Residuals for directional data *

Various types of residual are proposed for use with directional data. Asymptotic distributions are given for large sample sizes and for concentrated error distributions. A form of residual plot is suggested and is illustrated with some practical examples.     

Optimum stratification with two variates

For the 2×2 rectilinear stratification of a bivariate normal distribution with proportional and optimum allocation the dependence of the objective function z(x₁;y₁) on the coefficient of correlation ρ and the sampling fraction q=n/N is investigated. With proportional allocation for great values of ρ (but already for q=0) a so-called ρ-effect arises, which results in a saddle-point of z as “optimum” stratification point in the center of gravity of the distribution and two additional minima. With optimum allocation first for smaller values of q also the ρ-effect arises; for grater values of q a so-called q-effect is superposed, which results in a multitude of minima, saddle-points and maxima of z. All these points satisfy the generalized conditions of Dalenius, but for practical use only the global minimum is of interest.     

The narrative self in autobiographical accounts of illness

The paper analyzes autobiographical acounts of the experience of chronic illness and its treatment to develop a sociological theory of the self. It is suggested that ‘self’ is not a biologistic or psycologistic thing. Rather self is autobiographical narrative – hence the narrative self. It is argued that four elements constitute such narrative selves in autobiographical discourse: evaluative relationships between events in time; cosmology; power relationships; and conceptualisation of self as object.     

The assessment of parent-led prevention programs: a preliminary assessment of impact

This article reports on a preliminary study of the impact of parent-led prevention groups on youthful drug and alcohol use. In addition, the study assessed the extent to which families involved with parent-led prevention programs reported improved family relations and increased parental control of children's social activities--two major mechanisms by which parent-group advocates claim their activities alter youth substance use patterns. Consistent with the claims of parent-group advocates, the study results suggest that the parent groups did have some impact on family relations and on parental control of children's social activities. The evidence for an impact on drug and alcohol use was, however, weak. A somewhat unexpected finding was that parents who become involved in parent-led prevention activities may not be those parents whose children are at highest risk.     

Severity of illness: red herring or horse of different color? Part 2.

In this continuation of his article, the author defines severity and acuity of illness and discusses approaches to the measurement of the two factors. He provides some background on severity of illness measures that are in current use and prepares for a discussion of the uses of these measures.     

Child-rearing practices of two generations of Punjabi parents

The major objective of this article is to report the findings of two studies which compare and contrast the early child-rearing practices of two generations of Punjabi parents (1970s and 1990s) living in England. Additionally, the findings are compared with a small group of white mothers to broaden our understanding of the changing patterns of parenting. The data was collected through in-depth semi-structured interviews from the first generation during the period 1970–73 and from the second generation in 1995. The research perspective adopted is a qualitative one in that variables and procedures for data collection are not rigorously controlled, and the narratives of the mothers are used extensively to illuminate the key areas of early child rearing. The findings show that the second-generation mothers are shedding most of the traditional customs and practices and are moving towards modern British ways.     

A Formal Restatement of Durkheim's "Division of Labor" Theory

Despite frequent references in the sociological literature to Durkheim's theory about the division of labor, sociologists have made few attempts to test it. The paucity of attempts and the very debatable outcomes thereof are due largely to Durkheim's use of the traditional discursive mode of theory construction. A discursively stated theory's logical structure is likely to be obscure, and for that reason alone tests of it are difficult and controversial. Rather than perpetuate the exegetical tradition in sociological treatments of the subject, this paper restates Durkheim's theory in accordance with a particular formal mode. That restatement identifies the theory's shortcomings and problems. But the eight premises imply only one testable theorem, and the theorem's predictive accuracy appears minimal unless "population concentration" is substituted for "density" in the first axiom. Nonetheless, the restatement clearly shows how extension of the theory (additional postulates) could further its testability.