Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PHYSICA-VERLAG GMBH & CO  

In this paper, we produce two projects and their results for statistical quality control on the web. The first system named DLLQC: Dynamic Link Library for Statistical Quality Control, is a statistical software library system with the DLLs. The second system named EBQC: Electronic Books for Quality Control, is an e-book system on the Web. Both systems, which can be used freely through the internet, have many contents with the DLLs of statistical analysis and PDF files of e-books.

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：PHYSICA-VERLAG GMBH & CO  

We propose a method that finds target groups such that. the response probability of a dichotomous dependent variable is larger than a pre-specified target value. This is enabled by a selection of independent variables with high order interactions. The method is effective to extract interesting patterns from datasets. We developed software for this method. The software incorporates various types of tools Eke data management, model building, visualization, and so on.

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (other academic)   Publisher：Japanese Society of Computational Statistics  

Statistical softwares are used for a variety of purposes. Naturally, demands for software vary according to the purpose of users. For educational use, it is not necessary to have many options and elaborate output. On′the other hand, softwares for research and practical use need to meet many kinds of the users′ demands, and hence many option and applicability for further analysis and presentation would be desirable for such softwares. The currently marketed software, however, does not satisfy all the varying demands of users since it is very difficult to create such software. In this paper, to overcome the difficulty, we propose a new approach to make a statistical software and introduce our project called DLLSA(Dynamic Link Library for Statistical Analysis). The purpose of this project is to DLLize various source programs written in several programming languages for statistical analysis and turn them into a library. This means that individual users will make the interface for input/output according to their needs and working environments while using this DLL as a statistical engine. There are many application softwares for the Windows system that can call the DLL. It is also easy to DLLize program sources written in common programming languages such as Basic, C/C++, Fortran, and Pascal. All contents of our library can be downloaded freely from the DLLSA web site.

DOI： 10.20551/jscswabun.13.2_115

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (scientific journal)   Publisher：Japanese Association For Mathematical Sociology  

     Connectivity is the index of social network analysis that deals with network data, and has been measured so far by tracing the adjacent relations between nodes. This algorithm is equivalent to the method called depth first search in the field of computer science. It is known that this algorithm is so efficient for detection of the depth of the data that has graph structure. Through taking advantage of Path theorem in graph theory and the nature of diameter of graph, however, it is possible to measure connectivity by simple matrix operation. In this study we present algorithm for measurement of connectivity based on matrix operation, and after demonstration of the algorithm using few examples we define connectivity as graph theoretical terms.

DOI： 10.11218/ojjams.14.2_119

CiNii Article

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

CiNii Article

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：English   Publishing type：Research paper (international conference proceedings)   Publisher：NOVA SCIENCE PUBLISHERS  

researchmap

Language：Japanese   Publishing type：Research paper (bulletin of university, research institution)  

researchmap

Language：English   Publishing type：Research paper (scientific journal)   Publisher：Japanese Society of Computational Statistics  

The analysis of repeated measurements is studied on the situation where there are some outliers which deviate so much from the other data as to arouse suspicions that they were generated by different mechanisms. In these case, if we use distributions which are heavy-tailed relative to the normal distribution as the assumed error distributions, the estimates might be less affected by outliers. From this point of view, we assume scale mixtures of multivariate normal distributions as the error distributions. Also, we consider the case with missing observation and propose a method to obtain the maximum likelihood estimates by applying the EM algorithm. Model selection by AIC and detection of outliers are also discussed with the aid of real data.

DOI： 10.20551/jscswabun.3.1_11

CiNii Article

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (other academic)  

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：Japanese   Publishing type：Research paper (bulletin of university, research institution)   Publisher：関西大学経済学会  

CiNii Article

researchmap

Language：English   Publishing type：Research paper (other academic)  

researchmap

Language：English   Publishing type：Research paper (bulletin of university, research institution)  

researchmap

Language：Japanese Book type：Other

researchmap

Language：Japanese Book type：Other

researchmap

Language：English Book type：Other

researchmap