Considerations for optimal nonparametric regression under a generalizederror structure

Nonparametric smoothing, such as kernel or spline estimation, has been examined extensively under the assumption of uncorrelated errors. This paper addresses the effects of potential correlation on consistency and other asymptotic properties in a repeated-measures model, using directly optimized linear smoothers of the replicate means. Unrestricted optimal weights, with respect to squared error loss, are used to confirm a lack of consistency for all linear estimators in an autocorrelated errors model. The results indicate kernel methods that work well for an uncorrelated errors model may not have the ability to perform satisfactorily when correlation is introduced, due to an asymmetry in the optimal weights, which disappears for an uncorrelated errors model. These would include data-driven bandwidth selection methods, adjustments of the bandwidth to accommodate correlation, higher-order kernels, and related bias reduction techniques. The analytic results suggest alternative approaches, not considered here in detail, which have shown merit.     

Chain ratio type estimator for ratio of two population m3ans using auxiliary characters

In this paper we have proposed chain ratio type estimators for ratio of two population means using two auxiliary characters. The expressions for bias and mean square error of these estimators have been derived. A comparison of the proposed estimator with that of double sampling estimator has been made in terms of mean square error. An emperical study has also been made.     

On the total sojourn time of particles in semi-markov compartmental system with branching particles

We consider a semi-Markov compartroental system with branching particles, Me study the total sojourn time of all the particles and obtain the asymptotic behaviour of its mean. We also discuss some special systems.     

A Preliminary Investigation of a Telephone Administration of the Quality of Marriage Index

Follow‐up data collection presents many challenges for longitudinal research. Validating paper‐and‐pencil assessments for use via telephone may alleviate these issues. This study evaluates psychometric properties of the Quality of Marriage Index (QMI; Norton, 1983, Journal of Marriage and the Family, 45, 141) when administered by telephone and compares scores with the paper‐and‐pencil version. Participants included women with major depressive disorder and dyadic discord and their male spouses (n = 24 couples). Results suggest excellent scale reliability for the verbal QMI. However, a significant mean difference was found: participants scored on average 3 points higher on the telephone‐administered QMI than on the written QMI. Recommendations for future research and clinical implications are discussed.     

The Disclosure Panacea: A Comparative Perspective on Charity Financial Reporting

This article examines the charity financial reporting regimes of three common law jurisdictions: Ireland, the UK and the US. It assesses whether these respective disclosure models improve either nonprofit behaviour or enforcement odds. Three core aspects of the regimes are reviewed: the reliability of the disclosed information, the consistency of such information and its ability to facilitate comparison between charities, and the level of enforcement arising from disclosure. Particular attention is paid to oversight mechanisms, including audits, and their rates of effectiveness in the regulation of charities. The article examines ongoing efforts to reform broader international accounting standards and considers the impact such moves are likely to have at both regional and national level for charity accountability. It concludes that given the markedly different spheres in which for-profits and nonprofits operate, care should be taken in modelling charity disclosure regimes on those developed for for-profit entities.     

Violence in the nursing profession: Occupational and lifestyle risk factors in Swedish nurses

Abstract

In a national study of the work environment, physical, and mental well-being of more than 2600 Swedish nurses, 30% reported having experienced violence at work. Possible association between violence and a range of occupational, demographic, and lifestyle characteristics were studied. Stepwise multiple linear and logistic regressions were used to further examine risk factors for violence. Occupational factors with significant correlations to workplace violence were nursing discipline (type of ward or facility), years of work experience, supervisory responsibilities, night work, work dissatisfaction, work-related musculoskeletal injury, and frequency of patient handling. Demographic/lifestyle factors related to violence were age, gender, smoking, coffee consumption at work, and use of alcohol to relax after work. The best fit linear regression model explained 17% of the variance in violence, 13%, of the variance in threat of violence. The logistic regression model confirmed an increased risk of violence and threats in psychiatric and geriatric settings. However, much remains unexplained about the aetiology of violencc in health carc settings. This report provides the basis for a pilot intervention study currently in progress.     

TMR: An Automated System for Managing Revenue

Abstract

The Total Medical Record (TMR) system used by the Division of University Health Services at Duke University is an integrated medical and management information system. One module supports the financial needs of the division. To facilitate managerial performance, TMR automatically prints insurance claims, refund statements, revenue summary data, service utilization, itemized visit statements, monthly patient bills, dunning letters, and has a host of unique features that aid management with controlling the private fees generated by the University Health Services. In addition, the servicing of prepaid programs is accommodated, and the splitting of charges between prepaid and fee-for-service programs occurs automatically.     

Making Meanings,Meaning Identity: Hmong Adolescent Perceptions and Use of Language and Style as Identity Symbols

Using qualitative interview data gathered from 28 Hmong adolescents, we examined the meaning ascribed to language and style and how language and style behaviors are used to distinguish identity. We found that the participants used language and style to define their own ethnic group membership and cultural identities. Moreover they inferred meaning from these identity behaviors to discern which peer groups are desirable (those who wear American style clothing and are bilingual) and which are of low social status (“fobby” style clothing and monolingual). The cultural identity symbols used by participants reveal heterogeneity among Hmong adolescent peer groups and evolving definitions of what it means to be Hmong in America.     

Grading with norm-referenced or criterion-referenced measurements: To curve or not to curve,that is the question

Assigning grades is an integral and everyday part of social work education. However, social work educators, especially those teaching the academically-based as opposed to practice-based courses, must decide whether to use norm-referenced or criterion-referenced measurements to grade exams and other assignments. Norm-referenced measurement is commonly called grading on a curve in higher education. While grading on the curve is not obsolete in academia, I have eliminated it in my courses. New and perhaps experienced social work educators may benefit from a review of both grading methods. This article examines both sides of a grading issue relevant to the wider context of higher education and, therefore, relevant to social work education. Grading with norm-referenced or criterion-referenced measurements is reviewed along with issues related to both types of grading. I will describe why I grade with criterion-referenced measurement and why I believe it is a better choice for social work education.