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.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.
"For our primary hypothesis test, we assume participants lost to follow-up are smokers. Depending on actual follow-up rates achieved, the results may be presented using recommended new strategies  to deal with missing data. Characteristics associated with nonresponse in smokers are used with SOLAS and SAS programs for implementing multiple imputation procedures. "
[Show abstract][Hide abstract] ABSTRACT: Background
Extended smoking cessation follow-up after hospital discharge significantly increases abstinence. Hospital smoke-free policies create a period of ‘forced abstinence’ for smokers, thus providing an opportunity to integrate tobacco dependence treatment, and to support post-discharge maintenance of hospital-acquired abstinence. This study is funded by the National Heart, Lung, and Blood Institute (1U01HL1053231).
The Inpatient Technology-Supported Assisted Referral study is a multi-center, randomized clinical effectiveness trial being conducted at Kaiser Permanente Northwest (KPNW) and at Oregon Health & Science University (OHSU) hospitals in Portland, Oregon. The study assesses the effectiveness and cost-effectiveness of linking a practical inpatient assisted referral to outpatient cessation services plus interactive voice recognition (AR + IVR) follow-up calls, compared to usual care inpatient counseling (UC). In November 2011, we began recruiting 900 hospital patients age ≥18 years who smoked ≥1 cigarettes in the past 30 days, willing to remain abstinent postdischarge, have a working phone, live within 50 miles of the hospital, speak English, and have no health-related barriers to participation. Each site will randomize 450 patients to AR + IVR or UC using a 2:1 assignment strategy. Participants in the AR + IVR arm will receive a brief inpatient cessation consult plus a referral to available outpatient cessation programs and medications, and four IVR follow-up calls over seven weeks postdischarge. Participants do not have to accept the referral. At KPNW, UC participants will receive brief inpatient counseling and encouragement to self-enroll in available outpatient services. The primary outcome is self-reported thirty-day smoking abstinence at six months postrandomization for AR + IVR participants compared to usual care. Additional outcomes include self-reported and biochemically confirmed seven-day abstinence at six months, self-reported seven-day, thirty-day, and continuous abstinence at twelve months, intervention dose response at six and twelve months for AR + IVR recipients, incremental cost-effectiveness of AR + IVR intervention compared to usual care at six and twelve months, and health-care utilization and expenditures at twelve months for AR + IVR recipients compared to UC.
This study will provide important evidence for the effectiveness and cost-effectiveness of linking hospital-based tobacco treatment specialists’ services with discharge follow-up care.
"To address these concerns, researchers have proposed to use generalized estimating equations (GEE) and generalized linear mixed-effects models (GLMM) . Both GEE and GLMM use repeated outcome measures and take the intra-personal association into account, and provide a means to comparing intervention effects at each time point and to examining whether the effects vary over time . GEE provides population-averaged estimates, and the covariate effects can be interpreted as in standard logistic regression models. "
[Show abstract][Hide abstract] ABSTRACT: Background:
GEE and mixed models are powerful tools to compare treatment effects in longitudinal smoking cessation trials. However, they are not capable of assessing the relapse (from abstinent back to smoking) simultaneously with cessation, which can be studied by transition models.
We apply a first-order Markov chain model to analyze the transition of smoking status measured every 6 months in a 2-year randomized smoking cessation trial, and to identify what factors are associated with the transition from smoking to abstinent and from abstinent to smoking. Missing values due to non-response are assumed non-ignorable and handled by the selection modeling approach.
Smokers receiving high-intensity disease management (HDM), of male gender, lower daily cigarette consumption, higher motivation and confidence to quit, and having serious attempts to quit were more likely to become abstinent (OR = 1.48, 1.66, 1.03, 1.15, 1.09 and 1.34, respectively) in the next 6 months. Among those who were abstinent, lower income and stronger nicotine dependence (OR = 1.72 for ≤ vs. > 40 K and OR = 1.75 for first cigarette ≤ vs. > 5 min) were more likely to have relapse in the next 6 months.
Markov chain models allow investigation of dynamic smoking-abstinence behavior and suggest that relapse is influenced by different factors than cessation. The knowledge of treatments and covariates in transitions in both directions may provide guidance for designing more effective interventions on smoking cessation and relapse prevention.
BMC Medical Research Methodology 07/2012; 12(1):95. DOI:10.1186/1471-2288-12-95 · 2.27 Impact Factor
"In the case of smoking cessation trials, those who fail to complete treatment or study assessments may do so because they have not quit smoking. One common method for handling such missing data in smoking cessation trials is to conduct intention-to-treat analyses, whereby those lost to follow-up are treated as smokers in the analyses (Hall et al., 2001). If large numbers of individuals do not receive the intervention or otherwise fail to provide outcome data, the treatment is likely to be deemed ineffective or results may be inconclusive, whether or not it is actually so. "
[Show abstract][Hide abstract] ABSTRACT: Techniques to recruit and retain college fraternity and sorority members who reported past 30-day smoking into a cessation trial are described. Recruitment efforts included relationship-building, raffles, and screening survey administration during existing meetings. Surveys were administered to 76% (n = 3,276) of members in 30 chapters, 79% of eligible members agreed to participate, and 76% of those completed assessments and were enrolled in the trial (n = 452). The retention rate was 73%. Retention efforts included cash incentives, flexible scheduling, multiple reminders, chapter incentives, and use of chapter members as study personnel. Retention was not related to demographic, behavioral, or group characteristics. The strategies of partnership, convenience, and flexibility appear effective and may prove useful to investigators recruiting similar samples.
Research in Nursing & Health 04/2010; 33(2):144-55. DOI:10.1002/nur.20372 · 1.27 Impact Factor