Estimation problems of non-linear functional relationships

Non-linear functional relationships between two variables (curve fitting with errors in both variables) may be defined in a similar way to linear functional relationships. The ratio of the error variances must be fixed to obtain a solution to the likelihood equations, but this solution may not be unique. The best fitting solution may change abruptly as the error variance ratio passes through a critical value. Some examples are given.     

Gay youth in four cultures: a comparative study

Young and older homosexual men in four countries (Sweden, Finland, Ireland, and Australia) were compared on a number of psychological, social, and psychometric indices to determine what differences existed between them, and the effect of culture on any such differences. Data show that there are greater differences between younger and older homosexual men as the culture appears more antihomosexual, and that younger homosexual men are less likely to accept their sexual orientation and more likely to accept myths surrounding homosexuality. Younger homosexual men were also more likely to have had gonorrhea (regardless of their number of sexual partners), to prefer receptive anal intercourse, and to have contacted partners by cruising. These data confirm that mental health consequences of antihomosexual environments are most negative where homosexuality is most severely stigmatized.     

An investigation of cognitive style and alcohol/work-related problems among Naval personnel.

This study examines the relationship between cognitive style (i.e., information, normative, and diffuse orientation, and commitment) and alcohol/work-related problems. A random sample of Naval personnel (n = 2000) with less than two years of service toward their first enlistment was sent a questionnaire to assess cognitive style [1] and alcohol/work-related problems. A total of 899 respondents (45.0%) returned their questionnaires. Findings support prevention strategies that incorporate problem-solving, decision-making, and coping strategies, particularly among participants who employ diffuse problem-solving/coping strategies (lack of exploration and commitment, avoidance of problems). Correlations between cognitive style and alcohol/work-related problems are theoretically compatible. Diffuse orientation scores are positively related to both alcohol- and work-related problems, while norm and information orientation scores are negatively related to both measures. Collectively, cognitive style measures explain 11.4 percent of the variability in alcohol-related problems, and 14.0 percent of the variability in work-related problems.     

Empathy and Emotional Responsiveness in Delinquent and Non-delinquent Adolescents

Two groups of male adolescents, incarcerated young offenders (N = 64, mean age = 16.3 years) and a comparison group of community youth (N = 60; mean age = 16.6 years), were administered the Empathy Continuum (measuring cognitive‐affective responses to persons in emotionally evocative videotaped vignettes) and questionnaire measures of empathy, emotional responsiveness, guilt, shame, and antisocial attitudes and behaviors. Although both groups endorsed general statements of empathy, young offenders responded with empathy less often to particular persons in particular situations, and reasoned regarding their empathic responses in more self‐referencing ways. They also described their emotional responses to stimulus persons as less intense. In addition to the expected group differences, responsive empathy was a stronger predictor of delinquency than self‐reported antisocial behavior, and correctly classified 69 percent of young offenders and comparison youths. Although guilt was consistently related to lower self‐reported antisocial attitudes and behaviors, guilt (and shame) only weakly differentiated the two groups, limiting the usefulness of the TOSCA‐A as a predictor of delinquency.     

Performance of localized regression tree splitting criteria on data with discontinuities

Properties of the localized regression tree splitting criterion, described in Bremner & Taplin (2002) and referred to as the BT method, are explored in this paper and compared to those of Clark & Pregibon's (1992) criterion (the CP method). These properties indicate why the BT method can result in superior trees. This paper shows that the BT method exhibits a weak bias towards edge splits, and the CP method exhibits a strong bias towards central splits in the presence of main effects. A third criterion, called the SM method, that exhibits no bias towards a particular split position is introduced. The SM method is a modification of the BT method that uses more symmetric local means. The BT and SM methods are more likely to split at a discontinuity than the CP method because of their relatively low bias towards particular split positions. The paper shows that the BT and SM methods can be used to discover discontinuities in the data, and that they offer a way of producing a variety of different trees for examination or for tree averaging methods.     

Relationships and alliances in the social interaction of kibbutz toddlers

Two groups of five 20-month-old Kibbutz toddlers were studied in order to examine relationships and alliances. The toddlers were observed during free-play periods over a two-month period. Evidence of relationships is found when children make special adjustments in their interactions with specific partners that would not be predicted based on the individual characteristics that these children display with others, and were found for both conflict and positive interactions. Qualitative analyses revealed a variety of types of relationships, although reciprocal relationships that combined either high or low levels of both positive and conflict interactions predominated. Alliances occur when third parties intervene in conflicts they witness in the group and were present, though relatively rarely, at this age. Alliances were based not on the established relationships in the group, but rather on who had been wronged in the initial conflict. Results are discussed in terms of the links between relationships, cultural standards of fairness, and alliances.