Combining Cluster and Discriminant Analysis to Develop a Social Bond Topology of Runaway Youth

Abstract

Typology development using discriminant analysis is extremely valuable in learning more about heterogeneous client populations of interest to social workers. However, the discriminant analysis procedure is confined to situations in which individuals can be categorized into subgroups by the social work researcher. Classifying individuals by demographic variables such as gender or services utilized is straightforward and presents few problems. However, when more subjective categories are used to identify subgroup membership, problems may arise. There are many populations, such as the sexually abused, alcohol and drug abusers, sex offenders, and so on, who may avoid answering direct questions or deliberately give incorrect answers on questions formulated to classify them. This places in question the results of the discriminant analysis. In this article, data on 258 runaway and homeless youth are used to demonstrate how cluster analysis can be employed to create a classification variable needed to perform discriminant analysis. First, the data are submitted to cluster analysis to identify the groups in the population. Then, utilizing the cluster groups as the classifying variable needed to perform a discriminant analysis, the discriminantfunctions are extracted to develop a typology. The limitations of cluster analysis and this approach are discussed.The purpose of this article is to demonstrate an approach that employs both cluster and discriminant function analysis to develop a typology of a heterogeneous population. These two procedures are combined because of limitations that often hamper typology development in social research.When the research effort is to differentiate subgroups in a population and to predict the group to which a case belongs, discriminant analysis is one of the best statistical techniques available. Discriminant analysis uses a linear combination of predictor variables to classify each case into one of several groups that are identified by the classification variable. For a better understanding of the role of these variables, the classification variables can be thought of as the dependent variable. This variable identifies group member-

Subgroups of Dutch homeless young adults based on risk- and protective factors for quality of life: Results of a latent class analysis

“…Quantitative studies go a step further in providing empirical evidence for classifications of homeless young people. Such typologies of HYA, similar to homeless people in general (Humphreys & Rosenheck, 1995;Kuhn & Culhane, 1998;Morse, Calsyn, & Burger, 1992;Tsai, Edens, & Rosenheck, 2011;Tsai, Kasprow, & Rosenheck, 2013), are often based on housing status (Tierney, Gupton, & Hallett, 2008), reasons for homelessness (Cherry, 1993;Heinze, Jozefowicz, Toro, & Blue, 2012), family background (Benjaminsen, 2016), service utilisation (Kort-Butler & Tyler, 2012), and risk factors (or risk practices) associated with homelessness and well-being, such as psychological problems, substance use and victimisation experiences (Adlaf & Zdanowicz, 1999;Bender, Ferguson, Thompson, & Langenderfer, 2014;Bucher, 2008;Mallett, Rosenthal, Myers, Milburn, & Rotheram-Borus, 2004;Milburn et al, 2009). Some studies also included protective factors for healthy development, such as having supportive friends, being employed or going to school to categorise HYA (Mallett et al, 2004;Milburn et al, 2009;Zide & Cherry, 1992).…”

Identifying the Patterns of Emergency Shelter Stays of Single Individuals in Canadian Cities of Different Sizes

“…Much of the research in this area has been limited to examining relatively small samples of homogeneous subgroups of people who are homeless, categorized on the basis of either age, sex, or some other demographic or clinical characteristic (Adlaf & Zdanowicz, 1999;Bonin et al, 2009;Cherry, 1993;Danseco & Holden, 1998;Goldstein et al, 2008aGoldstein et al, , 2008bHumphreys & Rosenheck, 1995;Morse et al, 1991;Zide & Cherry, 1992). Another limitation is that most of the research has been cross-sectional in nature.…”

Outcomes for Adolescents Using Runaway and Homeless Youth Services

“…Four major types of runaways have been identified: (1) ''running to,'' (2) ''running from,'' (3) ''thrown out,'' and (4) ''forsaken'' (Jones, 1988;Cherry, 1993;Zide & Cherry, 1992;Hier et al, 1990). While previous work has identified and described homeless and runaway youths, there has been little research to date that examines outcomes of these youths that use community services.…”