A modified random-effect procedure for combining risk difference in sets of 2×2 tables from clinical trials

Summary Meta-analyses of sets of clinical trials often combine risk differences from several 2×2 tables according to a random-effects model. The DerSimonian-Laird random-effects procedure, widely used for estimating the populaton mean risk difference, weights the risk difference from each primary study inversely proportional to an estimate of its variance (the sum of the between-study variance and the conditional within-study variance). Because those weights are not independent of the risk differences, however, the procedure sometimes exhibits bias and unnatural behavior. The present paper proposes a modified weighting scheme that uses the unconditional within-study variance to avoid this source of bias. The modified procedure has variance closer to that available from weighting by ideal weights when such weights are known. We studied the modified procedure in extensive simulation experiments using situations whose parameters resemble those of actual studies in medical research. For comparison we also included two unbiased procedures, the unweighted mean and a sample-size-weighted mean; their relative variability depends on the extent of heterogeneity among the primary studies. An example illustrates the application of the procedures to actual data and the differences among the results. This research was supported by Grant HS 05936 from the Agency for Health Care Policy and Research to Harvard University.     

Improving the contributions of technology assessment to the health care system of the U.S.A.

Summary Based on 14 case studies of highly effective therapies and the reasons they succeeded less frequently than they could, we propose a variety of steps to improve the health care system of the U.S.A. Whatever proposal emerges from current national debates until innovations are shown to be safe and effective, they should not be supported; when slightly better technologies are much more expensive than other good ones we need to consider appropriate choices carefully; simplified billing and bookkeping would reduce our costs; when a technology is rapidly introduced cautionnary measures may be needed; tracking immunization and repairing their omissions requires a new system; educational programs such as seen effective in hypertension should be applied in other areas such as vaccination; in organ transplantation the nation should consider “presumed consent”; our payment system sometimes creates perverse incentives and therefore needs review; and the preferences of the public in allocation of health resources need to be discovered once the public is informed about the issues. Research supported by Andrew W. Mellon Foundation.     

Economic Reform in the Czech Republic: Economic Strain,Depression, Hostility,and the Difference Gender Makes*

The Czech Republic is changing rapidly and its current economic transformation is a strain on Czech families. In this study, the connection between economic strain and individual well-being is investigated via mailed questionnaires from 234 households in the Czech Republic. For Czech women, depression rises more with economic strain than does hostility, while Czech men become more hostile than depressed in the face of economic strain. For women, social support is a buffer between economic strain and hostility, whereas self-esteem is a buffer for depression. For men, both self-esteem and social support exacerbate hostility in the context of economic strain.     

Effects of Category Order on Answers in Mail and Telephone Surveys1

Abstract Past research suggests that mail surveys encourage a primacy effect, which is a tendency to choose the first answers from a list, whereas telephone surveys encourage a recency effect, a tendency to choose the last answers from a list. This paper summarizes results from 82 new experiments conducted in 12 separate surveys in seven states. Only four of 33 mail survey comparisons exhibited significant primacy effects, while five of 26 experiments in telephone surveys exhibited recency effects. In addition, only three of 23 cross-method comparisons produced a significant primacy/recency effect in the expected manner. The conclusion is that the prevalence of primacy and recency effects has been over-estimated by past research and a new theoretical approach that takes into account multiple causation is needed for examining these effects.     

Tearoom trade: A research update

Conclusion Like many studies of covert deviance, this paper is based upon a captive sample of persons who have come to the attention of law enforcement agencies. The existence of Laud Humphreys' research, however, makes possible a comparison of police generated data with data obtained through observations and interviews with unapprehended offenders. Because police observations were so detailed, a rare opportunity to replicate a qualitative study presented itself. This research largely substantiates the picture drawn by Humphreys in his classic study,Tearoom Trade: Impersonal Sex in Public Places. Consistent with his observations, most tearoom participants (a) communicate through non-verbal gestures and seldom speak, (b) do not associate outside the tearoom or attempt to learn one another's identity or exchange biographical information, (c) do not use force or coercion or attempt to involve youths or children, (d) are primarily heterosexual and married, (e) depart separately with the insertor leaving first, (f) commit their sex acts out of sight of the entrance and accidental exposure, (g) do not undress or engage in anal sex, (h) break off sexual contact when someone enters the washroom, (i) rarely approach straight men, (j) read and write sexually explicit homosexual graffiti, and (k) linger inside and outside the washroom for someone to appear. In addition, (1) fellatio is generally not reciprocated and fellators are usually older men; (m) most offenders are neat in appearance; (n) some engage in series and simultaneous encounters; (o) encounters are brief, usually not exceeding twenty minutes; and (p) few have criminal records with the exception of those previously convicted of similar offenses.The behavior of players reveals remarkable consistency over time, from community to community, and across national boundaries. Many men, the majority of them married and primarily heterosexual, continue to visit out-of-the-way public washrooms in search of fast, impersonal, and exciting sex despite the risk to family, friends, job, and reputation. Although shopping malls have usurped public parks as the favorite locale of tearoom participants, the basic rules of the game and profile of the players—as Humphreys contends—remain the same over time and place.     

Setting health priorities: a review of concepts and approaches

The setting of health priorities is primarily concerned with the equitable distribution of resources and is now more than ever an important part of strategic planning within the National Health Service (NHS). The basic information which can be used to assist in such decision-making and the process by which different agencies become involved are important aspects of priority-setting; this article is based on a major review of the research literature on these aspects and provides a discussion and an analysis of experience within health and other fields. From this material a number of possible approaches to priority-setting are identified and discussed. The article concludes that, before it can be decided how priorities should be set in the future, outstanding questions about how far rational approaches are feasible, about who is to be involved and what role they should play, and about how far such decisions are to be taken nationally or locally will need further consideration.     

Disability at the intersections

Complete and accurate understandings of stratification depend on more regular consideration of disability. To build sociologists' recognition of disability as a socially constructed axis of stratification, we first demonstrate the construction of the disability category through classic legitimating processes: moral attributions, biological attributions, separation, and dichotomization. Expanding understandings of basic processes of stratification, we then document the centrality of disability in the social construction of class, race, gender, sexual orientation, and age. Finally, we show various ways disability functions as an axis of stratification in intersection with other key axes of stratification.     

The burdens of social capital: How socially-involved people dealt with stress after Hurricane Katrina

Research shows that those with greater social capital enjoy better physical and mental health. The current study illuminates a paradox of social capital which may afflict those involved in traumatic events. Several years of survey data reveal a dynamic picture of the link between social capital and stress following Hurricane Katrina. Results reveal that initially after Katrina, those who were more socially embedded carried the greatest load with respect to helping the displaced population, thus experiencing more stress. But over time, the most socially-involved then snapped back from their stressful experiences more rapidly than isolates. This confirms that over the course of stressful events, social involvement first exposes people to more stress, but as time passes, provides them a significant buffer against negative psychosocial experiences.     

A search of maximum generalized resolution quaternary-code designs via integer linear programming

Quaternary-code (QC) designs, an attractive class of nonregular fractional factorial designs, have received much attention due to their theoretical elegance and practical applicability. Some recent works of QC designs revealed their good properties over their regular counterparts under commonly used criteria. We develop an optimization tool that can maximize the generalized resolution of a QC design of a given size. The problem can be recast as an integer linear programming (ILP) problem through a linear simplification that combines the \(k\)- and \(a\)-equations, even though the generalized resolution does not linearly depend on the aliasing indexes. The ILP surprisingly improves a class of \((1/16)\)th-fraction QC designs with higher generalized resolutions. It also applies to obtain some \((1/64)\)th-fraction QC designs with maximum generalized resolutions, and these QC designs generally have higher generalized resolutions than the regular designs of the same size.     

Analysis of supersaturated designs via the Dantzig selector

A supersaturated design is a design whose run size is not enough for estimating all the main effects. It is commonly used in screening experiments, where the goals are to identify sparse and dominant active factors with low cost. In this paper, we study a variable selection method via the Dantzig selector, proposed by Candes and Tao [2007. The Dantzig selector: statistical estimation when p$p$ is much larger than n$n$. Annals of Statistics 35, 2313–2351], to screen important effects. A graphical procedure and an automated procedure are suggested to accompany with the method. Simulation shows that this method performs well compared to existing methods in the literature and is more efficient at estimating the model size.