Batch sampling to improve power in a community trial. Experience from the Pawtucket Heart Health Program

Experiments involving large social units, such as schools, work sites, or whole cities, are commonly limited in statistical power because the number of randomized units is small, leaving few degrees of freedom for residual (between-unit) error. The authors describe a method for increasing residual degrees of freedom in a community experiment without substantially increasing cost or difficulty. In brief, they propose that the experimental units should be divided into random subsamples (batches). Batch sampling can improve statistical power if the community endpoint means are stable over time or if their temporal variation is comparable in period to the batch-sampling schedule. The authors demonstrate the theoretical advantages of the batch system and illustrate its use with data from the Pawtucket Heart Health Program, in which such a design was implemented.     

Summing up. Recommendations and experiences for evaluation of community-level prevention programs

This article provides recommendations and observations about evaluation of a locally based prevention project to reduce problems at a total community or aggregate level. The shift from targeting specific individuals or subpopulations to the overall structure and environment of a community is most demanding. Evaluation tools and analysis techniques have lagged behind program development because community-level interventions are not linked to a specific target group who can be separately studied. Thus assumptions about using random assignment and/or comparison communities as means to control for confounding variables are weakened when the unit of analysis is the community itself and dependent measures are subject to trending and the effects of history.     

The minds of a medical director

This article is offered in a nod to all those readers who have been exposed to "whole brain" theory, either through the American College of Physician Executives or elsewhere. As managers struggle with balancing the "left brain" and "right brain" aspects of their work, the author says, they might consider exploiting a third area of activity, or inactivity--the "no brain." This center position can be especially effective in dealing with the high-technology aspects of delivering health care.     

A study on mortality rates and expectation of life at birth in demography]

An "age-time-area diagram" (referred to as a-t diagram) which is used as the basis for discussing different used and applications of variously defined mortality rates, as well two kinds of measurements for life expectancy is proprosed. The proposal is built upon the Lexis diagram. The a-t diagram is used to define a new way of measuring child mortality, projecting population, and proposing a formula for measuring successive and nonsuccessive life expectancy.     

The Quality of Urban Environments in the Brazilian Amazon

In the Brazilian Amazon during the 1980s,urban population growth outstripped rural growth, andby 1991, most of the region's population resided inurban areas. Much of this urban growth involvedestablishment of unplanned housing with inadequateinfrastructure, which resulted in rising pollution. This paper compares indicators of environmentalquality in urban populations of the Amazon in 1980 and1991, and among different kinds of urban populationsin 1991. The results show that environmental qualityin the region deteriorated during the 1980s as theproduction of and exposure to environmental hazardsrose while resources to ward off hazards eroded. Thefindings also show that environmental quality wasparticularly poor in more rapidly growing urbancenters. The urban Amazon may not afford an adequatestandard of living and this may generate out-migrationfrom the region.