An evaluation of population projection errors for census tracts

"In this article we evaluate the accuracy and bias of projections of total population and population by age group for census tracts in three counties in Florida. We use [U.S. census] data from 1970 and 1980 and several simple extrapolation techniques to produce projections for 1990; we then compare these projections with 1990 census counts and evaluate the differences. For the total sample, we find mean absolute errors of 17%-20% for the three most accurate techniques for projecting total population and find no indication of overall bias. For individual age groups, mean absolute errors range from 20%-29%." This is a revised version of a paper presented at the 1993 Annual Meeting of the Population Association of America.     

Finite mixture models with concomitant information: assessing diagnostic criteria for diabetes

The World Health Organization (WHO) diagnostic criteria for diabetes mellitus were determined in part by evidence that in some populations the plasma glucose level 2 h after an oral glucose load is a mixture of two distinct distributions. We present a finite mixture model that allows the two component densities to be generalized linear models and the mixture probability to be a logistic regression model. The model allows us to estimate the prevalence of diabetes and sensitivity and specificity of the diagnostic criteria as a function of covariates and to estimate them in the absence of an external standard. Sensitivity is the probability that a test indicates disease conditionally on disease being present. Specificity is the probability that a test indicates no disease conditionally on no disease being present. We obtained maximum likelihood estimates via the EM algorithm and derived the standard errors from the information matrix and by the bootstrap. In the application to data from the diabetes in Egypt project a two-component mixture model fits well and the two components are interpreted as normal and diabetes. The means and variances are similar to results found in other populations. The minimum misclassification cutpoints decrease with age, are lower in urban areas and are higher in rural areas than the 200 mg dl^-1 cutpoint recommended by the WHO. These differences are modest and our results generally support the WHO criterion. Our methods allow the direct inclusion of concomitant data whereas past analyses were based on partitioning the data.     

Ability, disability, and the oldest old

A measure of range of ability is used to profile the 85-years-old-and-older (oldest old) population, including the highly disabled institutional population. This new measure uses two new questions available in the 1990 Decennial Census concerning a self-care limitation and a mobility limitation as well as the usual question concerning a work limitation. In addition to examining the extent of disability among the oldest old, the article examines the extent of care potentially available in the household as well as the economic characteristics of this age group. It is also profiled in terms of relevant personal characteristics, including age, gender, marital status, race, ethnicity, rural residence, education, and employment. A key question addressed is the need for help or care among the oldest old and how various long-term care proposals would meet such needs. A careful analysis of this unique and growing population is necessary to both allay fears of the cost of care or help as well as to dispel stereotypes of this age group as frail and dependent, and in need of institutional care.     

On the shrinkage of local linear curve estimators

Local linear curve estimators are typically constructed using a compactly supported kernel, which minimizes edge effects and (in the case of the Epanechnikov kernel) optimizes asymptotic performance in a mean square sense. The use of compactly supported kernels can produce numerical problems, however. A common remedy is ridging, which may be viewed as shrinkage of the local linear estimator towards the origin. In this paper we propose a general form of shrinkage, and suggest that, in practice, shrinkage be towards a proper curve estimator. For the latter we propose a local linear estimator based on an infinitely supported kernel. This approach is resistant against selection of too large a shrinkage parameter, which can impair performance when shrinkage is towards the origin. It also removes problems of numerical instability resulting from using a compactly supported kernel, and enjoys very good mean squared error properties.     

Planning for productivity

In the 1980s the subject of productivity will receive increasing attention as the old macro economic policies are replaced by micro economic policies. Everyone in various ways will discover the changes which will be involved in learning the real economic facts of life. The need to improve productivity and business performance is urgent and yet it is an area which is being neglected by management.     

The certainty of judgments in health evaluations

Most evaluators seem to presume that all evaluative studies should result in conclusive evidence. Often, however, less than conclusive evidence may not only suffice, but be the only real alternative under conditions of limited evaluation resources. Three levels of evidence common to evaluation studies are discussed: suggestive evidence, preponderant evidence, and conclusive evidence. Ten factors are also presented which can be used to determine the level of certainty appropriate for a given evaluation study. Consideration of these factors enables the evaluator to specify when less than conclusive evidence is acceptable.     

Public opinion and the privatization of welfare: some theoretical implications

The social policy of the Thatcher government is characterized by an abrupt shift in the direction of the private sector. To what extent does this reflect what people want? The Institute of Economic Affairs conclude from the only suitable national opinion survey that such a move is strongly supported. Our reanalysis of their data shows that this strand in public opinion can coexist with, and need not contradict, an equal public enthusiasm for state welfare. Such results have important implications for our understanding of social policy. We conclude, therefore, with a discussion of contrasting marxist and liberal accounts which seeks to show that the evidence of ambivalence in popular attitudes about the welfare state supports particular developments in theory.