Data Management and Analysis

数据管理和分析核心的目标是继续提供数据管理 为方案项目调查员提供广泛的数据获取和统计方面的服务和统计专业知识 分析活动。每个项目的目标都包括核心观测数据的管理和分析， 访谈、问卷和行为数据，以及个人数据的管理和分析 项目。数据管理活动利用数据管理和数据管理的大量资源。 北卡罗来纳大学弗兰克·波特·格雷厄姆儿童发展中心(FPG)的分析中心(DMAC)和 PSD的方法学中心(TMC)。数据管理和分析核心的具体目标是： 1)与执行委员会一起实施计划中的缺失设计。 2)制定和维护数据管理战略，处理共同议定书中收集的数据，并 个人项目高效、准确。 3)设计和维护项目和通用协议数据的综合数据库。 4)利用创新的纵向数据分析方法制定和实施数据分析计划 包括以变量为中心和以人为中心的方法来解决 与项目调查人员合作。 5)建立数据存档系统，实现数据共享。 这些目标需要有经验的统计学家和计算机程序员的合作。DMAC 程序员在量化数据管理的各个方面都有专业知识，从输入和跟踪 数据用于分析文件的生成和统计编程。DMAC和TMC统计学家 在许多早期设计和统计问题上与这些和其他调查人员合作 儿童研究项目。数据管理和分析核心为 这些领域中每个领域的计划项目。使用经验丰富的数据采集和分析中心 跨项目处理和分析数据将提供高水平的质量控制和成本 有效性。 中央数据采集和分析中心对本计划项目尤为重要，因为数据 来自每个项目的信息有助于共同议定书，供所有项目在处理其假设时使用。 特别是项目一“课堂观察”收集的行政运作和自我调节措施 和项目II收集的儿童认知/学习结果，以及由 项目III和来自核心的社区衡量标准是#年使用的主要预测指标或成果衡量标准 所有项目的分析。数据处理和分析的中央协调将确保一致和 及时处理这些数据，以供所有调查人员仔细记录数据评分，包括 “汇总变量的可靠性和分布，将促进一个项目的数据被其他项目使用 调查人员。 数据管理和分析核心提供的服务几乎涉及 研究包括设计、数据收集、数据录入和分析。它的主要优点是 数据管理和计算的集中化设施是提供协调服务的能力，该服务 解决这些活动所涉及的广泛问题。通过协调所有用户的数据处理活动 项目减少了重复劳动，提高了数据管理和分析的效率，以及 提供了跨不同项目的数据集进行更高级别分析的机会。因此， 在所有项目中获得最大限度的沟通，以促进对要分析的数据的理解，如 以及这些分析的统计程序。此外，项目之间的协同作用也得到了加强 通过让相同的程序员和统计学家在各个项目中工作。

The objective of the Data Management and Analysis Core is to continue to provide data management services and statistical expertise to Program Project investigators in a wide range of data acquisition and analysis activities. Integral to the goals of each project is the management and analysis of Core observational, interview, questionnaire, and behavioral data, as well as management and analysis of data from the individual projects. Data management activities draw on the considerable resources of the Data Management and Analysis Center (DMAC) at the Frank Porter Graham Child Development Center (FPG) at UNC and The Methodology Center (TMC) at PSD. Specific Aims of the Data Management and Analysis Core are to: 1) Implement the planned missing design in conjunction with the Executive Committee. 2) Develop and maintain data management strategies that process data collected in the common protocol and the individual projects efficiently and accurately. 3) Design and maintain integrated databases of project and common protocol data. 4) Develop and implement data analysis plans using innovative analytic methods for longitudinal data including variable-centered and person-centered approaches to address research questions in collaboration with project investigators. 5) To set in place a data archiving system for data sharing. These goals require the collaboration of experienced statisticians and computer programmers. The DMAC programmers have expertise in all aspects of quantitative data management, from the entry and tracking of data to the generation of analysis files and statistical programming. The DMAC and TMC statisticians collaborated with these and other investigators regarding design and statistical issues across many early childhood research projects. The Data Management and Analysis Core provides high level expertise to the Program Project in each of these areas. The use of an experienced data acquisition and analysis center to process and analyze data across the projects will provide both high levels of quality control and cost effectiveness. A central data acquisition and analysis center is especially important for this Program Project because data from each project contributes to the common protocol for use by all projects in addressing their hypotheses. In particular, executive functioning and self regulation measures collected by Project I, classroom observations and child cognitive/academic outcomes collected by Project II, and family process measures collected by Project III, and community measures from the core are primary predictor or outcome measures used in analyses by all projects. Central coordination of data processing and analysis will ensure the consistent and timely processing of these ¿data^for-all- inyestigatgrsv Careful documentation of data scoring, including the "reliability and distributions of summary variables, will facilitate the use of one project's data by other project investigators. The services provided by the Data Management and Analysis Core pertain to almost all phases of the research including design, data collection, data entry, and analysis. The main advantage of having a centralized facility for data management and computing is the ability to provide coordinated services that address the wide range of issues involved in these activities. By coordinating data processing activities for all projects, duplication of effort is reduced, efficiencies of data management and analyses are generated, and opportunities for higher level analysis across data sets from different projects are made available. Thus, maximum communication is obtained across all projects to further the understanding of data to be analyzed, as well as the statistical procedures for those analyses. Furthermore, synergy among projects is enhanced through having the same programmers and statisticians working across projects.