Combinations of Stressors in Midlife: Examining Role and Domain Stressors Using Regression Trees and Random Forests

Correspondence should be addressed to Stacey Scott, Center for Healthy Aging, Pennsylvania State University, University Park, PA 16802. E-mail: .
The Journals of Gerontology Series B Psychological Sciences and Social Sciences (Impact Factor: 3.21). 01/2013; 68(3). DOI: 10.1093/geronb/gbs166
Source: PubMed


Global perceptions of stress (GPS) have major implications for mental and physical health, and stress in midlife may influence adaptation in later life. Thus, it is important to determine the unique and interactive effects of diverse influences of role stress (at work or in personal relationships), loneliness, life events, time pressure, caregiving, finances, discrimination, and neighborhood circumstances on these GPS.

Exploratory regression trees and random forests were used to examine complex interactions among myriad events and chronic stressors in middle-aged participants' (N = 410; mean age = 52.12) GPS.

Different role and domain stressors were influential at high and low levels of loneliness. Varied combinations of these stressors resulting in similar levels of perceived stress are also outlined as examples of equifinality. Loneliness emerged as an important predictor across trees.

Exploring multiple stressors simultaneously provides insights into the diversity of stressor combinations across individuals--even those with similar levels of global perceived stress--and answers theoretical mandates to better understand the influence of stress by sampling from many domain and role stressors. Further, the unique influences of each predictor relative to the others inform theory and applied work. Finally, examples of equifinality and multifinality call for targeted interventions.

2 Reads
  • [Show abstract] [Hide abstract]
    ABSTRACT: Building on prior work linking high anger expression to poor health, this cross-sectional study addressed whether anger expression exacerbated age-related risk for metabolic syndrome in a national sample of adults, known as MIDUS (Midlife in the United States).Method.Respondents reported anger expression via survey assessments and completed an overnight clinic visit. Unadjusted metabolic syndrome prevalence was 40.6%. Men, less educated individuals, and those who reported not getting regular physical activity were at significantly higher risk for metabolic syndrome. Anger expression did not predict higher risk for metabolic syndrome in main effects models, but it moderated the relationship between age and metabolic syndrome. Age-associated risk for metabolic syndrome was significant only for adults with high anger expression.Discussion.Among older adults, anger expression predicted higher prevalence of metabolic syndrome. Older adults reporting low anger expression had metabolic syndrome rates comparable to younger adults. Results highlight that failing to show the frequently observed decline in anger expression with age may have pernicious health concomitants.
    The Journals of Gerontology Series B Psychological Sciences and Social Sciences 09/2013; 70(1). DOI:10.1093/geronb/gbt092 · 3.21 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Characterization of stress exposure requires understanding seasonal variability in stress biomarkers. To compare acute and chronic stress biomarkers between two seasons in a cohort of rural, Hispanic mothers. Stress questionnaires and cortisol measurements (hair, blood and saliva) were collected in the summer and fall. Cortisol biomarkers were significantly different and stress questionnaires were significantly correlated between seasons. The variability in cortisol and relative stability of questionnaires between seasons may indicate that cortisol responds to subtle stressors not addressed in questionnaires. There are significant differences in stress biomarkers in our cohort between seasons.
    Biomarkers 08/2015; 20(5). DOI:10.3109/1354750X.2015.1068863 · 2.26 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Technology and collaboration are enabling dramatic increases in the size of psychological and psychiatric data collections, but finding structure in these large data sets with many collected variables is challenging. Decision tree ensembles like random forests (Strobl, Malley, and Tutz, 2009) are a useful tool for finding structure, but are difficult to interpret with multiple outcome variables which are often of interest in psychology. To find and interpret structure in data sets with multiple outcomes and many predictors (possibly exceeding the sample size), we introduce a multivariate extension to a decision tree ensemble method called Gradient Boosted Regression Trees (Friedman, 2001). Our method, multivariate tree boosting, can be used for identifying important predictors, detecting predictors with non-linear effects and interactions without specification of such effects, and for identifying predictors that cause two or more outcome variables to covary without parametric assumptions. We provide the R package 'mvtboost' to estimate, tune, and interpret the resulting model, which extends the implementation of univariate boosting in the R package 'gbm' (Ridgeway, 2013) to continuous, multivariate outcomes. To illustrate the approach, we analyze predictors of psychological well-being (Ryff and Keyes, 1995). Simulations verify that our approach identifies predictors with non-linear effects and achieves high prediction accuracy, exceeding or matching the performance of (penalized) multivariate multiple regression and multivariate decision trees over a wide range of conditions.