Data Management/Statistics Core

点击翻译按钮获取中文摘要

PROJECT SUMMARY (See instructions): In this renewal, the Data Management, Measurement, and Stafistics (DMMS) Core will confinue to focus on four primary aims: (1) to provide expert data entry, management, and stafistical support across projects; (2) to develop common, psychometricahly sound measures (notably measures of smoking behaviors and outcomes) to use across projects; (3) to implement cross project, integrated analyses; and (4) to propose and develop stafisfical approaches to address key issues related to the analysis of adolescent smoking data. (1) SUPPORT. As in the original project, we will develop and maintain a computerized database for data entry and management, and we will develop detailed documentation ofthe database. We will continue to ufilize rigorous methods for data entry, edifing, and updafing to ensure that the data are clean, consistent, and secure. We will also provide stafistical support and collaboration for all projects. (2) MEASURES. We will assess smoking at mulfiple fimes and with mulfiple measures. A specific aim of the DMMS Core is to conceptualize and develop measures that will (a) aid in the identificafion of longitudinal smoking patterns and (b) aid in the interpretafion of contexts in which these patterns develop. (3) INTEGRATION. A key feature of the program project is that data will be available from the full cohort through questionnaires administered in Project 1 (four annual assessments) in addifion to data collected from subsets of the cohort in each of the other three projects. A major priority within the DMMS Core is to develop stafisfical models that allow integrated analyses of data from many sources. (4) DEVELOPMENT. Methodological research within the DMMS core will seek to advance the development of statisfical approaches for the analysis of smoking data. These efforts will be focused around three primary issues: the conceptualization/combinafion of mulfiple indices of "dependence," individual heterogeneity in smoking development across fime, and characterizing influences of heterogeneity.