• Proceedings of the Safety Management and Science Conference
• /
• 2008.04a
• /
• pp.451-460
• /
• 2008

This paper reviews nonparametric statistics by Neyman-Pearson test and Fisher test. Nonparametric statistics deal with the small sample with distribution-free assumption in multi-product and small-volume production. Two tests for various nonparametric statistic methods such as sign test, Wilcoxon test, Mann-Whitney test, Kruskal-Wallis test, Mood test, Friedman test and run test are also presented with the steps for testing hypotheses and test of significance.

• The Korean Journal of Applied Statistics
• /
• v.7 no.1
• /
• pp.59-68
• /
• 1994

The role of the department of statistics in Korea is discussed. There are more than 70 statistics departments in the universities throughout the country. However, we can hardly find that statisticians and statistical service organizations who are responsible for, for example, identifying the statistical services needed by clients in our society. In developed countries, statistics is now widely employed in all areas of societies including industry and government. Statistics and statisticians also have vital internal roles in production, research, marketing, and support functions of the modern corporation as stated by Marquardt(1987). Professors in the department of statistics are responsible for solving the problems with the discipline of statistics and with statisticians. In this article some of those problems are explored.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.15 no.2
• /
• pp.5-25
• /
• 2004

Library statistics is used for internal decisions to know and assess library operations or for external justifications to show of how libraries meet users' needs and contribute to the organization. It is included same frameworks with social indicators and cultural indicators in national level. In this basis, national library statistics, they are ANSI/NISO Z39.7, Canada's Core library statistics, LIST of united Kingdom, are examined and Delphi method is used for new scheme of korean library statistics. As the results, it is suggested that new korean framework of library statistics is composed of 7 parts with 31 items. There are 6 parts with 21 items of social indicators or cultural indicators related to library items as well.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.3
• /
• pp.845-849
• /
• 2008

2009 year new execution of appointments for secondary school teachers was announced at 2004 year by Ministry of Education. The new school teacher appointment has been developed and studied in various aspects of appropriate qualification for good school teacher. In the results of the studies by Korea School Mathematics Education Association and pre-exams by Korea Institute for Curriculum and Evaluation, the Probability and Statistics chapters are less revaluated as 7.5-10%, but we argue those more than 15% as along with our recent Korean school texts reviews(Lee, et al., 2005).

• The Korean Journal of Applied Statistics
• /
• v.23 no.4
• /
• pp.725-738
• /
• 2010

As an effort to reform legal system of Korea, the law school system is introduced in March 2009. Thus the law culture of Korea is expected to change drastically for diversification, specialization and globalization. With such social trend as background, the author writes on the pre-law and law school courses "Law and Statistics" which were offered at Korea University. Also, he reviews two legal cases and summarizes two research results: DNA database controversies and a sentence standardization model.

• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06c
• /
• pp.110-113
• /
• 2007

최근 과학적 정책결정의 합리성을 뒷받침하기 위해서 통계에 대한 수요가 급증하고 있는 실정이다. 따라서 통계 수요자들은 사용자가 필요한 통계표를 직접 실시간적으로 산출하고자 하는 요구를 지속적으로 제기하고 있다. 본 연구에서는 의사결정 및 통계시스템에서 주로 사용하고 있는 데이터웨어하우스, OLAP 시스템 및 스타스키마에 관하여 알아보고 수요자들의 다양한 요구에 부응하기 위한 교육인적자원 통계정보 시스템의 구축에 대해 기술한다. 또한 교육인적자원 통계정보시스템의 핵심기능인 Web OLAP 시스템을 통해서 수요자가 원하는 교육통계정보를 실시간적으로 산출하기 위한 시스템의 구축방안에 대하여 기술하고자 한다.

• The Korean Journal of Applied Statistics
• /
• v.21 no.5
• /
• pp.825-833
• /
• 2008

Discriminant analysis based on Gaussian mixture models, an useful tool for multi-class classifications, can be extended to semi-supervised learning. We consider a model selection problem for a Gaussian mixture model in semi-supervised learning. More specifically, we adopt Bayesian information criterion to determine the number of subclasses in the mixture model. Through simulations, we illustrate the usefulness of the criterion.

• Journal of the Korean School Mathematics Society
• /
• v.7 no.2
• /
• pp.51-65
• /
• 2004

The purpose of this study was to develop the way in improving of teaching statistics in school mathematics. I reviewed the curriculum of Korea and America in statistics at School. I proposed the effective way of teaching statistics with the curriculum and content of statistics and the method of teaching of students and teachers.

• Journal of Information Management
• /
• v.43 no.3
• /
• pp.161-180
• /
• 2012

In this study, concept and importance of e-journal usage statistics has been examined and Journal Usage Factor project performed by Project COUNTER group has been investigated. Advantages and limits of usage statistics generated by library, link resolver and publisher have been clarified. By analyzing various errors and problems included in publisher-generated usage statistics, we conclude that the current usage statistics is not completely credible yet.

• The Korean Journal of Applied Statistics
• /
• v.20 no.3
• /
• pp.531-540
• /
• 2007

The recursive feature elimination for support vector machine is known to be useful in selecting relevant genes. Since the criterion for choosing relevant genes is the absolute value of a coefficient, the recursive feature elimination may suffer from a scaling problem. We propose a modified version of the recursive feature elimination algorithm using bootstrap. In our method, the criterion for determining relevant genes is the absolute value of a coefficient divided by its standard error, which accounts for statistical variability of the coefficient. Through numerical examples, we illustrate that our method is effective in gene selection.