An analytic method for randomized trials with informative censoring: Part 1

Consider a randomized trial in which time to the occurrence of a particular disease, say pneumocystis pneumonia in an AIDS trial or breast cancer in a mammographic screening trial, is the failure time of primary interest. Suppose that time to disease is subject to informative censoring by the minimum of time to death, loss to and end of follow-up. In such a trial, the censoring time is observed for all study subjects, including failures. In the presence of informative censoring, it is not possible to consistently estimate the effect of treatment on time to disease without imposing additional non-identifiable assumptions. The goals of this paper are to specify two non-identifiable assumptions that allow one to test for and estimate an effect of treatment on time to disease in the presence of informative censoring. In a companion paper (Robins, 1995), we provide consistent and reasonably efficient semiparametric estimators for the treatment effect under these assumptions. In this paper we largely restrict attention to testing. We propose tests that, like standard weighted-log-rank tests, are asymptotically distribution-free -level tests under the null hypothesis of no causal effect of treatment on time to disease whenever the censoring and failure distributions are conditionally independent given treatment arm. However, our tests remain asymptotically distribution-free -level tests in the presence of informative censoring provided either of our assumptions are true. In contrast, a weighted log-rank test will be an -level test in the presence of informative censoring only if (1) one of our two non-identifiable assumptions hold, and (2) the distribution of time to censoring is the same in the two treatment arms. We also extend our methods to studies of the effect of a treatment on the evolution over time of the mean of a repeated measures outcome, such as CD-4 count.     

A non-parametric index of tracking

SUMMARY A two-sample version of the non-parametric index of tracking for longitudinal data introduced by Foulkes and Davis is described. The index is based on a multivariate U -statistic, and provides a measure of the stochastic ordering of the underlying growth curves of the samples. The utility of the U -statistic approach is explored with two applications related to growth curves and repeated measures analyses.     

Fit and Skill in Employee Selection: Insights from a Study of Headhunters

We draw upon evidence from a qualitative study of headhunters to provide insights into the character and importance of candidate fit and skill for the selection of a broad range of white-collar employees. Headhunters suggest that the fit of a job candidate is assessed at two levels, one corresponding with a general compatibility with organization-level norms, culture, and strategy, the other corresponding more closely with traits and characteristics of the person or persons with whom the job candidate actually interviews. Skill—a factor which is largely neglected by those who tout the importance of fit—also plays an important and independent role in employee selection. Stalls that influence the selection of employees from a pool of candidates tend to be highly specific if not idiosyncratic, and take the form of what headhunters call hot buttons. We conclude by discussing the conceptualization, causes, and implications of fit; we also consider how the importance of fit and hot buttons challenges the explanatory logic of standard accounts of labor-market success.     

The Effects of Diversity on Small Work Group Processes and Performance

Diversity is an increasingly important factor inorganizational life as organizations worldwide becomemore diverse in terms of the gender, race, ethnicity,age, national origin, and other personal characteristics of their members. The exact impact ofwithin-group diversity on small group processes andperformance is unclear. Sometimes the effect ofdiversity seems positive, at other times negative, andin other situations, there seems to be no effect at all.In this article, we suggest that these types of findingsmight be explained by using agroup-development model to examine theimpact of diversity on group processes and performance. Our modeluses concepts from Jackson et al.'s (1995), Milliken andMartins' (1996), and other models, as well as our ownconcepts, to show how diversity affects group development and performance. Among the conceptsincluded in the model are readily detectable personalattributes, underlying personal attributes, cognitiveparadigm dissimilarity, cognitive costs and rewards, diversity management skills, group behavioralintegration, and cognitive performance resources. In thepages that follow, we will explain each of thecomponents of the model and suggest specific hypotheses generated from the model.     

Arrow theorems in mixed goods, stochastic, and dynamic economic environments

The original Arrow Theorem and many variants were stated with the Universal Domain assumption; but in economic situations, natural assumptions like monotonicity restrict the domain so that the Theorem does not apply. Since 1979, several authors have proved Arrow-type impossibility results in situations such as models with public goods or private goods; and a few have considered mixed-goods or stochastic alternatives models. This paper has similar results in models with mixed-goods, stochastic, and dynamic alternatives; the objects of preference can have any two features or all three. With suitable qualifications, the impossibility result continues to hold, as does the Arrow-inconsistency of arbitrarily small domains type of result I have established elsewhere.     

Re-Visioning Attention Deficit Hyperactivity Disorder (ADHD)

Constructionist notions have become commonplace in theoretical discussions of the self, but are seldom translated into consideration of specific social work practice concerns such as ADHD. Explorations of ADHD, on the other hand, typically emphasize a narrow, medically-oriented symptom picture that is devoid of the psychosocial context in which the so-called symptoms emerge. A transactional approach to the understanding of ADHD is advanced. This article promotes a link between constructionism and social work's psychosocial or person-in-environment perspective. Such a perspective supports approaches to the assessment of ADHD that illuminate larger cultural messages and their constraining influence on individual meaning-making. Intervention, conducted at multiple levels, must be geared to the establishment of more hopeful and affirming narratives.     

The birds and the bees: interactive graphics and problem solving in the teaching of statistics

Software which allows interactive exploration of graphical displays is widely available. In addition there now exist sophisticated authoring tools which allow more general textual and graphical material to be presented in computer-based form. The role of an authoring tool in providing a graphical interface to a strategy for solving simple statistical problems in the context of teaching is discussed. This interface allows a variety of resources to be integrated. Specific examples, including the use of dynamic graphical displays in exploring data and in communicating the meaning of a model, are proposed. These ideas are illustrated by a problem involving the identification of the sex of a herring gull.     

The design of organizations and the right to act

Recent innovations in the structure of formal organizations suggest possible directions for the design of schools to bring about high achievement. The structure of output-driven in contrast to administratively-driven schools is described, and designs are described which address both the goal of high achievement and the goal of reduced inequality.An earlier version of this paper was presented as the author's Sorokin Lecture at the annual meeting of the Eastern Sociological Society, Boston, March 1993.     

Comment on 'facts and artifacts in the study of intra-uterine mortality: a reconsideration from pregnancy histories' by henri léridon(1)

Abstract Extract I have suggested that at a given birth order the probability of having a further pregnancy is greater when the last pregnancy had been spontaneously aborted than when it resulted in a birth.(2) Léridon,(3)in the course of a valuable paper on foetal wastage, presents data which, according to him, impugn my suggestion. I would like to question his claim.     

The corporate energy policy: A management planning perspective

The energy problems facing the world have been receiving increasing attention in the press and in business journals. This article examines the attitudes of 224 U.S. business executives toward the energy crisis and examines the role of a corporate energy policy in minimizing the economic impact of future energy price increases and/or shortages. A plan for a corporate energy policy is proposed.