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-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.
Full-textDOI: · Available from: Wayne F Velicer, Jun 12, 2015
- SourceAvailable from: Wayne F Velicer[Show abstract] [Hide abstract]
ABSTRACT: Treating multiple health behavior risks on a population basis is one of the most promising approaches to enhancing health and reducing health care costs. Previous research demonstrated the efficacy of expert system interventions for three behaviors in a population of parents. The interventions provide individualized feedback that guides participants through the stages of change for each of their risk behaviors. This study extended that research to a more representative population of patients from primary care practice and to targeting of four rather than three behaviors. Stage-based expert systems were applied to reduce smoking, improve diet, decrease sun exposure, and prevent relapse from regular mammography. A randomized clinical controlled trial recruited 69.2% of primary care patients (N = 5407) at home via telephone. Three intervention contacts were delivered for each risk factor at 0, 6, and 12 months. The primary outcome measures were the percentages of at-risk patients at baseline who progressed to the action or maintenance stages at 24-month follow-up for each of the risk behaviors. Significant treatment effects were found for each of the four behaviors, with 25.4% of intervention patients in action or maintenance for smoking, 28.8% for diet, and 23.4% for sun exposure. The treatment group had less relapse from regular mammography than the control group (6% vs. 10%). Proactive, home-based, and stage-matched expert systems can produce relatively high population impacts on multiple behavior risks for cancer and other chronic diseases.Preventive Medicine 09/2005; 41(2):406-16. DOI:10.1016/j.ypmed.2004.09.050 · 2.93 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: To significantly reduce smoking prevalence, treatments must balance reach, efficacy, and cost. The Internet can reach millions of smokers cost-effectively. Many cessation Web sites exist, but few have been evaluated. As a result, the potential impact of the Internet on smoking prevalence remains unknown. The present study reports the results, challenges, and limitations of a preliminary, large-scale evaluation of a broadly disseminated smoking cessation Web site used worldwide (QuitNet). Consecutive registrants (N=1,501) were surveyed 3 months after they registered on the Web site to assess 7-day point prevalence abstinence. Results must be interpreted cautiously because this is an uncontrolled study with a 25.6% response rate. Approximately 30% of those surveyed indicated they had already quit smoking at registration. Excluding these participants, an intention-to-treat analysis yielded 7% point prevalence abstinence (for the responders only, abstinence was 30%). A range of plausible cessation outcomes (9.8%-13.1%) among various subgroups is presented to illustrate the strengths and limitations of conducting Web-based evaluations, and the tensions between clinical and dissemination research methods. Process-to-outcome analyses indicated that sustained use of QuitNet, especially the use of social support, was associated with more than three times greater point prevalence abstinence and more than four times greater continuous abstinence. Despite its limitations, the present study provides useful information about the potential efficacy, challenging design and methodological issues, process-to-outcome mechanisms of action, and potential public health impact of Internet-based behavior change programs for smoking cessation.Nicotine & Tobacco Research 05/2005; 7(2):207-16. DOI:10.1080/14622200500055319 · 2.81 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: Three stage-based expert system interventions for smoking, high-fat diet, and unsafe sun exposure were evaluated in a sample of 2,460 parents of teenagers. Eighty-four percent of the eligible parents were enrolled in a 2-arm randomized control trial, with the treatment group receiving individualized feedback reports for each of their relevant behaviors at 0, 6, and 12 months as well as a multiple behavior manual. At 24 months, the expert system outperformed the comparison condition across all 3 risk behaviors, resulting in 22% of the participants in action or maintenance for smoking (vs. 16% for the comparison condition), 34% for diet (vs. 26%), and 30% for sun exposure (vs. 22%). Proactive, home-based, and stage-matched expert systems can produce significant multiple behavior changes in at-risk populations where the majority of participants are not prepared to change.Health Psychology 10/2004; 23(5):503-16. DOI:10.1037/0278-6220.127.116.113 · 3.95 Impact Factor