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

Resource Type: Reports & Papers
Author(s): Li, Spencer D.;
Date Issued: June, 2011
Description: 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)
show entire record ↓
Funder(s): United States. Administration for Children and Families
Journal Title: Evaluation Review
Volume Number: 35
Issue Number: 3
Page Range: 240-268
Note: This resource is also based on data from the National Youth Survey (NYS) (waves 3-5).
Topics: Research & Evaluation Methods > Research Methods > Data Analysis & Interpretation

Programs, Interventions & Curricula > Programs > Early Head Start/Head Start
Country: United States
ISSN: 0193-841X Paper
1552-3926 Online
Peer Reviewed: yes
hide record ↑

Related Resources

what is this? Related Resources include summaries, versions, or components of the currently selected resource, documents encompassing or employing it, or datasets/measures used in its creation.

Head Start Services, Parents' Social Capital, and Parent Involvement in Head Start Programs Administration for Children and Families/OPRE Projects

Related Datasets

Head Start Family and Child Experiences Survey (FACES): 2000 Cohort [United States]

More Like This

what is this? These resources were found by comparing the title, description, and topics of the currently selected resource to the rest of the Research Connections holdings.

Moderation and mediation in structural equation modeling: Applications for early intervention research Other
Longitudinal stability of IRT and equivalent groups linear and equipercentile equating Reports & Papers
Using symmetric predication of endogenous subgroups for causal inferences about program effects under robust assumptions: Part two of a method note in three parts Other
Two-year versus one-year Head Start program impact: Addressing selection bias by comparing regression modeling with propensity score analysis Reports & Papers
The comparative regression discontinuity (CRD) design: An overview and demonstration of its performance relative to basic RD and the randomized experiment Reports & Papers

Disclaimer: Use of the above resource is governed by Research Connections' Terms of Use.