Confidence Intervals for Current Status Data

Abstract.  The likelihood ratio statistic for testing pointwise hypotheses about the survival time distribution in the current status model can be inverted to yield confidence intervals (CIs). One advantage of this procedure is that CIs can be formed without estimating the unknown parameters that figure in the asymptotic distribution of the maximum likelihood estimator (MLE) of the distribution function. We discuss the likelihood ratio-based CIs for the distribution function and the quantile function and compare these intervals to several different intervals based on the MLE. The quantiles of the limiting distribution of the MLE are estimated using various methods including parametric fitting, kernel smoothing and subsampling techniques. Comparisons are carried out both for simulated data and on a data set involving time to immunization against rubella. The comparisons indicate that the likelihood ratio-based intervals are preferable from several perspectives.     

Beheimatungsprozesse begleiten — ein Werkstattbericht

Supporting processes of belonging in supervision and coachingThe contemporary employee has to cope with frequent changes. Not only does he lose his familiar environment, he also has to find ways to familiarize himself with new places and to develop a fresh sense of belonging. This process can be understood and facilitated by interpreting the German concept of “Heimat“ as something we have to create ourselves. First experiences demonstrate the usefulness of this approach in coaching processes.     

Expected sample moments of concomitants of selected order statistics

In this paper, the task of determining expected values of sample moments, where the sample members have been selected based on noisy information, is considered. This task is a recurring problem in the theory of evolution strategies. Exact expressions for expected values of sums of products of concomitants of selected order statistics are derived. Then, using Edgeworth and Cornish-Fisher approximations, explicit results that depend on coefficients that can be determined numerically are obtained. While the results are exact only for normal populations, it is shown experimentally that including skewness and kurtosis in the calculations can yield greatly improved results for other distributions.     

TOWARD A SYNTHESIS OF FEMINIST AND DEMOGRAPHIC PERSPECTIVES ON FERTILITY

In explaining fertility and reproduction and emerging patterns of childbearing, both demographers and feminists have centered their thinking on women's status (economic and social), women's changing roles and life experiences (increased labor force participation, increased availability of reproductive options, declining marriage rates in many parts of the industrialized world, and the centrality of women to development), and women as agents in micro- and macrolevel changes in family, fertility, and economic change. Although demography has recently begun to integrate feminist perspectives into fertility explanations, there is not yet a synthesis of feminist theoretical insights with demographic questions. Drawing from recent thinking on global and national political and policy challenges in the less and more developed worlds, to the epistemological shifts in knowledge of reproduction/mothering, to changes in the technologies of reproduction, this article moves toward an integration of feminist and demographic perspectives on fertility.
…far from the economic dependence of women working in the interests of motherhood, it is the steadily acting cause of a pathological maternity and a declining birthrate.
Charlotte Perkins Stetson, Women and Economics , 1899     

Africa's expanding population: old problems,new policies

Sub-Saharan Africa faces an historic challenge: to achieve economic and social progress while experiencing extraordinary population growth. With an estimated 1989 population of 512 million, the 42 countries of sub-Saharan Africa have the highest birth and death rates of any major world region. While death rates have fallen since the 1960s, persistently high birth rates yield annual growth rates above 3% in many countries. The United Nations projects that the region's population will increase 2.7 times by 2025--to 1.4 billion. Throughout the region, population has outstripped economic growth since the mid-1970s. In addition, many African countries are experiencing an epidemic of AIDS (Acquired Immunodeficiency Syndrome). The extent and demographic impact of the epidemic still are unknown, but disturbing social and political effects are already being felt. The region's population growth will slow only when African couples begin to have fewer children. The average number of children per woman ranges from 6 to 8 for most countries. The Africans' preference for large families is deeply rooted in the culture and fed by the perceived economic benefits they receive from their children. Economic stagnation during the 1980s prompted many national governments to recognize that rapid population growth was hindering their socioeconomic development. The political climate has shifted away from pronatalist or laissez-faire attitudes toward official policies to slow population growth. The policy formation process--detailed here for 4 countries (Zambia, Nigeria, Zaire, and Liberia)--is ponderous and beset with political and bureaucratic pitfalls, However, policy shifts in more and more countries combined with evidence of increased contraceptive use and fertility downturns in a few countries give some hope that the region's extraordinary population growth may have peaked and will start a descent. Whatever the case, the decade of the 1990s will be crucial for the future of sub-Saharan Africa.     

India: ‘Brain Drain’ or the Migration of Talent?

2 views on "brain drain" exist: 1) LDCs lose their enormous investments on higher education when skilled people migrate to other countries and 2) LDCs are exaggerating the problem and only a few skilled people migrate at 1 time. India does not completely lose its investment in education when professionals migrate, since the migrants still contribute to knowledge and also send remittances to relatives in India. Unemployed educated people would cause a greater drain on India's resources than educated migrants. The author prefers the phrase migration of talent to brain drain, since the former indicates a 2-way movement. Most migrants from LDCs are students. About 11,000 university graduates leave India every year for advanced study and/or work. A conservative estimate is that 2500 will remain abroad permanently. Most professionals who migrate go to the US and Canada. Factors promoting migration include 1) unemployment, 2) immigration rules, 3) colonial links, 4) financial incentives and material benefits, 5) pursuit of higher education, 6) improvement of working conditions and facilities, 7) avoidance of excessive bureaucratic procedures, and 8) compensation for the mismatch between Indian education and employment. Reasons for returning to India include 1) deference to wives who were unable to adjust to a foreign way of life, 2) contributing to Indian development, and 3) racial discrimination. It will probably not be possible to lure back migrants who left for material reasons. Attractive job offers could entice back those who left for advanced training. To encourage the return of those who left to pursue high quality research, India must 1) increase expenditure on research and development, possibly through the private industrial sector, 2) promote travel to other countries for professional enrichment, and 3) improve conditions of research work. The article concludes with an analysis of migration of talent from 3 perspectives: 1) the individual, 2) the nation-state, and 3) the world as a whole.     

Social choice theory in the case of von Neumann-Morgenstern utilities

Part I of this paper offers a novel result in social choice theory by extending Harsanyi's well-known utilitarian theorem into a multi-profile context. Harsanyi was contented with showing that if the individuals' utilities u _i are von Neumann-Morgenstern, and if the given utility u of the social planner is VNM as well, then the Pareto indifference rule implies that u is affine in terms of the u _i. We provide a related conclusion by considering u as functionally dependent on the u _i, through a suitably restricted social welfare functional (u ₁,...,u _n)u=f(u ₁,...,u _n). We claim that this result is more in accordance with contemporary social choice theory than Harsanyi's single-profile theorem is. Besides, harsanyi's initial proof of the latter was faulty. Part II of this paper offers an alternative argument which is intended to be both general and simple enough, contrary to the recent proofs published by Fishburn and others. It finally investigates the affine independence problem on the u _i discussed by Fishburn as a corollary to harsanyi's theorem.The authors are indebted to L. Haddad, A. Sen and two anonymous referees for useful written comments. They also benefited from stimulating remarks in seminars and helpful conversations with their colleagues. The usual caveat of course applies. One of the authors acknowledges partial financial support from the ARI Communication of the C.N.R.S., Paris.