• Journal of the Korean Statistical Society
• /
• v.16 no.1
• /
• pp.10-20
• /
• 1987

The value of statistics used for variable selection criteria can be reduced remarkably by excluding only a few influential cases. Furthermore, different subsets of regressors change leverage and influence patterns for the same response variable. Based on these motivations, this paper suggests a procedure which considers variable selection and detection of influential cases simultaneously.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.521-531
• /
• 2002

Various diagnostic techniques for identifying influential observations are mostly based on the deletion of a single observation. While such techniques can satisfactorily identify influential observations in many cases, they will not always be successful because of some mask effect. It is necessary, therefore, to develop techniques that examine the potentially influential effects of a subset of observations. The partial regression plots can be used to examine an influential observation for a single parameter in multiple linear regression. However, it is often desirable to detect influential observations for a subset of regression parameters when interest centers on a selected subset of independent variables. Thus, we propose a diagnostic measure which deals with detecting influential observations on a subset of regression parameters. In this paper, we propose a measure M, which can be effectively used for the detection of influential observations on a subset of regression parameters in multiple linear regression. An illustrated example is given to show how we can use the new measure M to identify influential observations on a subset of regression parameters.

• Journal of the Korean Statistical Society
• /
• v.30 no.1
• /
• pp.139-151
• /
• 2001

Although lots of works are done in influence diagnostics, results in the multivariate analysis are quite rare. One of recent works done by Fung(1995) is about the single case influence diagnostics in the linear discriminant analysis. In this paper we extend Fung's results to the multiple cases diagnostics which are necessary in the linear discriminant analysis for two reasons among others; First, the masking effect cannot be detected by single case diagnostics and secondly two populations are concerned in the discriminant analysis, i.e., influential cases can occur in one or both populations.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.15 no.25
• /
• pp.103-113
• /
• 1992

This paper is to study the various diagnostic measures for detecting outliers and influential cases in linear regression. In this paper we review the most common diagnostic measures and show the inter-relationships the exist among them. Based on the PRESS(Predicted REsidual Sum of Squares ) offered by Allen(1974) as a criterion for model selection, we propose three measures for detecting outliers and influential cases. Examples are given illustrating various diagnostic measures including Proposed measures.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.15 no.25
• /
• pp.97-101
• /
• 1992

This paper proposes a new procedures for assessing the influence of individual or groups of cases when any regressors are included. At first, various influence measures pickout influential cases when one regress-or is deleted. Next find influential subsets by using heuristic approach and perform group deletion. Retaining or removing any regressors may depend on the presence or absence of one or few cases. Then, we can identify the interrelationships that exist among regressors and cases and examine their impact on the fitted regression equation. We conclude with an example using fuel consumption data.

• Journal of the Korean Statistical Society
• /
• v.21 no.1
• /
• pp.35-46
• /
• 1992

On Box-Cox transformation, one or few responses are influential on transformation parameter estimator. To detect influential observatins, several diagnostics (Cook and Wang 1983, Hinkley and Wang 1988, Lawrance 1988, Tsai and Wu 1990) have been suggested. We compare these diagnostics and denote the necessity of multiple cases deletion which is important especially when the masking effect is present. Also, analytic expression of Tsai and Wu's diagnostic is given. We suggest a computationally feasible and useful algorithm based on the basic building blocks, and present descriptive examples using artificial data.

• Journal of Korean Society for Quality Management
• /
• v.32 no.1
• /
• pp.1-20
• /
• 2004

Six sigma has been the most influential management innovation program since 1996 in Korea. As a result of successful implementation of 6 sigma, there have been a number of dramatic quality improvement cases. However, no empirical study of 6 sigma implementation study has done especially in the service industry of Korea. This article reviews status of finance companies which implemented 6 sigma programs in Korea and then demonstrates the relationship between 6 sigma problem solving tools such as analysis of variance and graph techniques, etc and project success and operational performance. Customer survey tools, process analysis, and documentation tool are identified as influential tools on project success. Tools of measure steps, customer survey tools, and documentation tool are found as influential tools on operational performance.

• The Journal of the Korean dental association
• /
• v.16 no.12 s.115
• /
• pp.941-944
• /
• 1978

The author studied skin reactions and their incidences among 100 dental students and dental nurses to 2% Lidocaine HC1, 3% H₂O₂, Euginol, 5% Sodium Hypochlorite, Dycal and Adhesive plaster by means of Patch test. Following are the results of the study. 1. Eighty six cases out of 100 revealed slight response to 1 or 2 allergens. 2. 2% Lidocaine HC1 showed 1 case, 3% H₂O₂cases, Euginol 2 cases, 5% Sodium Hypochlorite 74 cases, Dycal 1 case Adhesive plaster 8 cases. 3. 5% Sodium Hypochlorite was the most influential to skin. 32 cases showed grade 1+, 20 cases showed grade 2++, 16 cases showed grade 3+++, 6 cases showed grade 4++++,

• Journal of Korea Technology Innovation Society
• /
• v.16 no.4
• /
• pp.1090-1108
• /
• 2013

Recently national technology commercialization policy using the outcomes of public R&D has been promoting the activities of technology transfer and licensing. Firms also are considering licensing strategies to make great strides and strengthen their future competitiveness. In the licensing deals, objective and reasonable royalty determination is required to be accepted for both negotiation parties. This study analyzed the appropriate royalty range for various types of business and established three royalty influential factors with ten valuation items to explain royalty difference. This study suggested new method to estimate rationally reasonable running royalty rate, combining the appropriate royalty range from classic 25% rule and the result evaluated from royalty influential factors. The adequacy of royalty range from classic 25% rule is confirmed because its range is similar to that of royalty of transfer cases. The final estimate of running royalty can be made from linear function for royalty determination using the results of royalty range and royalty influential factors. This method suggested here is expected to practically useful to determine an appropriate running royalty rate for licensing negotiation.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.979-986
• /
• 2011

A linear regression method is commonly used to analyze data because of its simplicity and applicability; however, it is well known that data may contain some outliers and influential cases that may have a harmful effect on a statistical analysis. Thus detection and examination of outliers or influential cases are important parts of data analysis. In detecting multiple outliers, masking effects usually occur and make it difficult to identify the true outliers. We propose to use dynamic plots as a method resistant to masking effect. The procedure using dynamic plots is useful to find appropriate basic sets with which a dependent outliers detection method start and detect a true outliers set. Examples are given to demonstrate the effectiveness of the suggested idea.