DETECTION AND TESTING OF DIFFEFENT TYPES OF OUTLIER IN LINEAR STRAUCTURAL RELATIONASHIPS

The linear structural model provides one way of modelling a linear relationship between two random variables. It is well known that problems of unidentifiability arise for unreplicated observations and normal error structure. As in all data sets, outliers can arise and methods are needed for detecting and testing them. An outlier-generating model of mean–slippage type can be used to characterise four different forms of outlier manifestation. It is interesting to find that the unidentifiability problem provides no obstacle for detecting or testing the outliers for three of the four forms. Detection principles, and specific discordancy tests, are derived and illustrated by application to some data on physical measurements of Pacific squid.     

Public relations in hospital

In this paper, the authors have dealt with the salient features of public relations function in a hospital situation while providing health care services to the patients. Public relations is an important function to build up corporate image of the hospitals in the minds of the public and the patients. The authors, therefore, suggest that proper attention may be paid to this aspect for greater appreciation of the services by the community at large.     

Fit,Flexibility and Performance in Manufacturing: Coping with Dynamic Environments

This research develops the notion of environmental fit and flexibility and illustrates the importance of such fit empirically using survey data from 101 manufacturing firms. Two dimensions of environmental dynamism are identified and the fit between them and different approaches to flexibility are assessed. Hierarchical regressions provide evidence that flexibility is a stronger predictor of performance in more dynamic environments. Specifically, presence of the unpredictability or the volatility aspects of environmental dynamism each warrant the use of different types of manufacturing flexibility strategies. Statistical results are interpreted with the caveat that while implemented capability must be used to study performance effects, this study uses perceived importance scales for flexibility.     

Household size and the poisson distribution

Household size distributions for 104 countries are examined. It is shown that a Poisson distribution truncated at zero can be used to derive models of household size distribution. An improved fit is obtained by adding a linear term to the truncated Poisson model. This distribution depends only on average household size which in turn is shown to be related to modified dependency ratios. This method can be used for comparisons of household size distributions across nations and for long-term forecasting.     

Wo lernen Kinder mit sonderpädagogischem Förderbedarf besser? Ein Vergleich schulischer Kompetenzen zwischen Regel- und Förderschulen in der Primarstufe

Promoted by the UN Convention on the Rights of Persons with Disabilities, there is a trend towards the inclusive education of students with special educational needs (SEN) in regular classrooms. The present study addresses the question if achievement differences emerge between SEN students who attend a regular primary school and those who attend a school for special education. Based on data from the IQB-Ländervergleich Primarstufe 2011, a national assessment in German primary schools, the achievement of SEN students in regular schools (n?=?658) was compared to the achievement of students in special schools (n?=?413). Propensity score matching was applied to control for differences in achievement related characteristics between the two groups. After matching, SEN students in inclusive educational settings showed significantly higher test scores in German reading and listening comprehension as well as in mathematics than comparable SEN students in special schools. The effects were more pronounced for students with a special need of learning support than for students with speech and language-related special education support. Possible explanations for the higher achievement of SEN students in regular schools and for differential effects with regard to type of SEN are discussed.     

The Eric Garner Case: Statewide Survey of New York Voters’ Response to Proposed Police Accountability Legislation

The Eric Garner case was unique because this police-induced death was caught on video from before the moment of physical confrontation. A mixed-methods representative household survey and Garner's arrest video were used to determine NYS voters’ opinions (n = 119) about police indictment and Governor Cuomo's request for expanded authority. Respondents were asked whether the officers should face indictment, shown the arrest video, and then asked again about indictment. Prior to the video, a majority of respondents (n = 86; 57.4%) believed involved officers should have been indicted. After viewing, the proportion increased by 13.7%. A majority supported Cuomo's call for expanded authority to appoint a special prosecutor in cases where police are involved in civilian deaths. Study limitations include prior exposure to the footage and a low response rate. NYS voters generally supported Cuomo's proposal for appointing a special prosecutor; however, a quarter of respondents disagreed with the method of reform and expressed a: 1) preference for every case to go to trial; 2) preference for a case-by-case basis; or 3) distrust in state-appointed special prosecutors. This research could inform discussions regarding proposed system reforms. Future research with a less well-circulated video is needed to determine the extent to which videos of police-induced deaths affect public opinion.     

Obtaining Informationally Consistent Decisions When Computing Costs with Limited Information

We demonstrate the need to view in a dynamic context any decision based on limited information. We focus on the use of product costs in selecting the product portfolio. We show how ex post data regarding the actual costs from implementing the decision leads to updating of product cost estimates and potentially trigger a revision of the initial decision. We model this updating process as a discrete dynamical system (DDS). We define a decision as informationally consistent if it is a fixed‐point solution to the DDS. We employ numerical analysis to characterize the existence and properties of such solutions. We find that fixed points are rare, but that simple heuristics find them often and quickly. We demonstrate the usefulness and robustness of our methodology by examining the interaction of limited information with multiple decision rules (heuristics) and problem features (size of product portfolio, profitability of product markets). We discuss implications for research on cost systems.     

Nonparametric bootstrap of sample means of positive-definite matrices with an application to diffusion-tensor-imaging data analysis

This paper presents nonparametric two-sample bootstrap tests for means of random symmetric positive-definite (SPD) matrices according to two different metrics: the Frobenius (or Euclidean) metric, inherited from the embedding of the set of SPD metrics in the Euclidean set of symmetric matrices, and the canonical metric, which is defined without an embedding and suggests an intrinsic analysis. A fast algorithm is used to compute the bootstrap intrinsic means in the case of the latter. The methods are illustrated in a simulation study and applied to a two-group comparison of means of diffusion tensors (DTs) obtained from a single voxel of registered DT images of children in a dyslexia study.