Regression of area mortality rates on explanatory variables: what weighting is appropriate?

"One can often gain insight into the aetiology of a disease by relating mortality rates in different areas to explanatory variables. Multiple regression techniques are usually employed, but unweighted least squares may be inappropriate if the areas vary in population size. Also, a fully weighted regression, with weights inversely proportional to binomial sampling variances, is usually too extreme. This paper proposes an intermediate solution via maximum likelihood which takes account of three sources of variation in death rates: sampling error, explanatory variables and unexplained differences between areas. The method is also adapted for logit (death rates), standardized mortality ratios (SMRs) and log (SMRs). Two [United Kingdom] examples are presented."     

The administrative costs of non-profit health insurers

Interest in the efficiency or inefficiency of non-profit firms has spawned research on the administrative costs of Blue Cross and Blue Shield plans. Relying on plausible implications of the property rights theory of the firm, both Blair, Ginsburg, and Vogel (1975) and Vogel (1977) noted some evidence of inefficiency in these firms. Our analysis, however, utilizing their models and more recent data, reveals little convincing evidence for the view that Blue Shield plans are inefficient.     

Out-migration and ethnic communities

"Comparative analysis of out-migration [in the United States]...reveals substantial ethnic differentials. Part of the variation results from group compositional differences in social class and other characteristics normally related to migration, particularly age, education and local birth. Equally important, however, are indicators of social and economic bonds." The data concern 3,345 adults who were first interviewed between 1967 and 1969 in Rhode Island and were reinterviewed in 1970, 1971, and 1979. "The results suggest that ethnic groups characterized by a dense network of social and economic ties do not sponsor out-migration, which has been the emphasis of many past studies of chain migration and migrant assimilation. Rather, they deter out-migration by providing alternative opportunities within the ethnic community."     

The aims of population statistics and demographic research

A detailed program for the improvement of population statistics and for the development of demographic research is presented, with particular reference to the USSR. Topics covered include global and regional population projections, special surveys on demographic behavior, and the need for improvements in migration data.     

Contraceptive behavior among unmarried young women: A theoretical framework for research

Adoption of the most effective methods of contraception requires individual decision-making and negotiation with contraceptive providers. In order to take account of both behavioral elements, a two-dimensional framework for understanding contraceptive adoption and continuation by unmarried young is proposed, incorporating a "social-psychological model" of individual decision-making and an "interpersonal model" of factors affecting provider-client interaction. The social-psychological model is based on an earlier value-expectancy theory of behavior motivation as applied to health-related behaviors. The interpersonal model is derived from conflict-bargaining perspectives on professional-client interaction; it is suggested that expectations for this interaction are based on a limited number of internalized "models": the "professional"; the "bureaucratic"; the "commercial"; and the "parental." Insofar as client and professional "models" disagree, communication may break down and client understanding and/or acceptance of provider advice cannot be assured. The components of the social-psychological and interpersonal models are described in detail, and a combined framework is proposed.