Novel Statistical Models for Intensive Longitudinal Analyses of Cancer Control Behaviors

项目总结 该提案响应了PAR-18-352(《行为和社会中的方法论和测量 科学“)。它将开发、应用、测试和传播用于估计的多水平统计模型和软件 由时变变量组成的个体内均值、方差、斜率对癌症控制风险的影响 因素和结果。癌症仍然是导致死亡的主要原因。年约42%的新癌症病例 美国人被认为可能是可以避免的，其中19%的人是由吸烟引起的，18%的人是由过度肥胖引起的 体重、缺乏体力活动、过量饮酒和营养不良。密集纵向数据(ILD) 方法，收集在微时间尺度(例如，秒， 几分钟、几小时)，使用实时数据捕获方法(例如移动传感和加速测量)，提供 洞察癌症风险因素和结果的动态性质的巨大机会。在ILD研究中， 每个受试者有成百上千的观察结果是很常见的，这使得我们能够 由时变变量组成的个体内参数，例如平均值(例如，受试者有多不高兴， 平均来说，在不同的场合？)、差异(例如，受试者的情绪在不同的场合有多反复无常？)和斜坡 (例如，受试者的情绪是否与不同场合的精力有关？)在前期工作中，我们有 开始开发一系列两阶段多水平统计模型，以测试个体内均值、方差和 斜率参数作为受试者水平结果的预测者、中介者和调节者。我们已经证明了 更大的个体内部变异性，但不是感觉精力充沛的平均水平，与较低的相遇几率有关 体力活动指南。我们还发现，积极情感中的个体内部变异性减缓了 个体内的关联意味着积极的情绪与抑郁症状和饮酒有关。 然而，当前的数据分析技术在几个关键领域受到限制，这严重限制了我们 充分利用ILD的全部潜力，加强癌症控制方面的行为和社会科学研究。至 为了解决这些差距，我们提出了以下目标。具体地说，我们将开发能够 (1)估计嵌套在时间或时间内的时变变量的个体内方差和斜率的影响 人群集群，(2)预测嵌套在时间或集群内的癌症控制结果，(3)比较 几个个体内方差的相对预测强度，以及(4)检验个体内方差或 计数变量或顺序变量的斜率。我们将通过进行二次分析来测试这些统计扩展 使用ILD进行的三项癌症控制研究(在643人中嵌套了94,892次)的数据包括 儿童、中年人、亲子二人。我们还将开发、测试和传播一个独立的 具有能够运行这些统计模型的图形用户界面的软件，可供应用行为和社会科学使用 研究人员。将要开发的方法可以很容易地推广到各种其他疾病领域，如哮喘， 饮食失调、自杀预防、艾滋病毒风险、服药依从性和环境暴露。

PROJECT SUMMARY This proposal responds to PAR-18-352 (“Methodology and Measurement in the Behavioral and Social Sciences”). It will develop, apply, test, and disseminate multilevel statistical models and software for estimating effects of intraindividual means, variances, slopes comprised of time-varying variables on cancer control risk factors and outcomes. Cancer remains a leading cause of mortality. Approximately 42% of new cancer cases in the U.S. are viewed as potentially avoidable including 19% caused by smoking and 18% caused by excess body weight, physical inactivity, excess alcohol consumption, and poor nutrition. Intensive Longitudinal Data (ILD) methods, which collect many assessments captured at high density on a micro-timescale (e.g., seconds, minutes, hours) using real-time data capture methodologies (e.g., mobile sensing and accelerometry), offer enormous opportunities for insight into the dynamic nature of cancer risk factors and outcomes. In ILD studies, it is common to have hundreds to thousands of observations per subject, and this allows us to model intraindividual parameters comprised of time-varying variables such as means (e.g., how unhappy is a subject, on average, across occasions?), variances (e.g., how erratic is a subject’s mood across occasions?), and slopes (e.g., is a subject’s mood related to feelings of energy across occasions?). In our preliminary work, we have begun developing a series of two-stage multilevel statistical models to test intraindividual mean, variance, and slope parameters as predictors, mediators, and moderators of subject-level outcomes. We have shown that greater intraindividual variability in, but not mean of feeling energetic, was associated with lower odds of meeting physical activity guidelines. We have also found that intraindividual variability in positive affect moderated the associations of intraindividual mean positive affect with depressive symptoms and alcohol consumption. However, current data analysis techniques are limited in several key areas, which severely limit our ability to capitalize on the full potential ILD to enhance behavioral and social science research in cancer control. To address these gaps, we propose the following aims. Specifically, we will develop multilevel models capable of (1) estimating effects of intraindividual variances and slopes for time-varying variables nested in time or within clusters of people, (2) predicting cancer control outcomes nested within time or clusters, (3) comparing the relative predictive strength of several intraindividual variances, and (4) examining intraindividual variances or slopes for count or ordinal variables. We will test these statistical extensions by conducting secondary analyses of data from three cancer control studies using ILD (with 94,892 occasions nested within 643 people) including children, middle-aged adults, parent-child dyads. We will also develop, test, and disseminate a stand-alone software with GUI capable of running these statistical models to be used by applied behavioral and social science researchers. The methods to be developed can easily generalize to a variety of other disease areas such asthma, disordered eating, suicide prevention, HIV risk, medication adherence, and environmental exposures.