RELAXING ASSUMPTIONS IN THE ONE SAMPLE t-TEST

This paper reviews what is currently known about the behaviour of the t-statistic when one is no longer sampling from a normal distribution. Suppose Y is a batch of data on which the t-test is performed. Briefly then, heavy-tailed components of Y give a light-tailed t , positive correlation among Y gives a heavy-tailed t, and positively skewed components of Y give a negatively skewed t. The emphasis is on understanding why one gets this type of behaviour, although some numerical tables are presented to illustrate the conclusions.     

Managers as Monitors: An Analysis of the Non‐executive Role of Senior Executives in UK Companies

An important aspect of current governance practice is the use of non‐executive directors to monitor the behaviour of company management. This paper examines the extent to which senior executives are utilized as non‐executives in large UK companies. The results suggest that executive directors are not an important source of non‐executive directors. The average number of non‐executive directorships held by each executive is 0.22. Indeed, 85% of executives hold no additional directorships. The holding of non‐executive directorships is positively related to the strength of board monitoring in the executive's company, executive tenure and company size. Executives in companies with greater growth opportunities and operating in regulated industries are less likely to hold non‐executive directorships.     

Stigma of ink: Tattoo attitudes among college students

We test a structural equations model of stigma against tattooed persons and attitudes toward future tattoos among 195 tattooed and 257 non-tattooed college students. Having tattooed friends and family members undermines stigma against tattooed persons while beliefs about negative side effects of tattooing reinforces stigma assignment. The variables above and the respondent having a tattoo predict attitude toward future tattoos. We test a second model, stigma victimization, drawing on data from the 195 tattooed respondents. While greater tattoo abundance results in greater stigma victimization, respondents with more tattoos also report a greater commitment to their current tattoos and less desire for removal. We discuss results using attitude theory, stigma theory, and the contact theory of prejudice.     

Fertility trends,excess mortality,and the Great Irish Famine

This paper has developed estimates of the age-specific mortality rates prevailing during the Great Irish Famine and has analyzed fertility trends during the 25 years before the Famine. Our calculations confirm that 1 million Irish people perished as a result of this disaster. This figure does not include the deaths among the 1.3 million emigrants who left Ireland during the Famine period. The Famine produced a significant drop in the fertility rate, and we estimate that more than 300,000 births did not take place as a result of the Famine. The effects were especially severe on the very young and the very old, a result echoed in the findings of demographic analyses of other famines. Our procedure permits a reconstruction of the Irish population by age and sex during the period 1821-1841. In addition, it yields year-by-year estimates of the birth rate over this period. We estimate that the rate fell by about 14 percent, a result robust to our assumptions regarding emigration. Economic historians have debated this issue, and we hope that our evidence, although preliminary, will be of assistance. Our analysis also permits year-by-year reconstruction of Irish population totals for the period 1821-1851. Two years are of particular interest. Virtually all recent writers, with the notable exception of Lee (1981), have suggested that the 1831 census returns overestimated the actual population resident in Ireland at that date. Our reconstruction supports the validity of the 1831 census figure. We obtain a total of 7,847,000, which is in good agreement with the disputed census figure of 7,767,000. But perhaps the most interesting figure is the population total for the end of 1845, the highest ever achieved in Ireland. We estimate that the population on the eve of the Great Famine was 8,525,000. Throughout the paper we have tried to highlight those areas in which the data are unreliable, unavailable, or distorted. We have tried to devise cross-checks for consistency and to test the sensitivity of the results to a range of assumptions. A case in point concerns the age-sex profile and volume of emigration to England, Scotland, and Wales. Additional work at the micro level would be helpful here. More solid evidence on Famine births would also be helpful. The parish registers we have sampled certainly provide a clue to trends, but we have only made a start in that respect. A much more comprehensive survey is needed to convey the national picture.(ABSTRACT TRUNCATED AT 400 WORDS)     

New evidence on the fertility transition in Ireland 1880–1911

Recent analyses of Ireland's marital fertility transition based on the Princeton Ig and the Stanford CPA measures are reassessed. Revised county estimates of Ig are subjected to regression analysis, and added insight into CPA is offered by comparing Ireland with Scotland and applying the measure to three specially constructed local data sets.     

Why People Believe They Were Exposed to Biological or Chemical Warfare: A Survey of Gulf War Veterans

The study sought to understand better how people come to believe they have been exposed to biological and chemical warfare. We conducted telephone interviews with 1,009 American veterans (65% response rate) deployed and not deployed to the Gulf War, a conflict during which there were credible threats that such warfare could be used. Only 6% of non-Gulf War veterans reported exposure to biological or chemical warfare, but most of Gulf War veterans reported exposure (64%). The majority of these were unsure whether the exposure was chemical or biological in nature. The most commonly reported exposure indicators were receiving an alert from the military and having physical symptoms. Veterans who were certain of the type of exposure (biological or chemical) were more likely to recall having been told by the military and to recall physical symptoms. Future communications with soldiers and the general public about biological and chemical warfare may need to emphasize the uncertain nature of such risk information. Evaluations of exposure diagnostic technologies should take into account the problem of people initially believing, but not later discounting, false positive results.     

Ecological Bias: Use of Maximum-Entropy Approximations

The focus of geographical studies in epidemiology has recently moved towards looking for effects of exposures based on data taken at local levels of aggregation (i.e. small areas). This paper investigates how regression coefficients measuring covariate effects at the point level are modified under aggregation. Changing the level of aggregation can lead to completely different conclusions about exposure–effect relationships, a phenomenon often referred to as ecological bias. With partial knowledge of the within‐area distribution of the exposure variable, the notion of maximum entropy can be used to approximate that part of the distribution that is unknown. From the approximation, an expression for the ecological bias is obtained; simulations and an example show that the maximum‐entropy approximation is often better than other commonly used approximations.     

Destabilizing Science From the Right: The Rhetoric of Heterosexual Victimhood in the World Health Organization's 2008 HIV/AIDS Controversy

This article examines the 2008 World Health Organization/Joint United Nations Program on HIV/AIDS controversy through original reports and media coverage. Analysis reveals that discourse rhetorically exonerates heterosexuals from HIV/AIDS while reifying homophobic and morally righteous ideology about HIV/AIDS and homosexuality. Discourses of “fraudulent science,” “heterosexual absence,” and reverse victimization destabilize meaning of HIV/AIDS and heterosexuality. “AIDS,” “heterosexuality,” and even victimhood and minority status were destabilized and resignified in a rhetoric that benefited from its status as science even as it rendered past science suspect as ideological.