Ordinal models and generalized estimating equations to evaluate disease severity

Many assays have been carried out in Capsicum spp. in order to evaluate its resistance to Phytophthora capsici , which causes blight and considerable yield loss. An assay aiming at the selection of resistant pepper and bell pepper genotypes to P. capsici was jointly performed in the laboratory of the Phytopathological Clinic of Entomology, Phytopathology and Agricultural Zoology and in the experimental area of the Plant Production Department, both located at ESALQ, University of São Paulo, Brazil. The data set for this assay comes from ordinal categorized random variables, whose analysis does not generally take into account the ordinal nature of the responses, but instead, builds indexes, among other measures, in order to evaluate the resistance of the studied genotypes. This work presents ordinal generalized linear fits in order to evaluate blight severity as well as to identify and select new resources to the pathogen. It also analyses the estimating equations proposed by Liang & Zeger (1986a, b) in order to obtain an infection pattern for the disease. From the fit of the cumulative logit models, valuable genotypes are identified for genetic breeding programs.     

Preparing an Effective Occupational Information Brochure for Ethnic Minorities

This article discusses the rationale for and process of creating and developing an occupational information brochure targeted for ethnic minority students. Minorities need to expand their awareness and knowledge of career options, and few specifically targeted resources now exist. Field testing during the development process showed that a printed brochure answering questions on how to pursue a specific occupation that contains brief biographies of ethnic minority role models, can both inform and inspire. Such a resource can help equalize minority access to career opportunities.     

Expectations of additional children by race,parity, and selected socio-economic characteristics,United States: 1967

This is a study of fertility expectations of wives in relation to selected demographic and social and economic characteristics. The data for this study were obtained from a special survey conducted in 1967 from a probability sample of 30,000 households. The analyzed data show that the number of children expected in the next five years is inversely related to parity. Because of the inverse relationship, the expectations of additional children tend to be inversely related to age at marriage of wife, number of years married, and similar temporal variables. The data show also that there exists an inverse relationship between expectations of additional children and selected socio-economic characteristics, such as education of wife, occupation, and income of husband.     

Pop,Porn, and Rebellious Speech

In Excitable Speech, Judith Butler contends that rebellious speech constitutes a “risk taken in response to being put at risk, a repetition in language that forces change.” With this in mind, this article examines the politics of employing and altering the language and imagery of “porn” in texts and multi-media performances of (post-)feminist (pop-)artists. The discussions about Elfriede Jelinek's novel Lust in the early 1990s exemplify the difficulties associated with transforming the language of pornography into rebellious feminist speech. The text received extensive media attention, but most critics felt ambivalent about Jelinek's attempt to create artificial, repetitious, pornographic speech and questioned the text's ability to foster any kind of “change.” At the beginning of the twenty-first century, the multi-media performances of Charlotte Roche and Reyhan Sahin aka Lady Bitch Ray again triggered discussions about feminism, pornography, body politics, and sexual expression. Their provocative pop-performances use multiple media outlets, TV, music, and electronic media. They are commercially successful and mainstream media understand them as challenging social conventions. This essay critically examines the politics of Jelinek's, Roche's, and Sahin's texts and performances and contextualizes the politics of their rebellious speech within discussions about social roles, gender, and sexuality.     

Non‐Take Up of Social Benefits in Greece and Spain

Even though interest in non‐take up of social benefits is considerable in many European countries, the topic is under‐researched in southern Europe. This article provides preliminary estimates of the extent of non‐take up of two pairs of means‐tested retirement benefits in Greece and Spain. The benefits examined are: (1) the minimum pension supplements pensioner social solidarity benefit EKAΣ and complementos por mínimos; and (2) the social pensions pension to uninsured elderly and pensión de jubilación no contributiva. The article finds that non‐take up of social benefits in the two countries is rather extensive, examines the methodological difficulties inherent in the analysis of non‐take up, and concludes with a discussion of the results and their implications.     

Predictive control of posterior robustness for sample size choice in a Bernoulli model

In this article we consider the sample size determination problem in the context of robust Bayesian parameter estimation of the Bernoulli model. Following a robust approach, we consider classes of conjugate Beta prior distributions for the unknown parameter. We assume that inference is robust if posterior quantities of interest (such as point estimates and limits of credible intervals) do not change too much as the prior varies in the selected classes of priors. For the sample size problem, we consider criteria based on predictive distributions of lower bound, upper bound and range of the posterior quantity of interest. The sample size is selected so that, before observing the data, one is confident to observe a small value for the posterior range and, depending on design goals, a large (small) value of the lower (upper) bound of the quantity of interest. We also discuss relationships with and comparison to non robust and non informative Bayesian methods.