Bayesian Poisson models for the graphical combination of dependent expert information

A supra-Bayesian (SB) wants to combine the information from a group of k experts to produce her distribution of a probability θ. Each expert gives his counts of what he thinks are the numbers of successes and failures in a sequence of independent trials, each with probability θ of success. These counts, used as a surrogate for each expert's own individual probability assessment (together with his associated level of confidence in his estimate), allow the SB to build various plausible conjugate models. Such models reflect her beliefs about the reliability of different experts and take account of different possible patterns of overlap of information between them. Corresponding combination rules are then obtained and compared with other more established rules and their properties examined.     

The Demand for Immigration to the United States

This paper examines trends and cross-national variation in the active demand for immigration to the United States in the period of 1984–1993, using data from the Visa Office and various other sources. The analysis is restricted to legal immigration in numerically limited categories. The results show that the total number of active immigrant visa applicants steadily increased in the aggregate and in each of the preference categories. Moreover, the active demand for immigration was highly skewed, with the majority of applications coming from a dozen countries: Mexico, the Philippines, India, mainland China, South Korea, Taiwan, Vietnam, the Dominican Republic, El Salvador, Jamaica, Hong Kong, and Pakistan. Most of these highly-backlogged countries displayed a significant increase in the growth rate of demand for immigration. The paper also shows a substantial cross-national variation in the active demand for immigration and explores its structural determinants. The regression results indicate that the level of economic development in sending countries and U.S. economic and cultural relations with sending countries play important roles in the determination process. Policy implications of the findings are also discussed.     

CUSUM method in predicting regime shifts and its performance in different stock markets allowing for transaction fees

Statistical Process Control (SPC) is a scientific approach to quality improvement in which data are collected and used as evidence of the performance of a process, organisation or set of equipment. One of the SPC techniques, the cumulative sum (CUSUM) method, first developed by E.S. Page (1961), uses a series of cumulative sums of sample data for online process control. This paper reviews CUSUM techniques applied to financial markets in several different ways. The performance of the CUSUM method in predicting regime shifts in stock market indices is then studied in detail. Research in this field so far does not take the transaction fees of buying and selling into consideration. As the study in this paper shows, the performances of the CUSUM when taking account of transaction fees are quite different to those not taking transaction fees into account. The CUSUM plan is defined by parameters h and k. Choosing the parameters of the method should be based on studies that take transaction fees into account. The performances of the CUSUM in different stock markets are also compared in this paper. The results show that the same CUSUM plan has remarkably different performances in different stock markets.     

Invariant distributions of the multivariate tests in the skew elliptical model

This paper gives the conditions for the invariance of the null distributions of the normal theory tests for the linear restriction on the location parameters in the family of the matrix variate skew elliptical distributions. Main properties of the Hotelling’s generalized statistic in this family are investigated.     

Methods for eliciting aetiological clues from geographically clustered cases of disease, with application to leukaemia–lymphoma data

The nearest neighbour analysis method has been developed to determine whether a disease case may be regarded as being unusually close to other neighbouring cases of the same disease. Using this method, each disease case is classified as spatially 'clustered' or 'non-clustered'. The method is also used to provide a test for global clustering. 'Clusters' are constructed by amalgamating geographically neighbouring clustered cases into one contiguous 'cluster area'. This paper describes a method for studying differences between clustered and non-clustered cases, in terms of case 'attributes'. These attributes may be person related, such as age and sex, or area based, such as geographical isolation. The area-based variables are subject to geographical correlation. The comparison of clustered and non-clustered cases may reveal similarities or differences, which may, in turn, give clues to disease aetiology. A method for studying 'linkage' or similarities in attributes between cases that occur in the same clusters is also described. The methods are illustrated by application to incidence data for leukaemias and lymphomas.     

Philanthropy without borders: US private foundation activity in Eastern Europe

Worldwide disillusionment with governmental problem-solving, decline in governmental resources, increasing prominence of multinational corporations, and the collapse of communism act as powerful stimuli to international philanthropic activity. US private foundations in particular have been highly motivated by the collapse of communism to act as venture capitalists in seeking grant-making opportunities and philanthropic partners in Eastern Europe. International philanthropy of private foundations can provide expertise in and resources for global as well as regional or local problem-solving. However, resources available must be viewed realistically. This paper puts available foundation resources in perspective. Further, international philanthropy by private foundations is no panacea for the world's problems, and may only be effective at the margins. But to the extent it can be an effective problem solver, it should not be artificially limited by boundaries and laws of any one nation, as it is at present. While reviewing some trends towards increasing activity of larger US private foundations in Eastern Europe, this paper also illustrates small segments of the existing legal, tax and other barriers to international philanthropy. In many instances, simple awareness of some of these barriers will enable potential grantees and philanthropic partners to surmount these barriers. But within the larger context of globalisation of philanthropy, all such barriers to the free movement of philanthropic capital and expertise should be identified and ultimately removed so that international philanthropy, like international trade and free movement of capital and goods, can emerge to an optimal level.Susan Flaherty is a partner in the law firm of Roha & Flaherty, 1900 L. Street N.W., Washington, DC, 20036-5002.     

AIDS and college health: knowledge, threat, and prevention at a northeastern university

We performed secondary analyses on data originally collected by telephone from a random sample of 294 undergraduates from a large northeastern university to examine students' knowledge about acquired immunodeficiency syndrome (AIDS) and the students' reactions to the health threat posed by human immunodeficiency virus (HIV). Our findings indicated that students are reasonably well informed about AIDS, are aware of the recommended precautions for avoiding HIV infection, and are fearful that the virus may spread within the student population. These data also show that students are reluctant to change their sexual behavior unless the threat of infection is personalized. The implications of our findings for future research are briefly discussed.     

Estimation of nonlinear errors-in-variables models: an approximate solution

We propose an easy to derive and simple to compute approximate least squares or maximum likelihood estimator for nonlinear errors-in-variables models that does not require the knowledge of the conditional density of the latent variables given the observables. Specific examples and Monte Carlo studies demonstrate that the bias of this approximate estimator is small even when the magnitude of the variance of measurement errors to the variance of measured covariates is large. Cheng Hsiao and Qing Wang's work was supported in part by National Science Foundation grant SeS91-22481 and SBR94-09540. Liqun Wang gratefully acknowledges the financial support from Swiss National Science Foundation. We wish to thank Professor H. Schneeweiss and a referee for helpful comments and suggestions.     

Some understandings about the population development of the minorities in China]

China is a Socialist country which is composed of numerous ethnic groups. In addition to the Han people, there are 55 minorities in various parts of China. Since liberation (1949), the lives of the minorities have improved greatly. There has also been reasonable advancement in their local economic situation, cultural and educational establishments, and health care, and the population growth among ethnic minorities has also increased rapidly. At the present time, the rate of population growth among the minorities is extremely high, and the age structure of the minority population is young. The custom of early marriage and having children at a young age is still popular. The levels of economic development, cultural and educational establishments and medical and health care are still too low to satisfy current needs of the local people. Within a short period of time, population growth among the minorities may reach among climax, and the problem of overpopulation may become more serious. This new trend is not encouraging for the economic and cultural development of the minority people. In order to protect the economic situation of the minority population, various rules and regulations should be established according to local situations, and work in family planning and birth control is also urgently needed for the minorities.     

Correctly understand and use the measures of progress of the family planning program]

It is necessary to understand correctly the measures of progress in the accomplishments of family planning work. From a developmental and historical perspective the primary measures are constantly in flux. In the last decade, the criteria used to assess the progress have ranged from the natural rate of growth to the birth rate, to multiple-child rate, and to the planned family rate, all of which reflect different emphasis in the various stages of family planning work. They also show a tendency toward making planning work more scientific. None of the criteria is flawless, however. For instance, the planned family rate can be influenced by the total number of births. When that number increases, it can cause the planned family rate to decrease; or, when the number of births decreases, the planned family rate can increase. The measures used for assessing the accomplishments of family planning work only reflect individual aspects of the work; it can never reflect the totality of family planning work because the scope is so vast, encompassing virtually all levels and organizations of society.