaura, R.

In: Nicotine and Tobacco Research, Vol. 3, No. 3, 2001, p. 193-202.

Research output: Contribution to journalArticle

Hall, SM, Delucchi, KL, Velicer, WF, Kahler, CW, Ranger-Moor, J, Hedeker, D, Tsoh, JY & Niaura, R 2001, 'Statistical analysis of randomized trials in tobacco treatment: Longitudinal designs with dichotomous outcome', Nicotine and Tobacco Research, vol. 3, no. 3, pp. 193-202.
Hall SM, Delucchi KL, Velicer WF, Kahler CW, Ranger-Moor J, Hedeker D et al. Statistical analysis of randomized trials in tobacco treatment: Longitudinal designs with dichotomous outcome. Nicotine and Tobacco Research. 2001;3(3):193-202.
Hall, S. M. ; Delucchi, K. L. ; Velicer, W. F. ; Kahler, C. W. ; Ranger-Moor, J. ; Hedeker, D. ; Tsoh, J. Y. ; Niaura, R. / Statistical analysis of randomized trials in tobacco treatment : Longitudinal designs with dichotomous outcome. In: Nicotine and Tobacco Research. 2001 ; Vol. 3, No. 3. pp. 193-202.
@article{691ed32ec4634c01b06f102604fde723,
title = "Statistical analysis of randomized trials in tobacco treatment: Longitudinal designs with dichotomous outcome",
abstract = "This article considers two important issues in the statistical treatment of data from tobacco-treatment clinical trials: (1) data analysis strategies for longitudinal studies and (2) treatment of missing data. With respect to data analysis strategies, methods are classified as 'time-na{\"i}ve' or longitudinal. Time-na{\"i}ve methods include tests of proportions and logistic regression. Longitudinal methods include Generalized Estimating Equations and Generalized Linear Mixed Models. It is concluded that, despite some advantages accruing to 'time-na{\"i}ve' methods, in most situations, longitudinal methods are preferable. Longitudinal methods allow direct effects of the tests of time and the interaction of treatment with time, and allow model estimates based on all available data. The discussion of missing data strategies examines problems accruing to complete-case analysis, last observation carried forward, mean substitution approaches, and coding participants with missing data as using tobacco. Distinctions between different cases of missing data are reviewed. It is concluded that optimal missing data analysis strategies include a careful description of reasons for data being missing, along with use of either pattern mixture or selection modeling. A standardized method for reporting missing data is proposed. Reference and software programs for both data analysis strategies and handling of missing data are presented.",
author = "Hall, {S. M.} and Delucchi, {K. L.} and Velicer, {W. F.} and Kahler, {C. W.} and J. Ranger-Moor and D. Hedeker and Tsoh, {J. Y.} and R. Niaura",
year = "2001",
language = "English (US)",
volume = "3",
pages = "193--202",
journal = "Nicotine and Tobacco Research",
issn = "1462-2203",
publisher = "Oxford University Press",
number = "3",

}

TY - JOUR

T1 - Statistical analysis of randomized trials in tobacco treatment

T2 - Longitudinal designs with dichotomous outcome

AU - Hall, S. M.

AU - Delucchi, K. L.

AU - Velicer, W. F.

AU - Kahler, C. W.

AU - Ranger-Moor, J.

AU - Hedeker, D.

AU - Tsoh, J. Y.

AU - Niaura, R.

PY - 2001

Y1 - 2001

N2 - This article considers two important issues in the statistical treatment of data from tobacco-treatment clinical trials: (1) data analysis strategies for longitudinal studies and (2) treatment of missing data. With respect to data analysis strategies, methods are classified as 'time-naïve' or longitudinal. Time-naïve methods include tests of proportions and logistic regression. Longitudinal methods include Generalized Estimating Equations and Generalized Linear Mixed Models. It is concluded that, despite some advantages accruing to 'time-naïve' methods, in most situations, longitudinal methods are preferable. Longitudinal methods allow direct effects of the tests of time and the interaction of treatment with time, and allow model estimates based on all available data. The discussion of missing data strategies examines problems accruing to complete-case analysis, last observation carried forward, mean substitution approaches, and coding participants with missing data as using tobacco. Distinctions between different cases of missing data are reviewed. It is concluded that optimal missing data analysis strategies include a careful description of reasons for data being missing, along with use of either pattern mixture or selection modeling. A standardized method for reporting missing data is proposed. Reference and software programs for both data analysis strategies and handling of missing data are presented.

AB - This article considers two important issues in the statistical treatment of data from tobacco-treatment clinical trials: (1) data analysis strategies for longitudinal studies and (2) treatment of missing data. With respect to data analysis strategies, methods are classified as 'time-naïve' or longitudinal. Time-naïve methods include tests of proportions and logistic regression. Longitudinal methods include Generalized Estimating Equations and Generalized Linear Mixed Models. It is concluded that, despite some advantages accruing to 'time-naïve' methods, in most situations, longitudinal methods are preferable. Longitudinal methods allow direct effects of the tests of time and the interaction of treatment with time, and allow model estimates based on all available data. The discussion of missing data strategies examines problems accruing to complete-case analysis, last observation carried forward, mean substitution approaches, and coding participants with missing data as using tobacco. Distinctions between different cases of missing data are reviewed. It is concluded that optimal missing data analysis strategies include a careful description of reasons for data being missing, along with use of either pattern mixture or selection modeling. A standardized method for reporting missing data is proposed. Reference and software programs for both data analysis strategies and handling of missing data are presented.

UR - http://www.scopus.com/inward/record.url?scp=0034851806&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0034851806&partnerID=8YFLogxK

M3 - Article

C2 - 11506764

AN - SCOPUS:0034851806

VL - 3

SP - 193

EP - 202

JO - Nicotine and Tobacco Research

JF - Nicotine and Tobacco Research

SN - 1462-2203

IS - 3

ER -