A Population Approach to Analysis of Variance Models

Several authors have contributed to what can now be considered a rather complete theory for analysis of variance in cases with orthogonal factors. By using this theory on an assumed basic reference population, the orthogonality concept gives a natural definition of independence between factors in the population. By looking upon the treated units in designed experiments as a formal sample from a future population about which we want to make inference, a natural parametrization of expectations and variances connected to such experiments arises. This approach seems to throw light upon several controversial questions in the theory of mixed models. Also, it gives a framework for discussing the choice of conditioning in models     

Severely Traumatized Siblings: A Treatment Strategy

Siblings who have suffered severe trauma and disrupted attachment relate to one another in ways that interfere with individual development, the chance to benefit from connections with adults, the establishment of healthy sibling relationships, and the working through of traumatic experiences. The authors use case examples to illustrate four distinct sibling patterns: absent, adult lockout, half and half, and trauma shield. The authors highlight the importance of recognizing these types and then varying the therapist's treatment stance to pursue five goals. These include suspending problematic sibling relationships to create room for bonding with caring adults, transferring attachment behaviors and impulses to a receptive adult, resuming healthy individual development, forming more adaptive sibling connections, and expressing shared traumatic content.     

The paradox of multiple elections

Assume that voters must choose between voting yes (Y) and voting no (N) on three propositions on a referendum. If the winning combination is NYY on the first, second, and third propositions, respectively, the paradox of multiple elections is that NYY can receive the fewest votes of the 2³ = 8 combinations. Several variants of this paradox are illustrated, and necessary and sufficient conditions for its occurrence, related to the “incoherence” of support, are given. The paradox is shown, via an isomorphism, to be a generalization of the well-known paradox of voting. One real-life example of the paradox involving voting on propositions in California, in which not a single voter voted on the winning side of all the propositions, is given. Several empirical examples of variants of the paradox that manifested themselves in federal elections – one of which led to divided government – and legislative votes in the US House of Representatives, are also analyzed. Possible normative implications of the paradox, such as allowing voters to vote directly for combinations using approval voting or the Borda count, are discussed. Received: 31 July 1996 / Accepted: 1 October 1996     

Lessons from the trenches in physician integration

Beyond the theoretical basis for integration, three core considerations stand out as the primary reasons for pursuing integration from a physician's perspective. In the authors' experience, the ability to make a case for physician integration stands or falls based on the ability of the integrated delivery system to address these considerations: Gain greater access to capital; develop human resources with talents in managed care and the full spectrum of care services; and sustain an information infrastructure. This article explores the lessons learned in pursuing physician integration.     

Sex preference versus number preference: the case of Korea

The author argues that the effect of sex preference must be disentangled from the effect of number preference in Korea. This study tests--with hazard models--the effect of the number of previous children on the next birth according to the sex composition of previous children. Data were obtained from the 1974 Korean Fertility Survey. This paper also analyzes the timing of childbearing in recent periods in order to determine whether replacement-level fertility is temporary or permanent. The ideal number of children declined from 3.9 children in 1965 to 2.1 in 1991. The age-specific fertility rates for ages 20-24 years declined rapidly during the late 1980s. The fertility rates among women aged 25-29 years and 30-34 years increased during 1985-90. The proportion of fertility among women aged 20-29 years increased from 67.9% in 1975 to 86.6% in 1984. Women born in the late baby boom period of the late 1950s to mid-1960s reached prime reproductive age during the late 1980s and 1990s, but the crude birth rate remained about the same during 1985-92. A higher percentage of women (22.4%) born during 1955-59 remained single in 1990. During 1960-90, the percentage of women aged 20-24 years who were married declined. These trends indicate later age at childbearing and an explanation for the temporary nature of below-replacement fertility in the late 1980s. Korean women did not want to have more than 2 children, and the interval between first and second births increased since 1985. Among pregnancies of parity 2 conceived since 1985, over 90% of women with at least one son ended subsequent pregnancies by abortion compared to only 59% without sons. Hazard models of 1974 data reveal that son preference had an important effect on fertility. Fertility was higher among women with only daughters. Findings suggest that the value of sons must be measured at the societal and not at the individual level.     

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.     

Matching anonymous pre-posttests using subject-generated information

Sensitive research issues call for anonymous questionnaires. This makes accurately matching pretests with posttests difficult or impossible. Various subject-generated coding schemes have been developed, but their accuracy has been unknown. This anonymous study, with 745 students, used subject-generated coding to match pretests with posttests. The matching was verified for accuracy with the use of a collateral, anonymous, sticker identification system. The coding system was able to accurately match 75.2% of all the pretest-posttest pairs. An additional 22.1% of the pairs were left unmatched and only 2.7% were matched incorrectly. Subject-generated coding systems can be very effective where confidentiality is important to protect.