Identifying rational distributed lag models using a joint test applied to the corner table

Often a distributed lag response pattern can be usefully represented in rational polynomial form. When the impulse response function decays, the corner table may be useful for model identification if appropriate statistical tests may be done. One or more joint tests are called for since use of the corner table involves studying groups of its elements. We consider an asymptotic x2 statistic that permits joint tests. We report simulation results showing that the distribution of this statistic follows the x ² distribution, for certain sample sizes and degrees of freedom, well enough to be useful in practice. With two data sets we illustrate how this statistic can be a useful aid when using the corner table.     

From fun to fraught: marketing to kids and regulating “risky foods” in Canada

ABSTRACT

In an era of industrialized food production, ultra-processed foods, “Big Food” marketing, and growing obesity rates, food has come to be framed as an object of risk – and as an object of regulation. Such reframing has fascinating implications related to issues of responsibility and decision making, especially when it comes to children’s food. This article probes the relationship between representation, regulation and “risky” consumption with respect to children’s food. I examine how child-targeted foods become framed as “risky” and what counts as “risky” food messaging under Health Canada’s commitment to restrict the marketing of unhealthy foods to children. Detailing the tension between food as a risk object and food as a child object, I suggest how issues of semantic provisioning and the politics of the unseen work to complicate and destabilize the (seemingly) straightforward process of prohibiting unhealthy food marketing to children.     

Teaching Ethics in a Statistics Curriculum with a Cross-Cultural Emphasis

Like most professional disciplines, the ASA has adopted ethical guidelines for its practitioners. To promote these guidelines, as well as to meet governmental and institutional mandates, U.S. universities are demanding more training on ethics within existing statistics graduate student curricula. Most of this training is based on the teachings of Western philosophers. However, many statistics graduate students are from Eastern cultures (particularly Chinese), and cultural and linguistic evidence indicates that Western ethics may be difficult to translate into the philosophical concepts common to students from different cultural backgrounds. This article describes how to teach cross-cultural ethics, with emphasis on the ASA Ethical Guidelines, within a graduate-level statistical consulting course. In particular, we present content that can help students overcome cultural and language barriers to gain an understanding of ethical decision-making that is compatible with both Western and Eastern philosophical models. Supplementary materials for this article are available online.     

Guinea Pigs on the payroll: The ethics of paying research subjects

Regulatory bodies and scholars have traditionally conceptualized biomedical research on healthy subjects in the same way as research on patients. Guidelines and regulations have portrayed payment to a healthy subject as a potential constraint, or “undue influence,”; on the subject's free consent. In this essay we suggest an alternative way of conceptualizing research on healthy subjects, which sees the basic issue not as one of undue influence but as one of justice. Healthy subjects generally enroll in research protocols not for humanitarian reasons but for the money they will receive. Many of these protocols are conducted by profit‐driven corporations. Yet current guidelines and regulations prohibit subjects from negotiating for fair payment for the risks, discomforts and inconveniences they undergo, and IRBs are not staffed adequately to monitor the subject's safety. We propose to remedy the situation by regulating payment to healthy subjects as a labor relation.     

Family assets,postsecondary education,and students with disabilities: Building on progress and overcoming challenges

Students with disabilities are increasingly enrolling and participating in two-year, four-year, and other institutions of higher education. Federal policies and initiatives addressing the educational needs of students and adults with disabilities provided impetus for these increases. For example, mandates within the Individuals with Disabilities Education Act (2004) have resulted in K-12 public schools increasingly preparing students for postsecondary education. Nonetheless, students with disabilities continue to face financial challenges as well as low educational expectations in their pursuit of postsecondary education. Family assets may provide a framework for addressing these challenges and provide specific implications for policy as well as educational practice.     

The value of event history techniques for understanding social processes: Modelling women's employment behaviour after motherhood

Over the last two decades there has been an increase in the longitudinal data available to social scientists, and this has been accompanied by the development of concepts and tools which allow for a rigorous approach to empirical research. However, there is still an appreciable gap between the methodological innovations within the field of applied statistics and the everyday practice of the majority of social scientists. The aim of this paper is therefore to demonstrate some of the advantages of using event history data to underpin our understanding of social processes. In particular, the paper explores the benefits of using SABRE (Software for the analysis of binary recurrent events, developed at the University of Lancaster) as a tool for carrying out event history analysis. The specific advantage of this software is that it allows the researcher to focus on duration effects or temporal dependencies in the social process under investigation. The substantive focus of the paper is the way in which women manage to combine paid employment with motherhood. Analyses are based on data from women's life histories, collected as part of the fifth sweep of the National Child Development Survey carried out in 1991. Within this paper, the primary focus is on the conceptual issues raised by modelling event history data; statistical terminology and notation has been kept to a minimum.     

The structural roots of food insecurity: How racism is a fundamental cause of food insecurity

Rates of food insecurity skyrocketed during the COVID-19 pandemic, doubling overall and tripling among households with children. Even before the pandemic, the rate of food insecurity in the United States was “unusually high” compared to other rich democracies, and rates have not improved substantially over the last 25 years. What explains the lack of progress in addressing food insecurity? This article maps out an overview of the experiences, causes, and consequences of food insecurity in the United States. We demonstrate that racism is a fundamental cause of food insecurity, both because racism contributes to racial disparities in income and wealth, and because racism is linked to food insecurity independent of poverty and socioeconomic status. For example, people of color are more likely to experience racial discrimination, which is associated with food insecurity, and to live in states where stricter regulations and harsher punishments are tied to social assistance programs, including food assistance programs. Because racism is a fundamental cause of food insecurity, eliminating it requires going beyond “just” eliminating poverty. Instead, the fundamental cause must be tackled directly: racism itself, which is built into the structure of American society and entrenched in its institutions.     

An algorithm for the design of factorial experiments when the data are correlated

Since the development of methods for the analysis of experiments with dependent data, see for example Gleeson and Cullis (1987), the design of such experiments has been an area of active research. We investigate the design of factorial experiments, complete and fractional, for various dependency structures. An algorithm for generating optimal or near optimal designs is presented and shown to be useful across a wide range of dependency structures.