• Communications for Statistical Applications and Methods
• /
• v.27 no.1
• /
• pp.149-161
• /
• 2020

In this paper we extend the functional principal component analysis for real-valued random functions to the case of Hilbert-space-valued functional random objects. For this, we introduce an autocovariance operator acting on the space of real-valued functions. We establish an eigendecomposition of the autocovariance operator and a Karuhnen-Loève expansion. We propose the estimators of the eigenfunctions and the functional principal component scores, and investigate the rates of convergence of the estimators to their targets. We detail the implementation of the methodology for the cases of compositional vectors and density functions, and illustrate the method by analyzing time-varying population composition data. We also discuss an extension of the methodology to multivariate cases and develop the corresponding theory.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.32 no.3
• /
• pp.178-187
• /
• 2009

Six Sigma emphasizes KPI and establishes the present level as well as the goal level through statistical calculation and tries to achieve management innovation through process improvement. But in the area of new product development or service, sufficient data for statistical measurement may not be secured. On the other side, looking for contradictions through problem analysis, TRIZ is a methodology that stresses the process of solving these problems. TRIZ also has its own problems: it is hard to define its initial task, to objectify the measurement of effect, and to optimize the drawn out idea. The purpose of this report is to give a comprehensive understanding about each methodology (Sigma Six and TRIZ) through its analysis, to confirm the need of linking both methodologies, and to suggest a model for this linking process. Also, they will be verified through examples, and the synergy effect will be discussed.

• Journal of Korean Society for Quality Management
• /
• v.7 no.2
• /
• pp.22-28
• /
• 1979

The problem considered in this paper is to select the vital factor effect to the product quality through the experimental design and analysis of response surface, so as to control the quality improvement of industrial product. In this time, even through the mathematical model is unknown it could be applicable to control the quality of industrial products and to determine optimum operating condition for many technical fields, particulary, for industrial manufacturing process. When a set of data is available from an experimental design, it is often of interest 1:0 fit polynominal repression model in independent variables (eg, time, temperature, pressure, etc) the optimize the response variable (eg. yield, strength etc). This paper proposes a method known to obtain the optimum operating condition, and how to find the condition by using table of orthogonal array experiments, and optimization methodology of statistical model. A criterion can be applied determining to optimum operating conditions in manufacturing industry and improving the fit of response surface which may be used for prediction of responses and quality control of industrial products.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.289-301
• /
• 1996

This paper suggests a new diagnostic measure for detecting influential observations in two group linear discriminant analysis(LDA). It is developed from an information theoretic point of view using the minimum discrimination information(MDI) methodology. MDI estimator of symmetric divergence by Kullback(l967) is taken as a measure of the power of discrimination in LDA. It is shown that the effect of an observation over the power of discrimination is fully explained by the diagnostic measure. Asymptotic distribution of the proposed measure is derived as a function of independent chi-squared and standard normal variables. By means of the distributions, a couple of methods are suggested for detecting the influential observations in LDA. Performance of the suggested methods are examined through a simulation study.

• The Korean Journal of Applied Statistics
• /
• v.25 no.5
• /
• pp.865-875
• /
• 2012

In this study, we identify the variables that affect the number of crime and spatial correlation in the Seoul metropolitan area, in addition, we measure the relative risk on the incidence of crime by a Poisson regression model. We suggest a statistical methodology to make a risk map for crime based on relative risk instead of the total event of crime by region using the Geographic Information System. To demonstrate the use and advantages of this methodology, this study presents an analyses of the total crime count in 25 wards in the Seoul metropolitan area.

• Journal of Environmental Impact Assessment
• /
• v.6 no.1
• /
• pp.135-149
• /
• 1997

Environmental issues are currently in the forefront of the political and economic area both globaly and nationally. In the all spheres of socio-economic development and policy, it is suggested that there are need, to measure environmental impacts and to produce and disseminate environmental statistics systematically for environmentally sound and sustainable development. Specially, because environmental statistics encompass a wide spectrum of sectors from the natural to the social sciences and are dispersed among various agencies, an organized approach and compilation methods in complicated fields such as environment are required. This article includes the methodology on the framework for development of environmental statistics to advance korean environmental statistics.

• KIEAE Journal
• /
• v.7 no.3
• /
• pp.31-37
• /
• 2007

Statistical analyses with actual data are used in estimating construction cost for many years, but collected data could include factors that distort analytical results, namely outliers. To enhance reliability in predicting construction cost, the methodology, which is able to identify outliers and determine how to manage them, is needed. Actual costs obtained from 22 construction projects were studied. It is found that there is substantial disparity between results considering outliers and results not considering ones. Therefore, it is to identify outliers and apply an optimum process in estimating construction cost when actual data is used in statistical analysis.

• Journal of the Korean Institute of Telematics and Electronics A
• /
• v.30A no.12
• /
• pp.69-76
• /
• 1993

The statistical methodology using RSM (response surface method) was used too ptimize the deposition conditions of selective CVD tungsten process for improving the deposition rate and the adhesion property. Temperature, flow rate of SiH$_4$ and WF$_6$ and H$_2$ and Ar carrier gases were chosen for the deposition variables and process characteristics due to carrier gas were intensively investigated. It was observed that temperature was the main factor influencingthe deposition rate in the case of H$_2$ carrier gas while the reactant ratio, $SiH_{4}/WF_{6}$, had the principal effect on the deposition rate in the case of Ar carrier gas. The increased deposition rate and the good adhesion to Si were obtained under Ar carrier gas compared to H$_2$ carrier gas. The optimum conditions for deposition rate and antipeeling property were found to be the temperature range of 300~32$0^{\circ}C$ and the reactant ratio, $SiH_{4}/WF_{6}$, of 0.5~0.6.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.787-806
• /
• 2016

Mixed-mode (MM) designs in which data are collected by different modes in one design have become increasingly popular. An MM data collection has several advantages such as reductions of coverage error, non-response and cost. However, MM designs may introduce mode effects that are confounded by selection effects and measurement effects, which can make MM data quality poor. In order to investigate mode effects, SRI implemented a concurrent mixed-mode experiment in 2014 where respondents could choose between a self-administrated Web survey and a self-administrated paper survey. This paper separately estimates selection effects and measurement effects. We found that measurement effects on some items are large.

• Journal of Korean Society of Water and Wastewater
• /
• v.22 no.6
• /
• pp.647-655
• /
• 2008

Sewer Rehabilitation Project (SRP) is planed, designed and constructed to perform its intended performance as sewerage delivery systems. Recently, a subject of performance evaluation methodology development for SRP has become a great deal of concern among researchers in Korea. From the view point of Sewage Treatment Plant (STP), however, the estimation of improvement efficiency for SRP is in lack of reliability due to the fact that affections for the treatment efficiency and operating condition are not reflected on SRP design and construction. In this study, statistical methodology was used in the analysis of data, which are taken during 1,186 days ($1^{st}$ Jan. 2005 - $31^{th}$ Mar. 2008) from the influent, effluent and operating conditions of full-scale STP($25,000m^3/d$). Then the effect of SRP on the influent characteristics and operating conditions changing was compared and evaluated. Results from the statistical evaluation show that SRP causes characteristic changes in influent and exerts a significant effect especially on the performance of STP.