Predicting Daily Sheltering Arrangements among Youth Experiencing Homelessness Using Diary Measurements Collected by Ecological Momentary Assessment

Abstract

Youths experiencing homelessness (YEH) often cycle between various sheltering locations including spending nights on the streets, in shelters and with others. Few studies have explored the patterns of daily sheltering over time. A total of 66 participants completed 724 ecological momentary assessments that assessed daily sleeping arrangements. Analyses applied a hypothesis-generating machine learning algorithm (component-wise gradient boosting) to build interpretable models that would select only the best predictors of daily sheltering from a large set of 92 variables while accounting for the correlated nature of the data. Sheltering was examined as a three-category outcome comparing nights spent literally homeless, unstably housed or at a shelter. The final model retained 15 predictors. These predictors included (among others) specific stressors (e.g., not having a place to stay, parenting and hunger), discrimination (by a friend or nonspecified other; due to race or homelessness), being arrested and synthetic cannabinoids use (a.k.a., “kush”). The final model demonstrated success in classifying the categorical outcome. These results have implications for developing just-in-time adaptive interventions for improving the lives of YEH.

Who Is Couch-Surfing and Who Is on the Streets? Disparities Among Racial and Sexual Minority Youth in Experiences of Homelessness

“…Meanwhile, researchers and practitioners alike acknowledge the volatility of living arrangements employed by YEH. Instead of residing in one location for extended periods of time, youth frequently cycle through various settings, including the streets, emergency shelters, motel rooms, staying temporarily with family or friends, or spending the night with strangers [15,16]. Indeed, recent research suggests that the living arrangements of YEH can change almost daily [17].…”

“…Couch-surfing is frequently conceived as a housing strategy utilized by youth during an initial housing loss and a precursor to street homelessness [18,19]. However, longitudinal and retrospective studies suggest that couch-surfing can be part of diverse and complex trajectories of homelessness characteristic of YEH [15,20] and intertwined with young people's identity, social relationships, and vulnerabilities [6]. Couch-surfing youth may also be at uniquely higher risk of poor housing outcomes.…”

Understanding Why Many People Experiencing Homelessness Reported Migrating to a Small Canadian City: Machine Learning Approach With Augmented Data

“…Addressing and preventing homelessness is critical because it negatively affects the physical and mental health of these populations and causes substantial costs to the public [ 1 ]. Many important facets of homelessness have been studied by researchers, including homelessness experienced by youth, family, and veterans [ 2 - 6 ], as well as homelessness because of substance use [ 7 , 8 ], financial strain [ 9 ], mental health [ 9 , 10 ], and racism [ 11 ].…”

“…Many previous studies have presented the use of applied statistical analysis to produce qualitative results, such as finding the important risk factors contributing to homelessness [ 15 ]. Meanwhile, several studies have used machine learning concepts to perform predictive analysis and develop decision support tools related to homelessness research, such as predicting whether a person will become homeless, the duration of homeless stay [ 16 ], the readmission to the homeless state [ 16 , 17 ], and which individuals get housing and daily sheltering arrangements [ 6 , 18 ]. Furthermore, researchers have also focused on understanding homelessness by group identities, such as racial identity [ 11 ], adolescence [ 6 , 19 , 20 ], substance use [ 8 ], the uptake of medical treatments [ 8 ], and veterans [ 2 ].…”

Unsheltered homeless and unstably housed adults have higher levels of stress and more health risk factors than sheltered homeless adults

“…Thus, unsheltered homeless and unstably housed people who are not allowed to stay at shelters may have worse outcomes compared with sheltered homeless adults. Speci cally, they may be less likely to utilize health care services, and this may have detrimental effects on their health behaviors and health outcomes (19). Understanding characteristics of subgroups of homeless adults (sheltered vs. unsheltered vs. unstably housed) could inform health promotion and health intervention programs for this understudied and underserved population.…”