語言:

Representing general theoretical concepts in structural equation models: the role of composite variables

Grace, James B ; Bollen, Kenneth A

Environmental and ecological statistics, 2008-06, Vol.15 (2), p.191-213 [同儕審閱期刊]

可取得全文

引用被引用

傳送到

題名:
Representing general theoretical concepts in structural equation models: the role of composite variables
著者: Grace, James B ; Bollen, Kenneth A
主題: Biomedical and Life Sciences ; Chemistry and Earth Sciences ; Composites ; Computer based modeling ; Computer Science ; Construct models ; Constructs ; Diagnostic tests ; Ecologists ; Ecology ; Environmental studies ; Health Sciences ; Hypotheses ; Latent variables ; Life Sciences ; Math. Appl. in Environmental Science ; Medicine ; Parameter estimation ; Physics ; Statistics for Engineering ; Statistics for Life Sciences ; Structural equation modeling ; Studies ; Theoretical concepts ; Theoretical Ecology/Statistics ; Theory ; Variables ; Variance analysis
所屬期刊: Environmental and ecological statistics, 2008-06, Vol.15 (2), p.191-213
描述: Structural equation modeling (SEM) holds the promise of providing natural scientists the capacity to evaluate complex multivariate hypotheses about ecological systems. Building on its predecessors, path analysis and factor analysis, SEM allows for the incorporation of both observed and unobserved (latent) variables into theoretically-based probabilistic models. In this paper we discuss the interface between theory and data in SEM and the use of an additional variable type, the composite. In simple terms, composite variables specify the influences of collections of other variables and can be helpful in modeling heterogeneous concepts of the sort commonly of interest to ecologists. While long recognized as a potentially important element of SEM, composite variables have received very limited use, in part because of a lack of theoretical consideration, but also because of difficulties that arise in parameter estimation when using conventional solution procedures. In this paper we present a framework for discussing composites and demonstrate how the use of partially-reduced-form models can help to overcome some of the parameter estimation and evaluation problems associated with models containing composites. Diagnostic procedures for evaluating the most appropriate and effective use of composites are illustrated with an example from the ecological literature. It is argued that an ability to incorporate composite variables into structural equation models may be particularly valuable in the study of natural systems, where concepts are frequently multifaceted and the influence of suites of variables are often of interest.
出版者: Boston: Boston : Springer US
語言: 英文
識別號: ISSN: 1352-8505
EISSN: 1573-3009
DOI: 10.1007/s10651-007-0047-7
資源來源: SpringerLink Journals AutoHoldings
Agricultural & Environmental Science Collection

返回到檢索清單

Representing general theoretical concepts in structural equation models: the role of composite variables

Grace, James B ; Bollen, Kenneth A

正在檢索遠程資料庫，請稍等