检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
机构地区:[1]北京市应用实验心理重点实验室,北京师范大学心理学院,北京100875
出 处:《心理科学进展》2007年第3期567-576,共10页Advances in Psychological Science
摘 要:项目组合(item parceling)是对同一量表中的若干项目进行整合并形成新的观测指标的过程。虽然一直以来它都是一个有争议的议题,但随着其在结构方程模型中的应用日益广泛,它越来越受到研究者重视。文章从项目组合的基本逻辑、优缺点以及具体方法等方面对项目组合的研究进行了概括,并在此基础上提出了使用的具体建议:(1)根据研究的目的与具体情境选择是否需要组合;(2)组合之前必须首先确定概念的维度性;(3)项目组合最好建立在一定的理论基础上等等。未来的研究可以深入探讨各种组合方法对模型拟合以及参数估计的影响以及项目组合在一些SEM高阶应用中的效果,并进一步与项目反应理论等测量理论相结合。Item parceling could be defined as a technique of composing two or more items assessing the same construct to a new manifest indicator. Although item parceling was controversial all the time, it attracted more and more researchers' attention since this technique had been widely applied in structural equation modeling procedures. The purpose of this article is to discuss some important aspects about the research in this field, especially the rationale, the advantage and disadvantage, and the methods of parceling practice. On this base, we give some advice about how to construct item parcels, including (a) choosing to parcel or not to parcel according to the research goal and situation; (b) ensuring the dimensionality before parceling; and (c) building parcels on certain theories etc. Future research can focus on the impact of various parceling methods on the model fit and estimates, or the application of parceling in advanced SEM procedures and other measurement theories.
分 类 号:B841[哲学宗教—基础心理学]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.117