Domains of convergence for the EM algorithm: a cautionary tale in a location estimation problem

The EM algorithm is a popular method for maximizing a likelihood in the presence of incomplete data. When the likelihood has multiple local maxima, the parameter space can be partitioned into domains of convergence, one for each local maximum. In this paper we investigate these domains for the location family generated by the t-distribution. We show that, perhaps somewhat surprisingly, these domains need not be connected sets. As an extreme case we give an example of a domain which consists of an infinite union of disjoint open intervals. Thus the convergence behaviour of the EM algorithm can be quite sensitive to the starting point.     

The psychodynamically oriented clinical social worker as sports consultant: A preliminary report

This paper explores an unusual and innovative application of psychodynamically oriented clinical social work method to the sports area. The coach of a national Olympics team requested a clinical consultation because he suspected that there might be psychosocial reasons why a certain number of world class atheletes he was coaching were not performing up to their full potential.     

Correlates of female crime

This article discusses the complexity of developing correlates of female crime in the comparative context of Western and Indian literature. It selectively reviews the findings of American and Indian studies of female crime and concludes with the author’s own findings from a study of 120 women prisoners conducted in a federal women’s prison in India. The author’s main contention is that whereas broad contours of offender profiles can be drawn, it is difficult to draw statistically significant relationships and infer from them predictable variables of criminality.     

Cognitive and behavioral therapies for pathological gambling

The purpose of this paper is to provide an overview of behavioral and cognitive treatment approaches in the management of pathological gambling disorders. Disappointingly, the literature to date contains only one controlled outcome study in which two differing behavioral techniques were compared. Although research in general has focussed on identifying the nature of cognitive distortions in gambling, findings from these studies have not been systematically translated into treatment programs. It is concluded that methodological limitations including small sample size, absence of control groups, multiple concurrent interventions and poorly defined outcome criteria preclude conclusive statements to be drawn regarding the active ingredient of either behavioral or cognitive strategies. The program offered within the Impulse Disorders Research Centre is outlined.The authors wish to gratefully acknowledge the assistance and contribution of Zachary Steel, Research Assistant, in the preparation of this paper.     

Reducing U.S. carbon dioxide emissions: an assessment of different instruments

The possibility that carbon dioxide emissions from fossil fuel use might lead to global warming has become a leading environmental concern. Many scientific and environmental organizations have called for immediate action to limit carbon dioxide production. For the most part, however, public debate has focused on a single policy instrument: a carbon tax applied to fossil fuels in proportion to their carbon content. We present a detailed model of the U.S. economy and use it to compare carbon taxes with two other instruments that could achieve the same reduction in carbon dioxide emissions: a tax on the energy content of fossil fuels (a BTU tax) and an ad valorem tax on fuel use. We find that carbon taxes can achieve a given reduction with the least overall effect on the economy, but with a large effect on coal mining. Energy taxes are fairly similar to carbon taxes but have slightly less impact on coal mining and slightly greater overall cost. In contrast, ad valorem taxes fall much more lightly on coal mining but have a much greater effect on the economy as a whole.     

Clinical Writing of a Therapy in Progress: Ethical Questions and Therapeutic Challenges

Clinical implications and ethical dilemmas of the use of confidential case material in clinical writing are examined, including a review of the discourse among professionals who publish clinical work. This literature is applied to a clinical illustration of psychotherapy with a client who gave consent for publication and read the clinical write-up of her case material. It is suggested that clinical writing may increase client “self-reflection” if there is a “secure base” of attachment between therapist/author and the client. The impact on the client’s treatment process is examined, in addition to a discussion of ethical questions and professional recommendations. ²Dr. Susanne Bennett is an Assistant Professor, National School of Social Service of the Catholic University of America. Dr. Bennett is also a psychotherapist in private practice in Falls Church, VA.     

Immigrants' Language Skills and Visa Category1

This article is concerned with the determinants of English language proficiency among immigrants in a longitudinal survey for Australia. It focuses on both visa category and variables derived from an economic model of the determinants of destination‐language proficiency among immigrants. Skills‐tested and economic immigrants have the greatest proficiency shortly after immigration, followed by family‐based visa recipients, with refugees having the lowest proficiency. Other variables the same, these differences disappear by 3.5 years after immigration for speaking skills; and although they diminish, they persist longer for reading and writing skills. The variables generated from the model of destination‐language proficiency (such as schooling and age at migration) are, in part, predictions of visa category, but they are more important statistically for explaining proficiency.     

Why Did House Members Vote for H.R. 4437?1

This article examines why members of the U.S. House of Representatives voted for H.R. 4437, the controversial 2005 bill to construct a 700‐mile immigration barrier along the U.S.‐Mexican border and to criminalize illegal presence and aid to undocumented immigrants. Logit analysis suggests that being a first‐term House member or a Republican and representing a district that was in the South or the West or heavily blue‐collar substantially boosted the odds of supporting H.R. 4437. If a member's district was disproportionately Asian, Latino, or, especially, African American, he or she was instead more likely to oppose the measure.