Konfidenzintervalle für den überlappenden Teil zweier Normalverteilungen

Zusammenfassung Der überlappende Teilω zweier Verteilungen wird definiert. Es wird beschrieben wie man für den Spezialfall zweier Normalverteilungen mit gleichen Kovarianzmatrizen Konfidenzintervalle fürω finden kann. Tafeln sind gegeben, von denen man 95% Konfidenzintervalle fürω und für den Parameterλ der nichtzentralenF - Verteilung ablesen kann. Diese Tafeln sind das Ergebnis neuer "exakter" Berechnungen; einige der numerischen Werte nach denen sie gezeichnet wurden sind tabelliert.

---

Summary The overlapping proportionω of two distributions is defined. Methods for finding confidence limits forω are given for the special case of two normal distributions with identical moment matrices. The given graphs are based on new "exact" computations of 2.5 and 97.5 percentage points of the noncentralF - distribution. They may also be used for reading off 955 confidence limits for the noncentrality parameterλ. How to apply the graphs is summarized in section 6 and an example of application is given in section 7. Some of the numerical values on which the graphs are based are tabulated.

---

---

H. Linhart, jetzt im South African Wool Textile Research Institute, Rhodes University Grahamstown, Südafrika. Diese Arbeit wurde im National Institute for Personnel Research, South African Council for Scientific and Industrial Research, Johannesburg ausgeführt.     

The measurement of productivity in the nonmarket sector

In many sectors of the economy, governments either provide various services at no cost or at highly subsidized prices. Examples are the health, education and general government sectors. The System of National Accounts 1993 recommends valuing these nonmarket outputs at their costs of production but it does not give much guidance on exactly how to do this. In this paper, an explicit methodology is developed that enables one to construct these marginal cost prices. However, in the main text, an activity analysis approach is taken in order to simplify the analysis, so in particular, constant returns to scale, no substitution production functions for the specific activities in the nonmarket sector are assumed. It is shown that it is possible to obtain meaningful measures of Total Factor Productivity growth in this framework. An “Appendix” relaxes some of the restrictive assumptions that are used in the main text.     

Argumatics: a text analysis procedure for supporting problem formulation

Problem formulation is the most critical phase of the decision making process. This, particularly in the case of high level multi-stakeholder problems, is not trivial, as the problems do not come “neatly packaged”. The procedure presented in this paper aims to support (i) the exploration of the stakeholders' mental constructs, and (ii) the generation, comparison and synthesis of alternative problem formulations. The suggested procedure — while using the decision analytic approach of the traditional text analysis procedures, follows an inverse, bottom-up direction of analysis: first the individual arguments inherent in the text are explored, then taking them as a starting point, the structures behind the arguments are identified.     

A Conceptual Framework for Quantitative Text Analysis

Quantitative text analysis refers tothe application of one or more methods for drawingstatistical inferences from text populations. Afterbriefly distinguishing quantitative text analysisfrom linguistics, computational linguistics, andqualitative text analysis, issues raised during the1955 Allerton House Conference are used as a vehiclefor characterizing classical text analysis as aninstrumental-thematic method. Quantitative textanalysis methods are then depicted according to a2 × 3 conceptual framework in which texts areinterpreted either instrumentally (according to theresearcher's conceptual framework) orrepresentationally (according to the texts' sources'perspectives), as well as in which variables arethematic (counts of word/phrase occurrences),semantic (themes within a semantic grammar), ornetwork-related (theme- or relation-positions withina conceptual network). Common methodological errorsassociated with each method are discussed. Thepaper concludes with a delineation of the universeof substantive answers that quantitative text analysisis able to provide to social science researchers.     

Are day traders bias free?—evidence from internet stock message boards

This study addresses the issue whether day traders’ recommendations on stocks are biasfree. We test whether on average day traders’ “Hold” sentiment is skewed and different from a neutral opinion. Posted messages and mature text classifier technology provide a novel approach to analyze the content of these “Hold” sentiment postings among day traders. Findings indicate that the self-disclosed “Hold” sentiment conveys an optimistic opinion and significantly differs from neutral. These results help both investors and researchers to better understand day traders’ psychology and behaviors when they recommend stocks. The paper also provides insight into the construction of future online sentiment indexes based on stock message boards.     

Modality analysis: a semantic grammar for imputations of intentionality in texts

Modality analysis is a text analysis methodology that affords comparisons of how people from distinct cultural contexts differ in their accounts of why one or more of their numbers find specific activities possible, impossible, inevitable, or contingent. The technique is built around a two-part semantic grammar, the application of which involves the identification of modal clauses in texts, the classification of these clauses according to their modal forms, and the identification of rationales associated with the clauses’ modalities. We show that with sufficient training the method affords high interrater agreement. After providing a few tips on data-collection strategies, results are presented from a modality analysis of editorials sampled from the Arab newspaper, Al Riyadh, and the Hindi newspaper, Hindustan. The analysis illustrates how modal expressions can be used in locating well-known (e.g., Islamic and Hindu) cultural characteristics from among the vast quantities of discourse that societies continuously generate.     

The Influence of Graphic Techniques in the Evaluation of the Effectiveness of Treatment in Time-Series Design

The objective of this research was to see if the evaluation of the effectiveness of a given treatment through visual inspection depended on the type of graphs used. Three subjects were studied using 3000 graphs (1000 line, 1000 bar and 1000 box-plots), each one representing the results of an A–B design. The results indicate that the subjects committed more errors when the data were presented by line or bar graphs instead of box-plots.     

Problemi di classificazione e connessione in una classe di grafi planari a facce esagonali

Aldo Ruscitti è mancato a Roma il 20 agosto 1978 a soli 39 anni di età. Era stato assistente ordinario e professore incaricato di Istituzioni di Analisi Matematica nella Facoltà di Scienze Statistiche Demografiche e Attuariali dell’Università di Roma. Sin dalla preparazione della tesi di laurea, i suoi interessi scientifici erano stati rivolti alle applicazioni della matematica in campo economico. Nell’ultimo periodo della sua attività si era impegnato in ricerche sulla struttura di particolari classi di grafi, settore nel quale aveva conseguito risultati a livello internazionale. Con la pubblicazione postuma di questo contributo di A. Ruscitti intendiamo rendere un affettuoso omaggio alla memoria di un caro amico che tra i primi aveva voluto entrare a far parte della famiglia dell’AMASES.

---

On the problems of classification and enumeration in a class of 6-valent planar graphs

In this article the author investigates the problems of classification and enumeration of maps with the vertices of degree six and with the faces of cardinality two or three. The graphs in this class are analysed in terms of the maximal number of vertices with degree two they possess on the boundary of their faces. Special emphasis is placed on the problem of the connectivity of these graphs, according with the suggestion of B. Grünbaum and J. Zaks (see [4], p. 112): in particular the author proves that there exist 5-connected graphsG _n in this class with degreen> , for all εN.

     

Computer assisted text analysis in the social sciences

We use the term “Computer Assisted Text Analysis” in a broad sense to refer to a range of current techniques from quantitative social science and content analysis to ‘data mining’ and ‘text classification’, including the analysis of open-ended survey questions, transcribed interviews and speeches, wherever, in fact, the researcher is confronted with data in the form of natural language texts of social scientific interest. These methods are often used in exploratory data analysis, but can also be applied systematically with moderate statistical rigour in the development and testing of hypotheses at various theoretical levels, ranging from the statistics of word usage to changes within or between discourses over time. The general approach is in the tradition of content analysis, by which words which occur together in relatively close proximity in the same context are interpreted as relating to a common theme or concept in the discourse studied. We review a comprehensive set of tools to identify and visualize structures of co-occurrence of words and concepts both within, and in comparing, a number of texts. These produce results not essentially different from those reached by representing word co-occurrences in terms of network analysis or neural network programming using schematic linguistic templates of various kinds. A comparison of the relational data analysis vs. a dictionary-based MDS approach shows that these provide very close if not identical results, despite the fact that the underlying assumptions are frequently represented as different theoretical approaches.     

渌水特大桥的施工技术要点

设计时速为200km/h的浙赣线渌水特大桥,主跨结构形式为42m+2×64m+42m单箱单室预应力混凝土双线连续梁,实体桥墩,桩基础。文章主要介绍了该桥施工的一些关键技术,包括深水基础施工的钢管桩平台和钢板桩围堰技术,基桩施工的溶洞和斜岩处理方法;主梁施工的菱形挂篮施工技术、其液压走行系统以及荷载试验等;主梁0#块施工的水上浮吊及降温养护措施;主梁合龙段施工等。该桥的施工技术和取得的经验可供同类桥梁施工参考。     

一种增长型自组织特征映射文本聚类方法

为建设和谐文明的网络环境,提升对网络不良文本信息的识别和应对能力。文章使用一种新颖的基于增长型自组织特征映射(GSOFM)和潜在语义索引(LSI)相结合方法用于不良文本聚类。这两种算法的结合能够发现全局和局部的模式特点。实验在相同的条件下使用了这种新颖的模式并和单一的GSOFM相比较。实验结果证明:这种新的两种技术的结合与单一的GSOFM方法相比提高了聚类结果的精确性,缩短了计算时间,为网络不良文本聚类提供了一种较好的方法。     

Measuring opinion distributions

In this study it will be argued that the perceived distribution of opinions among others is important for opinion research. Three different ways of measuring the perception of opinion distributions in survey research are compared: (a) by means of a questionwhat most people think about an issue, (b) by means of a questionhow many people are perceived to agree with an issue-statement, (c) by means of ‘line-production-boxes’, a special version ofmagnitude estimation. The results indicate that ‘line-production-boxes’ can improve data quality, but have also some drawbacks which will have to be dealt with. ‘Line-production-boxes’ give a wealth of information about individual differences in the forms of perceived opinion distributions. Although the normal distribution is used often, many other distribution forms are also used. The method of ‘line-production-boxes’ is compared with the method of estimating percentage points. Although high correlations suggest a good concurrent validity, some systematic differences do exist. New research directions are suggested.     

What have we learned from the Smart Machine?

Zuboff's (1988) book In the Age of the Smart Machine: The Future of Work and Power is one of the most celebrated texts among Information Systems researchers. Despite its significant influence, I suggest that it may have a richer story to tell than has been told to date. Motivated by this potential, my essay has two aims: to explicate the theory developed in Zuboff's text, and to determine how fully it has been used and extended by Information Systems researchers, through an analysis of papers citing her text. My findings show that the theory developed in Zuboff's text has been used in a fairly limited and piecemeal fashion. I discuss how this presents a significant opportunity for research because the theory appears to be just as relevant now as it was when the text was published.     

GenD An Evolutionary System for Resampling in Survey Research

The paper is a preliminary research report and presents a method for generating new records using an evolutionary algorithm (close to but different from a genetic algorithm). This method, called Pseudo-Inverse Function (in short P-I Function), was designed and implemented at Semeion Research Centre (Rome). P-I Function is a method to generate new (virtual) data from a small set of observed data. P-I Function can be of aid when budget constraints limit the number of interviewees, or in case of a population that shows some sociologically interesting trait, but whose small size can seriously affect the reliability of estimates, or in case of secondary analysis on small samples. The applicative ground is given by research design with one or more dependent and a set of independent variables. The estimation of new cases takes place according to the maximization of a fitness function and outcomes a number as large as needed of ‘virtual’ cases, which reproduce the statistical traits of the original population. The algorithm used by P-I Function is known as Genetic Doping Algorithm (GenD), designed and implemented by Semeion Research Centre; among its features there is an innovative crossover procedure, which tends to select individuals with average fitness values, rather than those who show best values at each ‘generation’. A particularly thorough research design has been put on: (1) the observed sample is half-split to obtain a training and a testing set, which are analysed by means of a back propagation neural network; (2) testing is performed to find out how good the parameter estimates are; (3) a 10% sample is randomly extracted from the training set and used as a reduced training set; (4) on this narrow basis, GenD calculates the pseudo-inverse of the estimated parameter matrix; (5) ‘virtual’ data are tested against the testing data set (which has never been used for training). The algorithm has been proved on a particularly difficult ground, since the data set used as a basis for generating ‘virtual’ cases counts only 44 respondents, randomly sampled from a broader data set taken from the General Social Survey 2002. The major result is that networks trained on the ‘virtual’ resample show a model fit as good as the one of the observed data, though ‘virtual’ and observed data differ on some features. It can be seen that GenD ‘refills’ the joint distribution of the independent variables, conditioned by the dependent one. This paper is the result of deep collaboration among all authors. Cinzia Meraviglia wrote § 1, 3, 4, 6, 7 and 8; Giulia Massini wrote §5; Daria Croce performed some elaborations with neural networks and linear regression; Massimo Buscema wrote §2.     

The shared reward dilemma on structured populations

In this paper we study the recently introduced “shared reward dilemma” (Cuesta et al. in J Theor Biol 251:253–263, 2008) in the presence of a structure governing the interactions among the population. The shared reward dilemma arises when the prisoner’s dilemma is supplemented with a second stage in which a fixed reward is equally distributed among all cooperators. We first extend our previous results on the equilibrium structure of this game to the case of a one-shot game taking place on a regular network. Subsequently, we consider an evolutionary version of the game on both lattices and random networks. We show that the evolutionary game on graphs exhibits important differences with the case of well-mixed populations. In particular, there exists an important parameter range in which the cooperation is boosted and a single cooperator can invade a population of defectors. We study the dependence of the cooperation levels on the neighborhood size, finding that on random networks the level of cooperation reached decreases as the neighborhood size increases. Moreover, square lattices favor cooperation more than random networks, and on them cooperation may be almost full for certain parameter regions even for large neighborhood sizes. Further, we show that the effect of the population structure is never detrimental for cooperation. We interpret our results in terms of weak versus strong temptation and discuss the nontrivial issues involved in trying to promote cooperation exogenously by means of such a reward mechanism.     

上市公司独立董事业绩考核探析

独立董事业绩考核指标的确定应包括两部分:一是独立董事个人素质的考核指标;二是独立董事个人工作绩效的考核指标。本文探讨了以百分制为基础的“三维一体”的考核体系,希望通过这种考核体系对我国独立董事的业绩考核有所启示。     

上市公司资本结构实证分析——房地产行业实例

房地产业是投资和消费都依靠高负债的典型行业,其资本结构的形成有其自身独有的特征。本文介绍了我国房地产行业的现状,对影响房地产业上市公司资本结构的主要公司特征因素进行了分析,并选择部分房地产业上市公司为样本,运用统计分析方法以及财务分析方法进行相关分析,提出优化房地产业上市公司的资本结构方法与建议。     

Web文本挖掘中模糊聚类的有效性评价研究

本文研究了基于模糊聚类的Web文本挖掘和模糊聚类有效性评价函数,并将其应用于Web文本挖掘中模糊聚类有效性评价。仿真实验表明该方法有一定的准确性和可行性。