Inequalities on partial correlations in Gaussian graphical models containing star shapes

ABSTRACT

This short paper proves inequalities that restrict the magnitudes of the partial correlations in star-shaped structures in Gaussian graphical models. These inequalities have to be satisfied by distributions that are used for generating simulated data to test structure-learning algorithms, but methods that have been used to create such distributions do not always ensure that they are. The inequalities are also noteworthy because stars are common and meaningful in real-world networks.     

A pseudo-complete sample technique for estimation from censored samples

An iterative procedure is presented whereby singly right censored samples are transformed into pseudo-complete samples. This involves the use of order statistics to calculate expected “complete” values of the censored observations. Estimates of the distribution parameters are then calculated by employing standard complete sample estimators. This procedure is applicable to various types of distributions.     

Comparing Two-Stage Segmentation Methods for Choice Data with a One-Stage Latent Class Choice Analysis

Market segmentation is a key concept in marketing research. Identification of consumer segments helps in setting up and improving a marketing strategy. Hence, the need is to improve existing methods and to develop new segmentation methods. We introduce two new consumer indicators that can be used as segmentation basis in two-stage methods, the forces and the dfbetas. Both bases express a subject’s effect on the aggregate estimates of the parameters in a conditional logit model. Further, individual-level estimates, obtained by either estimating a conditional logit model for each individual separately with maximum likelihood or by hierarchical Bayes (HB) estimation of a mixed logit choice model, and the respondents’ raw choices are also used as segmentation basis. In the second stage of the methods the bases are classified into segments with cluster analysis or latent class models. All methods are applied to choice data because of the increasing popularity of choice experiments to analyze choice behavior. To verify whether two-stage segmentation methods can compete with a one-stage approach, a latent class choice model is estimated as well. A simulation study reveals the superiority of the two-stage method that clusters the HB estimates and the one-stage latent class choice model. Additionally, very good results are obtained for two-stage latent class cluster analysis of the choices as well as for the two-stage methods clustering the forces, the dfbetas and the choices.     

Research subjects with limited English proficiency: ethical and legal issues

In this article, we examine Institutional Review Board (IRB) policies, international guidelines, and federal regulations and guidance for dealing with Limited English Proficiency (LEP) research subjects. We show that federal and international guidance concerning this topic is insufficient, and there is considerable variation in IRB policies. While some IRBs have thorough and useful policies, others do not. Many IRBs do not provide researchers and IRB member with answers to several important questions relating to language barriers in research. We recommend that federal agencies, international organizations, IRBs, and researchers take steps to fill in the gaps in guidance and policy to help insure that LEP populations will receive equitable and ethical treatment in research.     

Conventional and expanded adverse childhood experiences (ACEs) and maternal functioning among low-income Black mothers

A paucity of research has examined the individual and cumulative effects of conventional and expanded adverse childhood experiences (ACEs) on maternal functioning, especially among low-income Black mothers. Using self-report data from a subsample of Black mothers (N = 157) who participated in a larger study to evaluate the effectiveness of an urban public prekindergarten program in the mid-Atlantic region of the United States, we examined the prevalence of ACEs and the individual and cumulative effects of conventional (i.e., family trauma and dysfunction) and expanded (i.e., community stressors) ACEs on depression and health among low-income Black mothers. Findings indicated that Black mothers had more exposure to expanded than conventional ACEs. Hierarchical regression analyses revealed that experience of physical neglect was significantly associated with depression and physical abuse with compromised health, and perceived experience of racism was a predictor of depression and compromised health. More conventional and expanded ACEs were associated with clinical levels of depression and compromised health. Findings highlight the need for more research related to the impact of ACEs, especially expanded ACEs, on mental and behavioural health outcomes. Additionally, our findings indicate the need for more trauma-informed care to reduce and address the impact of individual and community-level adversities on low-income Black mothers.     

“We're in this together”: Attachment insecurities,dyadic coping strategies,and relationship satisfaction in couples involved in medically assisted reproduction

Attachment is an important predictor of relationship satisfaction and attachment insecurities are a risk factor for couples under stress. Drawing from the Vulnerability–Stress–Adaptation model, we investigated whether dyadic coping strategies (DCS) would explain the links between attachment insecurities and relationship satisfaction in 97 couples involved in medically assisted reproduction (MAR). Path analyses revealed that for women and men, attachment insecurities (anxiety, avoidance) were associated with their own lower relationship satisfaction through their lower use of positive DCS. Attachment avoidance was also associated with participants' own lower relationship satisfaction through their own lower use of negative DCS. Men's attachment avoidance was also related to their partner's lower relationship satisfaction via their own and their partner's lower use of positive DCS. The findings suggest that promoting the use of positive DCS may be important to preserve relationship satisfaction in couples involved in MAR.     

Much ado about very little: The dubious connection between ethnic minority business policy and ethnic minority entrepreneurship

This article presents a historical reprise of 40 years of policy interest in ethnic minority businesses in the UK. It contrasts the pronouncements of policymakers with the reality of ethnic minority entrepreneurship. Such an exercise is surprisingly rare given the activism of policymakers in this arena and growing scholarly interest in this field. Our historical overview is informed by a novel research method that plots references to ethnic minority entrepreneurship in the British Houses of Parliament. Though the UK has been the site of some interesting policy experiments on ethnic minority entrepreneurship, their impact has been slight when set against the context of broader political-economic change.     

AN ANALYSIS OF BEHAVIOR AND PERFORMANCE IN THE FOOD RETAILING INDUSTRY USING EXPERIMENTAL BUSINESS GAMING

This research tested hypotheses concerning the effects of organizational affiliation, differences among managers nested within organizational affiliation, degree of price competition and selected demographic and psychological traits of managers on economic behavior and performance. Experimental gaming in a behavioral science laboratory was used with a group of 60 subjects who were managers of Indiana supermarkets. The results support the influence of economic factors on the behavior and performance of managers. Degree of price competition imposed by the researchers significantly affected pricing decisions. At the same time, factors not usually considered in the static theory of the firm, such as organizational affiliation, had a significant influence on behavior and performance. While psychological and demographic traits generally did a poor job of explaining manager behavior, their effect may have been masked by the main treatments to which subjects were exposed. Realism in the experiment was not as high as expected, but the approach used was judged to be superior to alternative approaches.     

ADMISSION STANDARDS FOR GRADUATE STUDY IN MANAGEMENT

This paper reports the results of a study undertaken to evaluate the validity of requirements for admission to Florida State University's Graduate Program in Management offered by its School of Business in the Cape Kennedy Area of Florida. A multiple regression study was made using as independent variables students' undergraduate grade point average (UGPA), Graduate Record Examination aptitude test score (GRE), and age (AGE) at time of admission. The dependent variable was graduate grade point average (GGPA). The study revealed a significant positive correlation between GRE and GGPA. The correlation between AGE and GGPA was also significant but was positive for values of AGE up to approximately 29 and negative thereafter. UGPA was not even marginally significant.