Scott Menard

Multiple Problem Youth: Delinquency, Substance Use, and Mental Health Problems.

1 Introduction.- 2 The Demographic Distribution of Delinquency and ADM Problems.- 3 Prevalence and General Offending/Use Patterns: The Joint Occurrence of Delinquent Behavior and ADM Problems.- 4 Age, Period, and Cohort Effects.- 5 Developmental Patterns.- 6 The Etiology of Delinquency and ADM Problems.- 7 Prediction of Delinquent and ADM Behavior from Other Delinquent and ADM Behavior.- 8 Summary and Implications.- References.- Appendix A Frequency of Alcohol Use.- Appendix B Mental Health Measures.- Appendix C Prevalence and Offending/Use Rates for Multiple Problem Types.- Appendix D Annual Transition Matrices for Problem Behavior Types.- Author Index.

Coefficients of Determination for Multiple Logistic Regression Analysis

Abstract Coefficients of determination for continuous predicted values (R 2 analogs) in logistic regression are examined for their conceptual and mathematical similarity to the familiar R 2 statistic from ordinary least squares regression, and compared to coefficients of determination for discrete predicted values (indexes of predictive efficiency). An example motivated by substantive concerns and using empirical data from a national household probability sample is presented to illustrate the behavior of the different coefficients of determination in the evaluation of models including dependent variables with different base rates—that is, different proportions of cases or observations with “positive” outcomes. One R 2 analog appears to be preferable to the others both in terms of conceptual similarity to the ordinary least squares coefficient of determination, and in terms of its relative independence from the base rate. In addition, base rate should also be considered when selecting an index of predictive efficiency. As expected, the conclusions based on R 2 analogs are not necessarily consistent with conclusions based on predictive efficiency, with respect to which of several outcomes is better predicted by a given model.

Six Approaches to Calculating Standardized Logistic Regression Coefficients

This article reviews six alternative approaches to constructing standardized logistic regression coefficients. The least attractive of the options is the one currently most readily available in logistic regression software, the unstandardized coefficient divided by its standard error (which is actually the normal distribution version of the Wald statistic). One alternative has the advantage of simplicity, while a slightly more complex alternative most closely parallels the standardized coefficient in ordinary least squares regression, in the sense of being based on variance in the dependent variable and the predictors. The sixth alternative, based on information theory, may be the best from a conceptual standpoint, but unless and until appropriate algorithms are constructed to simplify its calculation, its use is limited to relatively simple logistic regression models in practical application.

Childhood Maltreatment, Subsequent Antisocial Behavior, and the Role of Monoamine Oxidase A Genotype

BACKGROUND A functional promoter polymorphism in monoamine oxidase A (MAOA) has been implicated as a moderating factor in the relationship between childhood maltreatment and later adolescent and adult antisocial behavior. Despite wide interest in this hypothesis, results remain mixed from the few attempts at replication. METHODS Regression-based analyses were conducted to test for a genotype-environment interaction using self-reported physical abuse and MAOA genotype to predict later antisocial behavior and arrests for violence by participants in the National Youth Survey Family Study. We also examined the interaction using a measure of violent victimization. The analysis sample included 277 Caucasian male respondents, aged 11-15 in 1976, who provided buccal swab DNA samples and who were successfully genotyped for the variable number tandem repeat (VNTR) in the MAOA promoter using polymerase chain reaction. RESULTS Maltreatment by a parent during adolescence was a risk factor for adolescent and adult antisocial and violence related behavioral problems. Tests for the main effect of MAOA and a MAOA-maltreatment interaction were nonsignificant. Similar results were obtained using the measure of adolescent violent victimization. CONCLUSIONS Findings from this general population sample could not confirm the hypothesis that MAOA moderates the relationship between adolescent maltreatment and adolescent or adult antisocial behavior.

Continuities in marital violence

Marital violence studies of clinical populations of battered women indicate that, over time, violence becomes an habitual strategy for resolving conflicts resulting in escalation in frequency and severity of violence. This study examines the issue of continuity of marital violence among a national probability sample of female victims and male offenders. Findings indicate that among the general population, approximately one-half of all marital violence is suspended over a three-year period. Predictors of marital violence continuity were also investigated in an exploratory way.

Delinquency and drug use: Temporal and developmental patterns

The long- and short-term relationships of alcohol and illegal drug use to delinquent and criminal behavior are examined. As anticipated, substance use and delinquency are positively associated, but there is little evidence that substance use leads to delinquency. Two possible exceptions to this generalization involve the role of alcohol use in sexual assault and the role of serious drug use in prolonging involvement in serious delinquency. There is evidence that minor delinquency is a necessary cause or precursor of illicit drug use, that less serious levels of delinquency are necessary causes or precursors of more serious levels of delinquency, and that less serious levels of substance use are necessary causes or precursors of more serious levels of substance use. Relationships between substance use and more serious (index) delinquency appear to be developmental, not causal.

Drugs and crime revisited

The relationship between drugs and crime is investigated, building on previous research by Huizinga, Menard, and Elliott and by Goldstein and his colleagues. The previous research is extended by examining the relationship between drugs and crime at different stages of the life course, adolescence and early adulthood; by extending the age range used in previous research by Huizinga and colleagues; and by examining the impact of adolescent substance use and illegal behavior on adult substance use and illegal behavior. The results are consistent with past research in finding that (1) for initiation, the “drug use causes crime” hypothesis is untenable because crime typically is initiated before substance use; (2) more serious forms of crime and substance use usually are initiated after minor forms of those behaviors, and rarely in the absence of such behaviors; and (3) once crime and substance use are initiated, each appears to increase the likelihood of continuity of the other or (equivalently) to reduce the likelihood of suspension. Beyond results from prior research, it also appears that (4) crime and drug use are more closely related in adolescence than in adulthood, and that (5) examination of the transition from adolescence to adulthood suggests that the most plausible conclusion is that drugs and crime are related by mutual causation: crime affects drug use and drug use affects crime.

A Developmental Test of Mertonian Anomie Theory

Mertons theory of anomie and deviant behavior has not been tested adequately. Oversimplified tests involving the relationship between crime and social class or between crime and the discrepancy between aspirations and expectations ignore both structural and social-psychological aspects of the theory, particularly the pivotal role of the mode of adaptation as an influence on the type and frequency of illegal behavior. In the present study, a careful review of Mertons writings on anomie theory is used to construct a more complete and rigorous test of the theory for respondents in early, middle, and late adolescence.

Longitudinal and cross-sectional data collection and analysis in the study of crime and delinquency

In response to recent debates about the utility of longitudinal as opposed to cross-sectional designs in the study of crime and delinquency, we examine empirical evidence on the extent to which longitudinal and cross-sectional data may be used interchangeably without altering substantive conclusions. We distinguish between longitudinal or cross-sectional methods of data collection and longitudinal or cross-sectional data, and acknowledge that longitudinal data may be collected by using a cross-sectional method. We examine the extent to which longitudinal data collected cross-sectionally are compatible with longitudinal data collected in a prospective longitudinal design. We then compare correlations and predictive models that use cross-sectional and longitudinal data to study the same substantive problem. We conclude with an examination of the issue of temporal order as a test of competing hypotheses. We find that longitudinal data collected in a cross-sectional design do not consistently produce the same...

Delinquent bonding, moral beliefs, and illegal behavior: A three-wave panel model

This paper examines the relationships among delinquent peer group bonding, conventional moral beliefs, and the frequency of minor and serious illegal behavior in the framework of an integrated theory of delinquent behavior. Three-wave, three-variable structural equation models are tested for minor and serious illegal behavior with data from a national longitudinal probability sample. The results are generally consistent with the integrated theory. Theoretical and methodological implications of the results are considered in the context of previous research on delinquent peer group bonding, moral beliefs, and illegal behavior.