Grounded in theory and research on the role of adolescent family experiences in young adult educational attainment, this study took the novel step of synthesizing results from prior studies and using a machine learning (ML) approach to address three questions: (1) By incorporating adolescent family experience factors examined across prior studies in a single analysis, how accurately can we predict young adult educational attainment? (2) Which family experience factors are the best predictors of young adult educational attainment? (3) What complex patterns among family experience predictors merit further examination? Based on a review of 101 publications that used National Longitudinal Study of Adolescent Health data to investigate links between adolescent family experiences and young adult attainment, we identified 53 family experience independent variables. We used an ML-based approach to train and test models with these 53 Wave I family variables (adolescent in Grade 7–12) as predictors of both college enrollment (N = 4598) and graduation (N = 4180) at Wave IV (young adult mean age = 28.88, SD = 1.76). Our models (1) obtained prediction accuracies of 73.43% and 72.33% for college enrollment, and 79.10% and 79.07% for college graduation, (2) identified the best predictors of college enrollment and graduation, including family socioeconomic characteristics and parent educational expectations, and (3) highlight nonlinear patterns for further examination. This study advanced understanding of how adolescent family experiences may influence educational attainment and provided a paradigm for developmental research to synthesize existing findings into novel discoveries with large-scale datasets.
|Original language||English (US)|
|Number of pages||16|
|Journal||Journal of Child and Family Studies|
|State||Published - Oct 1 2020|
Bibliographical noteFunding Information:
This material is based on work supported by the National Science Foundation under IGERT Grant DGE-1144860, Big Data Social Science.
This research uses data from Add Health, a program project directed by Kathleen Mullan Harris and designed by J. Richard Udry, Peter S. Bearman, and Kathleen Mullan Harris at the University of North Carolina at Chapel Hill, and funded by grant P01-HD31921 from the Eunice Kennedy Shriver National Institute of Child Health and Human Development, with cooperative funding from 23 other federal agencies and foundations. Special acknowledgment is due Ronald R. Rindfuss and Barbara Entwisle for assistance in the original design. Information on how to obtain the Add Health data files is available on the Add Health website ( http://www.cpc.unc.edu/addhealth ). No direct support was received from grant P01-HD31921 for this analysis.
© 2020, Springer Science+Business Media, LLC, part of Springer Nature.
- Adolescent family experiences
- Cross-study synthesis
- Machine learning
- National Longitudinal Study of Adolescent Health
- Young adult educational attainment