Adolescent Family Experiences Predict Young Adult Educational Attainment: A Data-Based Cross-Study Synthesis With Machine Learning.
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...
| Publicado en: | Journal of Child & Family Studies Vol. 29; no. 10; pp. 2770 - 2786 |
|---|---|
| Autores principales: | , , |
| Formato: | Artículo |
| Publicado: |
Springer Nature
Oct2020
|
| Materias: | |
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=145696012&site=ehost-live header: @attributes: shortDbName: ssf uiTerm: 145696012 longDbName: Social Sciences Full Text (H.W. Wilson) uiTag: AN controlInfo: bkinfo: jinfo: jid: 10621024 JFM jtl: Journal of Child & Family Studies issn: 10621024 maglogo: N pubinfo: dt: Oct2020 vid: 29 iid: 10 pid: 237 pub: Springer Nature artinfo: ui: 145696012 10.1007/s10826-020-01775-5 ppf: 2770 ppct: 16 formats: fmt: – @attributes: type: T – @attributes: type: P size: 1MB tig: atl: Adolescent Family Experiences Predict Young Adult Educational Attainment: A Data-Based Cross-Study Synthesis With Machine Learning. aug: au: Sun, Xiaoran Ram, Nilam McHale, Susan M. affil: The Pennsylvania State University, University Park, PA, USA su: Educational attainment Family relations Teenagers Education of young adults Machine learning College enrollment sug: subj: Educational attainment Family relations Teenagers Education of young adults Machine learning College enrollment keyword: Adolescent family experiences Cross-study synthesis National Longitudinal Study of Adolescent Health Young adult educational attainment Adolescent family experiences Cross-study synthesis National Longitudinal Study of Adolescent Health Young adult educational attainment ab: 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. Highlights: A machine learning paradigm for cross-study synthesis with large-scale datasets. Synthesized 101 education attainment studies with 53 adolescent family predictors. Family experiences predicted young adult attainment with 72.33–79.10% accuracy. Identified 12–19 key family predictors of young adult education attainment. Partial dependence plots highlight nonlinear patterns in prediction. pubtype: Academic Journal doctype: Article src: R language: English refInfo: copyright: @attributes: flag: N holdings: @attributes: islocal: N |
|---|