Identifying the key predictors of positive self-perceptions of aging using machine learning

Mohsen Joshanloo

Social Science & Medicine, 2025, vol. 374, issue C

Abstract: This study aimed to identify key predictors of self-perceptions of aging (SPA) among older adults by examining a comprehensive set of potential predictors across physical, psychological, social, and demographic domains. Data from over 4000 American adults (mean age ≈ 70) from the Health and Retirement Study were used. A machine learning approach using Random Forest regression was employed to assess the relative importance of 49 potential predictors of SPA. The results revealed that health status, age, and psychological resources emerged as the strongest predictors of SPA. The psychological resources included the positive triad of self-esteem, life satisfaction, and optimism, as well as sense of mastery. Emotional tendencies and experiences, financial satisfaction, personality traits, and social factors had substantially lower predictive power. This study provides a comprehensive understanding of the factors that predict SPA and their relative importance, offering insights for both theory and practice. The results highlight the potential for designing targeted, evidence-based interventions that enhance psychological resources, address health and functional well-being, provide tailored support across the lifespan, and incorporate lifestyle changes to foster positive aging perceptions.

Keywords: Aging; Random forest; Predictive model; Machine learning; Psychological resources; Health and retirement study (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0277953625003909
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:socmed:v:374:y:2025:i:c:s0277953625003909

Ordering information: This journal article can be ordered from
http://www.elsevier.com/wps/find/supportfaq.cws_home/regional
http://www.elsevier. ... _01_ooc_1&version=01

DOI: 10.1016/j.socscimed.2025.118060

Access Statistics for this article

Social Science & Medicine is currently edited by Ichiro (I.) Kawachi and S.V. (S.V.) Subramanian

More articles in Social Science & Medicine from Elsevier
Bibliographic data for series maintained by Catherine Liu ().