Abstract

Objective: Previous research has indicated high rates of intercity movement among homeless young adults (HYAs) for a variety of prosocial (e.g., avoiding domestic violence and seeking new employment opportunities) and antisocial (e.g., following drug supplies and avoiding law enforcement) reasons. The complicated mixture of individual circumstances associated with transience has made it difficult to predict features of transience, such as distance traveled and move frequency. Method: This study describes a method to build an artificial neural network (ANN) that predicts distance traveled and compares the results of that ANN to a generalized linear regression. Results: The ANN more accurately predicts distance traveled than does the linear statistical model and advances the development of approaches to predict complicated human phenomena. Conclusions: Accurately predicting features of transience among HYAs is important in tailoring effective interventions aimed at minimizing travel for negative reasons and making travel for positive reasons safer.

Original languageEnglish (US)
Pages (from-to)89-106
Number of pages18
JournalJournal of the Society for Social Work and Research
Volume9
Issue number1
DOIs
StatePublished - Mar 1 2018

Fingerprint

linear model
neural network
young adult
travel
employment opportunity
law enforcement
domestic violence
drug
regression

Keywords

  • Emerging adulthood
  • Hierarchical modeling
  • Homelessness
  • Quantitative methods
  • Risk behaviors

ASJC Scopus subject areas

  • Social Sciences (miscellaneous)
  • Sociology and Political Science

Cite this

Predicting movement of homeless young adults : Artificial neural networks and generalized linear models. / Helderop, Edward; Ferguson-Colvin, Kristin; Grubesic, Anthony; Bender, Kimberly.

In: Journal of the Society for Social Work and Research, Vol. 9, No. 1, 01.03.2018, p. 89-106.

Research output: Contribution to journalArticle

@article{bd6e58c78cf440ae856dd1d945f6bb1d,
title = "Predicting movement of homeless young adults: Artificial neural networks and generalized linear models",
abstract = "Objective: Previous research has indicated high rates of intercity movement among homeless young adults (HYAs) for a variety of prosocial (e.g., avoiding domestic violence and seeking new employment opportunities) and antisocial (e.g., following drug supplies and avoiding law enforcement) reasons. The complicated mixture of individual circumstances associated with transience has made it difficult to predict features of transience, such as distance traveled and move frequency. Method: This study describes a method to build an artificial neural network (ANN) that predicts distance traveled and compares the results of that ANN to a generalized linear regression. Results: The ANN more accurately predicts distance traveled than does the linear statistical model and advances the development of approaches to predict complicated human phenomena. Conclusions: Accurately predicting features of transience among HYAs is important in tailoring effective interventions aimed at minimizing travel for negative reasons and making travel for positive reasons safer.",
keywords = "Emerging adulthood, Hierarchical modeling, Homelessness, Quantitative methods, Risk behaviors",
author = "Edward Helderop and Kristin Ferguson-Colvin and Anthony Grubesic and Kimberly Bender",
year = "2018",
month = "3",
day = "1",
doi = "10.1086/696129",
language = "English (US)",
volume = "9",
pages = "89--106",
journal = "Journal of the Society for Social Work and Research",
issn = "2334-2315",
publisher = "University of Chicago Press",
number = "1",

}

TY - JOUR

T1 - Predicting movement of homeless young adults

T2 - Artificial neural networks and generalized linear models

AU - Helderop, Edward

AU - Ferguson-Colvin, Kristin

AU - Grubesic, Anthony

AU - Bender, Kimberly

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Objective: Previous research has indicated high rates of intercity movement among homeless young adults (HYAs) for a variety of prosocial (e.g., avoiding domestic violence and seeking new employment opportunities) and antisocial (e.g., following drug supplies and avoiding law enforcement) reasons. The complicated mixture of individual circumstances associated with transience has made it difficult to predict features of transience, such as distance traveled and move frequency. Method: This study describes a method to build an artificial neural network (ANN) that predicts distance traveled and compares the results of that ANN to a generalized linear regression. Results: The ANN more accurately predicts distance traveled than does the linear statistical model and advances the development of approaches to predict complicated human phenomena. Conclusions: Accurately predicting features of transience among HYAs is important in tailoring effective interventions aimed at minimizing travel for negative reasons and making travel for positive reasons safer.

AB - Objective: Previous research has indicated high rates of intercity movement among homeless young adults (HYAs) for a variety of prosocial (e.g., avoiding domestic violence and seeking new employment opportunities) and antisocial (e.g., following drug supplies and avoiding law enforcement) reasons. The complicated mixture of individual circumstances associated with transience has made it difficult to predict features of transience, such as distance traveled and move frequency. Method: This study describes a method to build an artificial neural network (ANN) that predicts distance traveled and compares the results of that ANN to a generalized linear regression. Results: The ANN more accurately predicts distance traveled than does the linear statistical model and advances the development of approaches to predict complicated human phenomena. Conclusions: Accurately predicting features of transience among HYAs is important in tailoring effective interventions aimed at minimizing travel for negative reasons and making travel for positive reasons safer.

KW - Emerging adulthood

KW - Hierarchical modeling

KW - Homelessness

KW - Quantitative methods

KW - Risk behaviors

UR - http://www.scopus.com/inward/record.url?scp=85043998376&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043998376&partnerID=8YFLogxK

U2 - 10.1086/696129

DO - 10.1086/696129

M3 - Article

AN - SCOPUS:85043998376

VL - 9

SP - 89

EP - 106

JO - Journal of the Society for Social Work and Research

JF - Journal of the Society for Social Work and Research

SN - 2334-2315

IS - 1

ER -