Data-driven smooth tests of the proportional hazards assumption

A new test of the proportional hazards assumption in the Cox model is proposed. The idea is based on Neyman’s smooth tests. The Cox model with proportional hazards (i.e. time-constant covariate effects) is embedded in a model with a smoothly time-varying covariate effect that is expressed as a combination of some basis functions (e.g., Legendre polynomials, cosines). Then the smooth test is the score test for significance of these artificial covariates. Furthermore, we apply a modification of Schwarz’s selection rule to choosing the dimension of the smooth model (the number of the basis functions). The score test is then used in the selected model. In a simulation study, we compare the proposed tests with standard tests based on the score process.     

The Relationship of Four Types of ‘Broken Home’ to Some Neglected Parameters of Juvenile Delinquency

Using a sample of 1,130 male juvenile offenders, the relationship of four types of ‘broken home’ to the age at onset of delinquency, recidivism, rate of offences, and types of offence was investigated. The number of recidivists was found to be significantly greater among offenders who were living only with fathers than among offenders living with both parents. A trend in this direction was also found among offenders living only with mothers. Offenders living apart from parents were found to be older at the time of their first offence than were offenders living with both parents. The findings were discussed critically, and it was concluded that they support the hypothesis that the ‘broken home’ is not per se a causal factor in juvenile delinquency.     

The transmission of socioeconomic status and prestige in Great Britain and the United States

We analyze male occupational attainment using separate models in which occupational level is measured by indigenous socioeconomic index (SEI) scales, indigenous prestige scales, and a common prestige scale. Other than some consistent societal differences, the SEI scales produce highly similar results in both societies. In sharp contrast, both indigenous and common prestige scales indicate a stronger relative effect of origin (compared with education) on occupation in Great Britain. The dimensions of prestige and socioeconomic status thus seem to tap different aspects of the social mobility process, and the societies differ in the transmission of prestige but not socioeconomic status.     

On the Consistency of Court Dispositions in the Juvenile Criminal Justice System: A Research Note

An analysis of 13,919 cases dealt with by the Children's Court during a two year period showed significant differences between the regional patterns of dispositions made by the courts in respect of comparable male juvenile offenders (Crimes Act). Urban courts presided over by special children's magistrates were more lenient than countrty courts with regular stipendiary magistrates, except for committing greater numbers of offenders for trial in a higher court. Country courts in general tended to be more lenient in respect of selected offences than country courts located in areas of Aboriginal concentration. However, differences were also found between the dispositions of individual urban courts which could not be accounted for by the social and circumstantial factors associated with regional differences.     

Classification of Juvenile Offenders and Ecological Factors

The study was concerned with the relationship of social ecology to types of juvenile delinquency. In comparison with ecology designated (in an earlier study) as ‘Low socio-educational status’, the delinquent from an area with an ecology designated as ‘Individual-social-economic alienation’ was found to be more likely: to offend alone and not be motivated by gain, to abscond from legal custody, to have a history of neuropsychiatric conditions, to come from a broken home and a small family, not to reside with his parents, to leave school before reaching form three, and to be given two or more probations before committal to an institution. The delinquent from 'Low socio-educational status' area was more likely: to offend in company and be motivated by gain, not to abscond, not to have a history of neuropsychiatric conditions, to come from an intact home and a large family, to reside with his parents, to reach at least form three before leaving school, and to have no more than one period on probation before being committed to an institution. The differences appeared to be consistent with the often used criminological distinction between individual and social delinquency.     

Modelling method effects as individual causal effects

Summary.  Method effects often occur when different methods are used for measuring the same construct. We present a new approach for modelling this kind of phenomenon, consisting of a definition of method effects and a first model, the method effect model , that can be used for data analysis. This model may be applied to multitrait–multimethod data or to longitudinal data where the same construct is measured with at least two methods at all occasions. In this new approach, the definition of the method effects is based on the theory of individual causal effects by Neyman and Rubin. Method effects are accordingly conceptualized as the individual effects of applying measurement method j instead of k . They are modelled as latent difference scores in structural equation models. A reference method needs to be chosen against which all other methods are compared. The model fit is invariant to the choice of the reference method. The model allows the estimation of the average of the individual method effects, their variance, their correlation with the traits (and other latent variables) and the correlation of different method effects among each other. Furthermore, since the definition of the method effects is in line with the theory of causality, the method effects may (under certain conditions) be interpreted as causal effects of the method. The method effect model is compared with traditional multitrait–multimethod models. An example illustrates the application of the model to longitudinal data analysing the effect of negatively (such as 'feel bad') as compared with positively formulated items (such as 'feel good') measuring mood states.     

Perceived Risk, Stigma, and Potential Economic Impacts of a High-Level Nuclear Waste Repository in Nevada

This study investigates the potential impacts of the proposed nuclear waste repository at Yucca Mountain, Nevada, upon tourism, retirement and job-related migration, and business development in Las Vegas and the state. Adverse impacts may be expected to result from perceptions of risk, stigmatization, and socially amplified reactions to "unfortunate events" associated with the repository (major and minor accidents, discoveries of radiation releases, evidence of mismanagement, attempts to sabotage or disrupt the facility, etc.). The conceptual underpinnings of risk perception, stigmatization, and social amplification are discussed and empirical data are presented to demonstrate how nuclear images associated with Las Vegas and the State of Nevada might trigger adverse economic effects. The possibility that intense negative imagery associated with the repository may cause significant harm to Nevada's economy can no longer be ignored by serious attempts to assess the risks and impacts of this unique facility. The behavioral processes described here appear relevant as well to the social impact assessment of any proposed facility that produces, uses, transports, or disposes of hazardous materials.     

Undetermined manner of death. A comparison with unintentional injury, suicide, and homicide death

Injury deaths can be grouped into four general categories: accident, homicide, suicide, and undetermined. The present study investigates the use of the "undetermined" category. External cause of death, as well as demographic and other variables, were abstracted from death certificates of the 386,936 Californians who died of an injury between 1969 and 1991. Differences among the four manner-of-death groups were examined, and characteristics of the decedent and the injury event were used to predict a classification of undetermined. Coroners classified 1.9% of the deaths as undetermined in manner. Deaths of women, Blacks, Asians, and Native Americans; the very young and the middle aged; or those involving poisoning or submersion were most likely to be classified as undetermined. Acknowledging that individual coroner judgment may not be free of bias, these findings can help provide a better estimate of the frequency and the epidemiologic features of injury deaths that are assigned to the category of undetermined.