Some Practical Aspects of Canonical Variate Analysis

Canonical variate analysis can be viewed as a two-stage principal component analysis. Explicit consideration of the principal components from the first stage, formalized in the content of shrunken estimators, leads to a number of practical advantages. In morphometric studies, the first eigenvector is often a size vector, with the remaining vectors contrast or shape-type vectors, so that a decomposition of the canonical variates into size and shape components can be achieved. In applied studies, often a small number of the principal components effect most of the separation between groups; plots of group means and associated concentration ellipses (ideally these should be circular) for important principal components facilitate graphical inspection. Of considerable practical importance is the potential for improved stability of the estimated canonical vectors. When the between-groups sum of squares for a particular principal component is small, and the corresponding eigenvalue of the within-groups correlation matrix is also small, marked instability of the canonical vectors can be expected. The introduction of shrunken estimators, by adding shrinkage constrants to the eigenvalues, leads to more stable coefficients.     

Word processors for qualitative sociologists: A review essay

Summary and Conclusions To reiterate, we think word processors driven by microcomputers can be used effectively for processing notes, observations and other textual data collected through qualitative research methods and later for analyzing them. Of course, machines cannot analyze data, engender concepts, or write insightful prose. In fact, these machines can do nothing that humans do not instruct them to do. InAnalyzing Social Settings, John Lofland describes the overlap of observation and analysis in a project and suggests the use of a general file structure and mechanical procedures that can stimulate on-going analysis during observation (1971:118). Whatever the system one uses, if the interplay between what is observed and what is made sociologically meaningful can be less a clerical task, then so much the better. In sum, we think word-processing systems can help a sociologist electronically cut and paste raw text files and spur the researcher into producing superior files and reports.     

Independent social choice correspondences

A fixed agenda social choice correspondence on outcome set X maps each profile of individual preferences into a nonempty subset of X. If satisfies an analogue of Arrow's independence of irrelevant alternatives condition, then either the range of contains exactly two alternatives, or else there is at most one individual whose preferences have any bearing on . This is the case even if is not defined for any proper subset of X.     

Creating a sense of mission

Mission is still a relatively neglected area of management, and there is no clear agreement on what it encompasses. The Ashridge Strategic Management Centre conducted a 2-year research project designed to fill this gap. The research found that if mission is more clearly defined it can be managed better, and developed a model of mission that includes four elements--purpose, strategy, behaviour standards and values. The project identified companies where, in addition to strong links between these elements, employees also showed an emotional commitment to their company which Campbell has called a 'sense of mission'. This commitment was deepest when there was a match between the employee's values and the company's values.     

Worth a Third Read: Six ANZJFT Readers Remember

If we do not sometimes look back over our shoulders to remind ourselves of the ANZJFT's past achievements, we may forget, and newcomers may never be stimulated to explore earlier contributions for themselves. For this reason, six subscribers were asked to write five hundred words in answer to the question ‘Over the time you have been reading the Journal, what article sticks in your memory the most?’ The one restriction that was placed upon their choice was that if they found themselves unable to choose between two articles, they were to discuss the older of the two, to help assure a wider spread.     

‘Violent’ deaths of children in England and Wales and the major developed countries 1974–2002: possible evidence of improving child protection?

Child protection services are criticised for failing to prevent abuse but demonstrating successful prevention is impossible as it is trying to prove a ‘negative’. The alternative is to examine ‘failures’, i.e. the ‘violent’ deaths of children (0–14 years) to indicate whether matters are improving or deteriorating. This paper uses the latest World Health Organisation data to compare children's ‘violent’ deaths in England and Wales with those in other major developed countries. To account for possible ‘hidden’ under‐reported abuse deaths, undetermined, i.e. ‘other external causes of death’ (OECD) and fatal accidents and adverse events (AAE), deaths are also analysed along with homicides, to compare all ‘violence‐related’ deaths between 1974–76 and 2000–02. England and Wales infant (<1 year) homicide rates were annually 57 per million but fell to 17 per million, a 74% fall. Infant AAE deaths fell in every country with England and Wales falling from 341 per million to 71 per million, a 76% reduction. Both these results were significantly better than those of eight other major developed countries, although England and Wales infant OECD at 26 per million, were high compared to the major developed countries. In the 1970s, combined ‘violent’ deaths of all children (0–14 years) (homicide, OECD and AAE) in England and Wales were 203 per million, they are now 61 per million, a 70% decline with only Italy having lower rates. The worst rates were in the USA which had the highest combined ‘violent’ death rate. These overall results in the major reductions of ‘violence‐related’ deaths in England and Wales can be a boost to the morale of front‐line staff and provide the public with an indication of the progress being made. Copyright © 2008 John Wiley & Sons, Ltd.