Strong consistency of least squares estimates with i.i.d. errors with mean values not necessarily defined

We establish strong consistency of the least squares estimates in multiple regression models discarding the usual assumption of the errors having null mean value. Thus, we required them to be i.i.d. with absolute moment of order r, 0<r<2, and null mean value when r>1. Only moderately restrictive conditions are imposed on the model matrix. In our treatment, we use an extension of the Marcinkiewicz–Zygmund strong law to overcome the errors mean value not being defined. In this way, we get a unified treatment for the case of i.i.d. errors extending the results of some previous papers.     

Creating Organisational Strength from Operationalising Restrictions: Welfare Non-profit Organisations in the Russian Federation

VOLUNTAS: International Journal of Voluntary and Nonprofit Organizations - The work of non-profit organisations (NPOs) in non-democratic country contexts tends to be judged on their contribution to...     

Loose women or lost women? The re-emergence of the myth of white slavery in contemporary discourses of trafficking in women

This article compares current concerns about “trafficking in women” with turn of the century discourses about “white slavery.” It traces the emergence of narratives on “white slavery” and their re-emergence in the moral panics and boundary crises of contemporary discourses on “trafficking in women.” Drawing on historical analysis and contemporary representations of sex worker migration, the paper argues that the narratives of innocent, virginal victims purveyed in the “trafficking in women” discourse are a modern version of the myth of “white slavery.” These narratives, the article argues, reflect persisting anxieties about female sexuality and women's autonomy. Racialised representations of the migrant “Other” as helpless, child-like, victims strips sex workers of their agency. The article argues that while the myth of “trafficking in women”/”white slavery” is ostensibly about protecting women, the underlying moral concern is with the control of “loose women.” Through the denial of migrant sex workers' agency, these discourses serve to reinforce notions of female dependence and purity that serve to further marginalise sex workers and undermine their human rights. An earlier version of this paper was presented at the International Studies Association Convention, Washington D.C., February 16–20, 1999, and is available on-line at www.walnet.org/NSWP.     

Relationships Between Candidate Self-Monitoring, Perceived Personality, and Selection Interview Outcomes

A study into the relationships between candidateself-monitoring ability, interviewer perceptions ofcandidate personality, and interviewer outcome decisionsin the context of actual graduate recruitment interviews (n = 130) is presented. Detailedpsychometric norm data is also reported on the Lennoxand Wolfe (1984) revised Self-Monitoring (RS-M) scale,together with the results of confirmatory factoranalyses into the factor structure of this measure. Itwas found that candidate self-monitoring ability wasonly moderately and nonsignificantly related tointerviewer outcome evaluations, and thatself-monitoring was generally uncorrelated with thepositiveness of recruiter impressions of candidatepersonality. Confirmatory factor analyses revealed thata two correlated factor structure for the RS-M scale, inaccordance with the original authors' formulation,provided the most parsimonious fit. Norm data for theRS-M scale is reported for this sample of Britishgraduates, including item statistics, item to subscale,item to scale correlations, and internal reliabilitycoefficients. Implications for future research intocandidate impression management, self-monitoring,interviewer decision making, and the practicalimplications arising from these findings arediscussed.     

Distributive Justice Evaluations in Two Cultural Contexts: A Comparison of U.S. and South Korean Teachers

The justice literature suggests, but has nottested, a positive relationship between met expectationsabout multiple workplace rewards and distributivejustice evaluations (the individual's assessment of whether s/he has been treated fairly). Datafrom samples of teachers in South Korea (N = 649) andthe U.S. (N = 810) are used to examine thisrelationship. In addition, U.S.-South Korea culturalvalue differences in individualism, seniority, and hierarchicalauthority are the basis for hypothesizing that certainreward-specific met expectations will be linkeddifferently to justice evaluations across the twosocieties. As hypothesized for both societies, the moreone's expectations about job-related rewards are met,the greater the perception of just treatment. Also ashypothesized, several societal differences based on cultural differences are found. Metexpectations about autonomy are more important inexplaining justice evaluations in the U.S., whereas metexpectations about advancement opportunities are moreimportant in South Korea.     

Parameter estimation in high dimensional Gaussian distributions

In order to compute the log-likelihood for high dimensional Gaussian models, it is necessary to compute the determinant of the large, sparse, symmetric positive definite precision matrix. Traditional methods for evaluating the log-likelihood, which are typically based on Cholesky factorisations, are not feasible for very large models due to the massive memory requirements. We present a novel approach for evaluating such likelihoods that only requires the computation of matrix-vector products. In this approach we utilise matrix functions, Krylov subspaces, and probing vectors to construct an iterative numerical method for computing the log-likelihood.     

Assessing Overweight,Obesity, Diet,and Physical Activity in College Students

Abstract

The authors surveyed 738 college students aged 18 to 27 years to assess overweight, obesity, dietary habits, and physical activity. They used BMI (body mass index) > 25 kg/m² or BMI > 85th percentile and BMI > 30 kg/m¹ or BMI > 95th percentile to estimate overweight and obesity in those aged < 19 years. To define overweight and obesity in those > 20 years, they used BMI > 25 kg/m² and > 30 kg/m². They found overweight rates of 21.6% using BMI directly and 16.2% using BMI percentile and obesity rates of 4.9% using BMI directly and 4.2% using BMI percentile. More than 69% of the participants reported < 5 servings of fruits and vegetables per day and more than 67% reported < 20 g of fiber per day; participants reported physical activity on fewer than 3 d/wk. Most college students are not meeting dietary and physical activity guidelines, suggesting the need for prevention interventions and increased understanding of overweight in college students.