Jost Reinecke

Strukturgleichungsmodelle in den Sozialwissenschaften

Mit diesem Werk wird neben der elementaren Einfuhrung in die Modellbildung mit Strukturgleichungen zugleich eine Ubersicht uber die Vielzahl von Anwendungsmoglichkeiten geboten. Es wird aufgezeigt, wie entsprechende Analysen unter Ruckgriff auf verbreitete Programme mit empirischem Datenmaterial durchgefuhrt werden konnen. Das Lehrbuch ist fur Veranstaltungen in Statistik und multivariaten Analyseverfahren in Hauptstudium konzipiert. Obwohl hier auch auf statistische Grundlagen fur Strukturgleichungsmodelle eingegangen wird, mussen elementare Kenntnisse der deskriptiven Statistik und der Inferenzstatistik vorausgesetzt werden.

Longitudinal Analysis of Adolescents’ Deviant and Delinquent Behavior

This article presents applications of different growth mixture models considering unobserved heterogeneity within the framework of Mplus (Muthen & Muthen, 2001a, 2001b, 2004). Latent class growth mixture models are discussed under special consideration of count variables that can be incorporated into the mixtures via the Poisson and the zero-inflated Poisson model. Fourwave panel data from a German criminological youth study (Boers et al., 2002) is used for the model analyses. Three classes can be obtained from the data: Adolescents with almost no deviant and delinquent activities, a medium proportion of adolescents with a low increase of delinquency, and a small number with a larger growth starting on a higher level. Considering the zero inflation of the data results in better model fits compared to the Poisson model only. Linear growth specifications are almost sufficient. The conditional application of the mixture models includes gender and educational level of the schools as time-independent predictor...

Protecting self-esteem from stigma: A test of different strategies for coping with the stigma of mental illness

Background: To date, there has been little research into effective strategies for preventing the detrimental effects of stigma on the well-being of people with mental illness. Aim: The present research set out to identify adaptive strategies for dealing with the stigma of mental illness. Methods: On the basis of the responses of 355 people with mental illness (PWMI) a standardized questionnaire assessing 10 identity management strategies was developed. Participants also reported their personal experiences with stigma, depression and self-esteem. Results: Hierarchical regression analyses showed that after controlling for depression and stigmatizing experiences, the strategies of community involvement, humour and positive ingroup stereotyping were related to higher self-esteem. Secrecy, selective disclosure and attempts at overcompensation or disproving stereotypes were related to lower self-esteem. The following strategies were unrelated to self-esteem: comparing the present social position of PWMI with that in the past, normalization of the illness within a medical model, information seeking and selective withdrawal. Conclusions: PWMI should be encouraged to seek support within their community and to develop a positive image of their ingroup.

Belittled, Avoided, Ignored, Denied: Assessing Forms and Consequences of Stigma Experiences of People With Mental Illness

People with mental illness experience discrimination, paternalistic treatment, and avoidance. To facilitate assessment of such experiences, the authors developed the Multifaceted Stigma Experiences Scale. It assesses four dimensions of experienced stigma in interpersonal interaction: hostile discrimination, benevolent discrimination, taboo, and denial. The influence of stigma experiences on mental health was modeled in a two-wave panel with persons with mental illness (N = 367, 79% repeated response rate). Results indicate that both subtle and blatant forms of stigma constitute a barrier to recovery and may be interpreted as attempts to increase social distance and reinforce the existing social order.

Explaining the development of adolescent violent delinquency

The etiological aspects of a structural dynamic model of delinquent development are analysed with the first five waves (age 13 to 17) of the German prospective panel study Crime in the Modern City, carried out since 2002 in Duisburg. By applying a combined Markov and growth curve model, the developments of structural explanatory factors and self-reported violent delinquency and their reciprocal as well as direct and indirect relations could be examined within one statistical model. Social macro-structure was considered within the notion of a wider social milieu, with social value orientations as the subjective component. The longitudinal analysis confirmed the conceptual distinction between distal and proximate structural factors: distal hedonistic value orientations marked the strongest pathway to violent delinquency via proximate pro-violent peer attachment and pro-violent norms. Although school bonds and parental education style were not of greater importance here, they nevertheless mediated a pathway into conformity with traditional value orientations as the structural background. A latent class growth analysis reproduced a by-now common pattern of six delinquency trajectories.

Conditional relevance of controls: A simultaneous test of the influences of self-control and deterrence on criminal behaviour in the context of Situational Action Theory

Situational Action Theory includes a series of propositions on the interaction between the moral filter and internal and external controls. These reflections are condensed into the principle of the conditional relevance of controls and the principle of moral correspondence. In this study, the interplay of controls and moral forces is tested within the framework of structural equation modelling. Survey data from two cohorts of students in the German cities of Dortmund (North-Rhine Westphalia) and Nuremberg (Bavaria) serve as the empirical base. By using multiple group comparisons, the influences of self-control and deterrence on self-reported delinquency are examined simultaneously for four different subgroups of respondents formed on the basis of their levels of crime propensity and criminogenic exposure. The analyses provide support for a conditional relevance of controls, but produce only mixed evidence for the principle of moral correspondence. Controls are more important when the moral filter is weak, but fail to lose their explanatory power among adolescents characterized by both high propensity and strong exposure. Our findings furthermore suggest that self-control appears to matter particularly when the moral context encourages crime and deterrence seems to be influential especially when personal morality encourages crime.

Introduction to the Special Issue with some reflections on the role of self-control in Situational Action Theory

In recent years, Per-Olof Wikström’s Situational Action Theory (SAT) (for example, Wikström, 2010; Wikström et al., 2012) has become one of the most-examined crime theories among European criminologists interested in crime causation. Although devised as a tool to explain rule-breaking behaviour in general, most contemporary applications deal with its potential to account for the formation of criminal or delinquent conduct. The theory’s key argument is that the interaction between an individual with a certain crime propensity and a setting with a certain criminogeneity triggers a perception–choice process that immediately governs action. Therewith SAT represents both a broad and a deep theory.1 It is broad in the sense that it successfully integrates person-oriented and environment-oriented explanations of criminal conduct. It is deep in the sense that it illuminates the mechanism that brings about criminal behaviour. A distinct feature is the theory’s focus on the interactive interplay of the various factors and processes involved in crime causation. ‘It’s all about interactions’ (Wikström et al., 2012) excellently describes the theory’s central credo. This implies a shift from the study of the unconditional effects of various influencing entities to their conditional effects, which runs through all articles included in this Special Issue of the European Journal of Criminology. In the first contribution to this issue, Wikström and colleagues provide a thorough introduction to SAT and preferred ways of testing it. Then they employ neural network

Youth Violence in Germany: Examining the Victim–Offender Overlap During the Transition From Adolescence to Early Adulthood

The victim–offender overlap is currently under discussion in criminology. However, the connection between victimization and offending over the life course still requires further investigation. The present study examines whether the victim–offender overlap is invariant during the transition from adolescence to early adulthood using seven consecutive waves of the German Research Foundation–funded self-report study “Crime in the Modern City,” which contain information about German students from the age of 14 to 20 years. The results indicate that the nature as well as the strength of the overlap changes over the period from adolescence to early adulthood. The introduced measurement of the relative victim–offender overlap indicates that with growing up, fewer victims are also offenders whereas the amount of offenders that are also victims remains stable. Longitudinal analyses based on latent growth and cross-lagged panel models further point out that the developments of victimization and offending are highly parallel processes that evince similar stability and mutual influence over the phase of youth and adolescence. However, the association between both weakens over age. In conclusion, our results suggest variance in the victim–offender overlap over the life course. This justifies the demand for further research and theory development on this criminological phenomenon.

Stage-Sequential Growth Mixture Modeling of Criminological Panel Data

The detection of distinctive developmental trajectories is of great importance in criminological research. The methodology of growth curve and finite mixture modeling provides the opportunity to examine different developments of offending. With latent growth curve models (LGM) (Meredith and Tisak, Psychometrika 55:107–122, 1990) the structural equation methodology offers a strategy to examine intra- and interindividual developmental processes of delinquent behavior. There might, however, not be a single but a mixture of populations underlying the growth curves which refers to unobserved heterogeneity in the longitudinal data. Growth mixture models (GMM) introduced by Muthen and Shedden (Biometrics 55:463–469, 1999) can consider unobserved heterogeneity when estimating growth curves. GMM distinguish between continuous variables which represent the growth curve model and categorical variables which refer to subgroups that have a common development in the growth process. The models are usually based on single-phase data which associate any event with a specific period. Panel data, however, often contain several relevant phases. In this context, stage-sequential growth mixture models with multiphase longitudinal data become increasingly important. Kim and Kim (Structural Equation Modeling: A Multidisciplinary Journal 19:293–319, 2012) investigated and discussed three distinctive types of stage-sequential growth mixture models: traditional piecewise GMM, discontinuous piecewise GMM, and sequential process GMM. These models will be applied here to examine different stages of delinquent trajectories within the time range of adolescence and young adulthood using data from the German panel study Crime in the Modern City (CrimoC, Boers et al., Monatsschrift fur Kriminologie und Strafrechtsreform 3:183–202, 2014). Methodological and substantive differences between single-phase and multi-phase models are discussed as well as recommendations for future applications.

Zur Messung von Handlungsabsichten im Kontext einer kriminologischen Panelstudie

Ausgehend von der besonderen Datenbasis und des speziellen Analysefokus im Bereich der kriminalsoziologischen Forschung wird in diesem Beitrag der methodische und inhaltliche Rahmen fur die Verwendung eines Vignetten-Designs zur Messung von Handlungsabsichten vorgestellt. Die Erfassung hypothetischer Reaktionen mithilfe einer alltagsnahen Situationsbeschreibung wird als sinnvolle Erganzung zu den durch Selbstberichte erfassten Pravalenz- und Inzidenzangaben sowie den eher abstrakten gewaltbefurwortenden Einstellungen der Befragten aufgefasst. Mithilfe exemplarischer Zusammenhangsanalysen der Querschnittsdaten aus dem Jahr 2015 des DFG-Projektes Kriminalitat in der modernen Stadt soll empirisch gezeigt werden, dass ein deutlicher Zusammenhang zwischen Handlung, intendierter Reaktion und den generellen Einstellungen zum Einsatz von Gewalt besteht.