• Journal of Korean Society for Quality Management
• /
• v.40 no.1
• /
• pp.15-24
• /
• 2012

For the construction of fractional factorial designs, the various arrays can be widely used. In this paper we review the statistical properties of fractional designs constructed by two arrays such as orthogonal array and partially balanced array, and develop a quick and easy method for analyzing unreplicated saturated designs. The proposed method can be characterized that we control the error rate by experiment-wise way and exploit the multivariate Student $t$-distribution. Especially the proposed method can be used efficiently together with some exploratory analysis methods, such as half normal probability plot method.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.491-503
• /
• 2002

In this paper, we propose a automatic document summarization method based on Principal Component Analysis(PCA) which is one of the multivariate statistical methods. After extracting thematic words using PCA, we select the statements containing the respective extracted thematic words, and make the document summary with them. Experimental results using newspaper articles show that the proposed method is superior to the method using either word frequency or information retrieval thesaurus.

• The Korean Journal of Applied Statistics
• /
• v.30 no.5
• /
• pp.747-757
• /
• 2017

We investigate multivariate volatilities based on high frequency time series. The PCA (principal component analysis) method is employed to achieve a dimension reduction in multivariate volatility. Multivariate realized volatilities (RV) with various frequencies are calculated from high frequency data and "optimum" frequency is suggested using PCA. Specifically, RVs with various frequencies are compared with existing daily volatilities such as Cholesky, EWMA and BEKK after dimension reduction via PCA. An analysis of high frequency stock prices of KOSPI, Samsung Electronics and Hyundai motor company is illustrated.

• The Korean Journal of Applied Statistics
• /
• v.22 no.1
• /
• pp.129-140
• /
• 2009

In this paper, we consider simultaneous confidence intervals for the difference of proportions between two groups taken from multivariate binomial distributions in a nonparametric way. We briefly discuss the construction of simultaneous confidence intervals using the method of adjusting the p-values in multiple tests. The features of bootstrap simultaneous confidence intervals using non-pooled samples are presented. We also compute confidence intervals from the adjusted p-values of multiple tests in the Westfall (1985) style based on a pooled sample. The average coverage probabilities of the bootstrap simultaneous confidence intervals are compared with those of the Bonferroni simultaneous confidence intervals and the Sidak simultaneous confidence intervals. Finally, we give an example that shows how the proposed bootstrap simultaneous confidence intervals can be utilized through data analysis.

• Journal of Korean Institute of Industrial Engineers
• /
• v.19 no.2
• /
• pp.35-41
• /
• 1993

Statistical calibration is a useful technique for achieving compatibility between two different measurement methods, and it usually consists of two steps : (1) estimation of the relationship between the standard and nonstandard measurements, and (2) prediction of future standard measurements using the estimated relationship and observed nonstandard measurements. A predictive multivariate errors-in-variables model is presented for the multivariate calibration problem in which the standard as well as the nonstandard measurements are subject to error. For the estimation of the relationship between the two measurements, the maximum likelihood (ML) estimation method is considered. It is shown that the direct and the inverse predictors for the future unknown standard measurement are the same under ML estimation. Based upon large-sample approximations, the mean square error of the predictor is derived.

• The Korean Journal of Applied Statistics
• /
• v.17 no.1
• /
• pp.35-47
• /
• 2004

In this paper, we generalizes Kim and Bickel(2003)'s statistic for bivariate normality to that of multinormality, applying Fattorini(1986)'s method. Fattorini(1986) generalized Shapiro-Wilk's statistic for univariate normality to multivariate cases. The proposed statistic could be considered as an approximate statistic to Fattorini(1986)'s. It can be used even for a big sample size. Power performance of the proposed test is assessed in a Monte Carlo study.

• Journal of the Korean Statistical Society
• /
• v.12 no.1
• /
• pp.24-35
• /
• 1983

In fitting models to data, selection of the most desirable estimation method and determination of the adequacy of fitted model are the central issues. This paper compares the maximum likelihood estimators and the minimum logit chi-square estimators, both being best asymptotically normal, when logit models are fitted to infant mortality data. Chi-square goodness-of-fit test and likelihood ratio one are also compared. The analysis infant mortality data shows that the outlying observations do not necessarily result in the same impact on goodness-of-fit measures.

• The Korean Journal of Applied Statistics
• /
• v.22 no.5
• /
• pp.1097-1102
• /
• 2009

Classification of subjects with unknown distribution in small sample size setup may involve order-restricted constraints in multivariate parameter setups. Those problems makes optimality of conventional likelihood ratio based statistical inferences not feasible. Fortunately, Roy (1953) introduced union-intersection principle(UIP) which provides an alternative avenue. Redescending M-estimator along with that principle yields a considerably appropriate robust testing procedure. Furthermore, conditionally distribution-free test based upon exact permutation theory is used to generate p-values, even in small sample. Applications of this method are illustrated in simulated data and read data example (Lobenhofer et al., 2002)

• Communications for Statistical Applications and Methods
• /
• v.16 no.4
• /
• pp.675-686
• /
• 2009

In this paper, it will be assumed that there are two distinct populations which are multivariate normal with equal covariance matrix. We also assume that the two populations are equally likely and the costs of misclassification are equal. The classification rule depends on the situation when the training samples include missing values or not. We consider the bootstrap confidence intervals for classification error rate when a block of observation is missing.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2007.11a
• /
• pp.239-240
• /
• 2007