Commissioned analysis of surgical performance using routine data: lessons from the Bristol inquiry

The public inquiry into paediatric cardiac surgery at the Bristol Royal Infirmary commissioned the authors to design and conduct analyses of routine data sources to compare surgical outcomes between centres. Such analyses are necessarily complex in this context but were further hampered by the inherent inconsistencies and mediocre quality of the various sources of data. Three levels of analysis of increasing sophistication were carried out. The reasonable consistency of the results arising from different sources of data, together with a number of sensitivity analyses, led us to conclude that there had been excess mortality in Bristol in open heart operations on children under 1 year of age. We consider criticisms of our analysis and discuss the role of statisticians in this inquiry and their contribution to the final report of the inquiry. The potential statistical role in future programmes for monitoring clinical performance is highlighted.     

Shipman's statistical legacy

Harold Shipman, who in January committed suicide in prison, has become notorious the world over as one of the most prolific serial killers of all time. His case has also seriously dented public confidence in doctors. David Spiegelhalter and Nicky Best explain how industrial quality control techniques could be adapted to signal when death rates among a doctor's patients are surprisingly high, and the tricky issues that would arise in implementing such a monitoring system.     

Magnetic Imagery: War‐Related Ribbons as Collective Display*

The collective display of particular symbols represents an emergent form of social movement participation. This study documents the patterns of the collective display of one such symbol; the magnetic war‐related ribbon (WRR). Using bivariate and multivariate analyses of a sample of 8,100 vehicles, we studied the relationships between WRR display and measures of political affiliation, patriotism, and war support. The results find that that WRR display is positively associated with affiliation with George W. Bush and the Republican Party, and various displays of patriotism and war support. This study demonstrates how advents in communication technologies, shifts in the social, economic, and political structures have converged and given rise to a new form of symbolic participation marked by the collective display of cause‐related symbols.     

Epistemological inclusiveness in researching the African American community

Abstract

African American communities have experienced negative effects from a history of medical abuse, lack of proper research procedures, and misinterpretations of study findings because of racism. These past injustices have led to a mistrust of research and researchers. This paper focuses on how some methodological challenges, in a study funded by a National Institutes of Health grant on two low-income African American communities in Kentucky, were mediated through the collaboration of a multi-racial/ethnic team of researchers engaged in cross-disciplinary research. The information for this paper is based on the reflections of key members of the research team. The reflections show that having researchers with different epistemologies resulted in a culturally aware and sensitive study in which emic and etic research approaches were adopted. The inclusion of race-based epistemologies and close community ties were found to be particularly useful in building trust and getting the support of the two communities. However, these outcomes were only possible because research team members provided each other latitude for intellectual freedom and leadership.     

A Latent Growth Curve Analysis of the Structure of Aggression,Drug Use,and Delinquent Behaviors and Their Interrelations Over Time in Urban and Rural Adolescents

Latent growth curve analysis was used to examine the structure and interrelations among aggression, drug use, and delinquent behavior during early adolescence. Five waves of data were collected from 667 students at three urban middle schools serving a predominantly African American population, and from a more ethnically diverse sample of 950 students at four rural middle schools. One set of models focused on changes in individual behaviors; the other on changes in a global problem behavior factor. Models with separate growth trajectories for aggression, drug use, and delinquent behavior provided the best fit for both samples and revealed relations between initial levels of aggression and subsequent changes in the other behaviors. Boys and girls differed in their initial levels of these behaviors, but not their patterns of change. Differences in growth curve trajectories were found across samples. These findings have important implications for assessment and prevention of problem behaviors in adolescents.     

Bayesian measures of model complexity and fit

Summary. We consider the problem of comparing complex hierarchical models in which the number of parameters is not clearly defined. Using an information theoretic argument we derive a measure p _D for the effective number of parameters in a model as the difference between the posterior mean of the deviance and the deviance at the posterior means of the parameters of interest. In general p _D approximately corresponds to the trace of the product of Fisher's information and the posterior covariance, which in normal models is the trace of the 'hat' matrix projecting observations onto fitted values. Its properties in exponential families are explored. The posterior mean deviance is suggested as a Bayesian measure of fit or adequacy, and the contributions of individual observations to the fit and complexity can give rise to a diagnostic plot of deviance residuals against leverages. Adding p _D to the posterior mean deviance gives a deviance information criterion for comparing models, which is related to other information criteria and has an approximate decision theoretic justification. The procedure is illustrated in some examples, and comparisons are drawn with alternative Bayesian and classical proposals. Throughout it is emphasized that the quantities required are trivial to compute in a Markov chain Monte Carlo analysis.     

Management consultants: systems development, power and the translation of problems

This paper aims to shed light on the exercise of power during the development and implementation of organisational information systems. Considering the use of Information Technology (IT) to help solve organisational problems, we employ the concept of the ‘sociology of translation’ to theorise the process by which the organisational problem is constituted and for which the appropriate IT solution is proposed. Discussing the nature of the power relationship between external management consultants in IT and client or user organisations, the paper considers the role of symbolic resources such as managerial discourse, and the differential access to IT knowledge and skills, as important aspects of power in that relationship.