Canonical correlation analysis of residential and vocational outcomes following psychiatric rehabilitation

This analysis uses canonical correlation techniques to explore client outcomes following psychosocial rehabilitation services in two rehabilitation areas: vocational and residential. At issue are the ways in which these two outcomes are affected by a series of eight client characteristics and service delivery features. The overarching question is the effectiveness of the program in establishing independence vocationally and residentially, and whether the same set of factors influences these two outcomes for persons with mental illness. Subjects were 212 ex-clients of a psychosocial rehabilitation agency who were working six months after leaving the program. The analysis derived two canonical functions both of which were significant. Canonical loadings and cross loadings indicated that client level of functioning and program tenure loaded most strongly with residential status on the first canonical variate while education loaded most strongly with salary on the second. These results support the notions that different predictors account for the variance associated with different outcomes following psychosocial rehabilitation. Discussion of the relevance of strong predictor variables highlights ways they can impact program design. Finally, the usefulness of canonical correlation in longitudinal program evaluation research is explored.     

Socio-political forecasting and management information systems

This paper is an attempt to place the forecasting of socio-political variables in the context of actual information needs of industrial companies. Initially discussion is of the effect of socio-political variables upon companies with a review of this significance for decision makers and decision takers. An attempt is then made to categorise existing forecasting techniques in the context of socio-political data whilst regard is paid to the possible effects of socio-political variables on companies. Discussion is then broadened to a consideration of current practice both in the UK and in the USA. Problems implicit in current practice are commented upon and the paper ends with the conclusion that socio-political forecasting is currently significant to many companies and that there is a major potential role for management scientists to play in the development and implementation of appropriate techniques.     

Statistical approaches for conducting network meta-analysis in drug development

We introduce health technology assessment and evidence synthesis briefly, and then concentrate on the statistical approaches used for conducting network meta-analysis (NMA) in the development and approval of new health technologies. NMA is an extension of standard meta-analysis where indirect as well as direct information is combined and can be seen as similar to the analysis of incomplete-block designs. We illustrate it with an example involving three treatments, using fixed-effects and random-effects models, and using frequentist and Bayesian approaches. As most statisticians in the pharmaceutical industry are familiar with SAS? software for analyzing clinical trials, we provide example code for each of the methods we illustrate. One issue that has been overlooked in the literature is the choice of constraints applied to random effects, and we show how this affects the estimates and standard errors and propose a symmetric set of constraints that is equivalent to most current practice. Finally, we discuss the role of statisticians in planning and carrying out NMAs and the strategy for dealing with important issues such as heterogeneity.     

Cross-state variation in Medicaid programs and female labor supply

Using a pooled cross-section data set from the 1980 through 1993 Current Population Survey March Supplements, we test if different Medicaid benefit levels across states impact the labor supply behavior of female heads of households. The ordinary least square (OLS) results support the prediction that Medicaid expenditures reduce labor supply. Controlling for state fixed or random effects alters the effect of both AFDC and Medicaid on the decision to participate as well as the number of hours worked. We also find that while the effects of program generosity are sensitive to the inclusion of state effects those of variation in eligibility thresholds are not.     

Confidence intervals on intraclass correlation coefficients in a balanced two-factor random design

A modified large-sample (MLS) approach and a generalized confidence interval (GCI) approach are proposed for constructing confidence intervals for intraclass correlation coefficients. Two particular intraclass correlation coefficients are considered in a reliability study. Both subjects and raters are assumed to be random effects in a balanced two-factor design, which includes subject-by-rater interaction. Computer simulation is used to compare the coverage probabilities of the proposed MLS approach (GiTTCH) and GCI approaches with the Leiva and Graybill [1986. Confidence intervals for variance components in the balanced two-way model with interaction. Comm. Statist. Simulation Comput. 15, 301–322] method. The competing approaches are illustrated with data from a gauge repeatability and reproducibility study. The GiTTCH method maintains at least the stated confidence level for interrater reliability. For intrarater reliability, the coverage is accurate in several circumstances but can be liberal in some circumstances. The GCI approach provides reasonable coverage for lower confidence bounds on interrater reliability, but its corresponding upper bounds are too liberal. Regarding intrarater reliability, the GCI approach is not recommended because the lower bound coverage is liberal. Comparing the overall performance of the three methods across a wide array of scenarios, the proposed modified large-sample approach (GiTTCH) provides the most accurate coverage for both interrater and intrarater reliability.     

Teaching and research in quantitative methods in university management schools

Much has been written and said about the education and development of operational researchers and management scientists from a specialist departmental viewpoint. Considerably less attention has been devoted to the role of management schools in this process and, more importantly, in their provision of a general education in quantitative methods for all their postgraduate taught course students. This paper aims to make a contribution towards rectifying this relative neglect. Moreover, it specifically contrasts the two sets of activities and argues that they are largely fulfilling different purposes and satisfying in the main different job markets. The paper also addresses some of the problems of management science researchers within a management school milieu.     

Modelling and measurement in retailing practice

The retailing sector has traditionally attracted the attention of economists and marketing specialists but only comparatively recently, at least in the UK, have management scientists become involved. Yet there is much of a measurement and modelling character in retailing to which the management scientist can contribute most usefully. This paper examines two areas of major practical importance to retailers: labour productivity, store location and size. Basic measurement and the establishment of standards can lead to considerable performance improvements in the first area. The second problem area is strategic rather than operational in essence and lends itself to either mathematical modelling or empirical techniques or to a combination of the two approaches.     

The chief executive and his information system

The authors examine the attitudes of British chief executives towards their information systems using recent survey evidence. They discuss the chief executive's individual computation needs and the extent to which he satisfies these personally, his attitudes towards computer-based information and corporate models, and his general informational and analytical requirements. Of particular interest, is the relative contribution as judged by chief executives of intuitive judgement, computer-based analysis and manual analysis respectively to strategic decision-taking; comparative valuations of formal and informal information systems are also ascertained. On the evidence provided by the chief executives, future prospects for computer systems and modelling techniques at strategic level are generally sound although it is difficult to see them achieving the dominance at top managerial level once envisaged by the more optimistic and imaginative management scientists and cyberneticians.     

Children with disabilities and disaster preparedness: a case study of Christchurch

An estimated seven million children with disabilities worldwide are affected by disasters annually. This significant figure emphasises the particular vulnerability of these children in facing natural hazards. However, their needs as well as their capacity and role in disaster risk reduction have largely been overlooked by researchers and policymakers. This paper draws on a case study in Christchurch to identify insights, realities, possibilities and obstacles in relation to the involvement in disaster preparedness of children with diverse disabilities. It reports on findings from focus group discussions and semi-structured interviews with children who have disabilities, their teachers and caregivers to explore children's preparedness and potential responses to a disaster. The findings indicate a considerable variation in how children with disabilities access available resources and perceive, face and cope with natural hazards. This paper shows their potential contribution to disaster preparedness and provides further suggestions for policy and practice.