Child Care and Early Education Research Connections

Skip to main content

Testing mediation using multiple regression and structural equation modeling analyses in secondary data

Mediation analysis in child and adolescent development research is possible using large secondary data sets. This article provides an overview of two statistical methods commonly used to test mediated effects in secondary analysis: multiple regression and structural equation modeling (SEM). Two empirical studies are presented to illustrate the respective circumstances in which the two methods are most useful. One study examines the mediated effect of parents' social capital on parent involvement in Head Start programs through parent-child bond. The other study assesses the mediating effects of structured routine activities, delinquent association, and prosocial belief on the relationship between religiosity and juvenile delinquency. (author abstract)
Resource Type:
Reports & Papers
United States

Related resources include summaries, versions, measures (instruments), or other resources in which the current document plays a part. Research products funded by the Office of Planning, Research, and Evaluation are related to their project records.

- You May Also Like

These resources share similarities with the current selection.

Moderation and mediation in structural equation modeling: Applications for early intervention research


Evaluating interventions with multimethod data: A structural equation modeling approach

Reports & Papers

Multiple mediation analysis of the relationship between rapid naming and reading

Reports & Papers
Release: 'v1.40.0' | Built: 2023-11-07 08:40:06 EST