NotesFAQContact Us
Collection
Advanced
Search Tips
Peer reviewed Peer reviewed
PDF on ERIC Download full text
ERIC Number: ED562786
Record Type: Non-Journal
Publication Date: 2014
Pages: 9
Abstractor: ERIC
Reference Count: 20
ISBN: N/A
ISSN: N/A
Meta-Analyzing a Complex Correlational Dataset: A Case Study Using Correlations That Measure the Relationship between Parental Involvement and Academic Achievement
Polanin, Joshua R.; Wilson, Sandra Jo
Society for Research on Educational Effectiveness
The purpose of this project is to demonstrate the practical methods developed to utilize a dataset consisting of both multivariate and multilevel effect size data. The context for this project is a large-scale meta-analytic review of the predictors of academic achievement. This project is guided by three primary research questions: (1) How do we meta-analyze the heterogeneous and complex, multivariate, multilevel, and longitudinal correlational literature on parental involvement and academic achievement?; (2) What are the associations between parental involvement and academic achievement, controlling for socioeconomic status and age?; and (3) Are there differential impacts on academic achievement as a function of the type of parental involvement (i.e., school-based versus home-based)? The research design of this project is a multilevel, multivariate meta-analysis. Researchers have collected over 700 primary studies that measured and reported longitudinal correlations of behavior, attitude, and school readiness predicting academic achievement. More than 150,000 bivariate correlations have been extracted. The population of interest, given that this project is a meta-analysis, is primary studies. Researchers searched and screened traditional and grey literature databases, including PsycInfo, ERIC, Digital Dissertations, as well as several conference websites, and national study repositories. Experts in this field were also contacted. The results of this analysis provide a synthesized correlation matrix. To account for differences across the effect sizes and studies, researchers use a meta-regression to control differences in attrition, age, and race. The results of this project are ongoing. Based on 1,559 longitudinal correlation estimates, the simple weighted-mean effect size is positive and moderate across all correlations. Tables and figures are appended.
Society for Research on Educational Effectiveness. 2040 Sheridan Road, Evanston, IL 60208. Tel: 202-495-0920; Fax: 202-640-4401; e-mail: inquiries@sree.org; Web site: http://www.sree.org
Publication Type: Reports - Research; Information Analyses
Education Level: N/A
Audience: N/A
Language: English
Sponsor: N/A
Authoring Institution: Society for Research on Educational Effectiveness (SREE)