Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Communications for Statistical Applications and Methods
Journal Basic Information
Journal DOI :
The Korean Statistical Society
Editor in Chief :
Volume & Issues
Volume 16, Issue 6 - Nov 2009
Volume 16, Issue 5 - Sep 2009
Volume 16, Issue 4 - Jul 2009
Volume 16, Issue 3 - May 2009
Volume 16, Issue 2 - Mar 2009
Volume 16, Issue 1 - Jan 2009
Selecting the target year
A Short Consideration of Binomial Confidence Interval
Ryu, Jea-Bok ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 731~743
DOI : 10.5351/CKSS.2009.16.5.731
The interval estimation for binomial proportion has been treated practically as well as theoretically for a long time. In this paper we compared the properties of major confidence intervals and summarized current issues for coverage probability and interval length which are the criteria of evaluation for confidence interval. Additionally, we examined the three topics which were considered in using the binomial confidence interval in the field. And finally we discussed the future studies for a low binomial proportion.
Detecting an Outlier in 2X2 Bioequivalence Trial
Jeong, Gyu-Jin ; Park, Sang-Gue ; Woo, Hwa-Hyoung ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 745~751
DOI : 10.5351/CKSS.2009.16.5.745
Outlying or extreme observations are defined to be subject data for which one or more bioavailability measures are discordant with corresponding data for that subject and/or for the rest of the subjects in a study. The presence of outlying observations can have very serious consequences on the conclusions resulting from a bioequivalence study. Two statistical methods are proposed by generalizing the current well known methods and an illustrated example is presented with discussion.
Measure of Agreement H in mXm Contingency Table
Kim, Jin-Gon ; Park, Mi-Hee ; Park, Yong-Gyu ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 753~762
DOI : 10.5351/CKSS.2009.16.5.753
A measure of agreement H in
contingency table was proposed by Park and Park (2007) to resolve the two paradoxes of k. In this study, we generalize H to where the number of categories is greater than two and derive its asymptotic large-sample variance. We also explain the relationships between k's paradoxes and marginal distributions. Using some examples of
contingency tables, the behaviors of H and other measures of agreement are compared.
Study of Sample Design for Improving the Method of Distribution of Singing Rooms Royalty
Lee, Kay-O ; Choi, Jung-Bai ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 763~779
DOI : 10.5351/CKSS.2009.16.5.763
Sample design is studied to estimate the number of records from singing rooms. The definition of survey population, stratification, sample size and allocation of sample are discussed with using the collected real data. The validity of sample design is testified by the log data collected from online singing room which is sampled with suggested design. Estimation of the number of hitting of off-line singing room is proposed and calculated from the log data collected from sampled off-line singing rooms. The difference of online and off-line singing rooms is analyzed and the method of distribution of singing room royalty is suggested.
Fuzzy Linear Regression Using Distribution Free Method
Yoon, Jin-Hee ; Choi, Seung-Hoe ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 781~790
DOI : 10.5351/CKSS.2009.16.5.781
This paper deals with a rank transformation method and a Theil's method based on an
-level set of a fuzzy number to construct a fuzzy linear regression model. The rank transformation method is a simple procedure where the data are merely replaced with their corresponding ranks, and the Theil's method uses the median of all estimates of the parameter calculated from selected pairs of observations. We also consider two numerical examples to evaluate effectiveness of the fuzzy regression model using the proposed method and of another fuzzy regression model using the least square method.
Combination of Value-at-Risk Models with Support Vector Machine
Kim, Yong-Tae ; Shim, Joo-Yong ; Lee, Jang-Taek ; Hwang, Chang-Ha ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 791~801
DOI : 10.5351/CKSS.2009.16.5.791
Value-at-Risk(VaR) has been used as an important tool to measure the market risk. However, the selection of the VaR models is controversial. This paper proposes VaR forecast combinations using support vector machine quantile regression instead of selecting a single model out of historical simulation and GARCH.
Extreme Quantile Estimation of Losses in KRW/USD Exchange Rate
Yun, Seok-Hoon ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 803~812
DOI : 10.5351/CKSS.2009.16.5.803
The application of extreme value theory to financial data is a fairly recent innovation. The classical annual maximum method is to fit the generalized extreme value distribution to the annual maxima of a data series. An alterative modern method, the so-called threshold method, is to fit the generalized Pareto distribution to the excesses over a high threshold from the data series. A more substantial variant is to take the point-process viewpoint of high-level exceedances. That is, the exceedance times and excess values of a high threshold are viewed as a two-dimensional point process whose limiting form is a non-homogeneous Poisson process. In this paper, we apply the two-dimensional non-homogeneous Poisson process model to daily losses, daily negative log-returns, in the data series of KBW/USD exchange rate, collected from January 4th, 1982 until December 31 st, 2008. The main question is how to estimate extreme quantiles of losses such as the 10-year or 50-year return level.
A View on Extension of Utility-Based on Links with Information Measures
Hoseinzadeh, A.R. ; Borzadaran, G.R.Mohtashami ; Yari, G.H. ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 813~820
DOI : 10.5351/CKSS.2009.16.5.813
In this paper, we review the utility-based generalization of the Shannon entropy and Kullback-Leibler information measure as the U-entropy and the U-relative entropy that was introduced by Friedman et al. (2007). Then, we derive some relations between the U-relative entropy and other information measures based on a parametric family of utility functions.
A General Procedure for Estimating the General Parameter Using Auxiliary Information in Presence of Measurement Errors
Singh, Housila P. ; Karpe, Namrata ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 821~840
DOI : 10.5351/CKSS.2009.16.5.821
This article addresses the problem of estimating a family of general population parameter
using auxiliary information in the presence of measurement errors. The general results are then applied to estimate the coefficient of variation
of the study variable Y using the knowledge of the error variance
associated with the study variable Y, Based on large sample approximation, the optimal conditions are obtained and the situations are identified under which the proposed class of estimators would be better than conventional estimator. Application of the main result to bivariate normal population is illustrated.
Precise Rates in Complete Moment Convergence for Negatively Associated Sequences
Ryu, Dae-Hee ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 841~849
DOI : 10.5351/CKSS.2009.16.5.841
1} be a negatively associated sequence of identically distributed random variables with mean zeros and positive finite variances. Set
. Suppose that 0 <
. We prove that, if
for any 0<
, where N is the standard normal random variable. We also prove that if
is replaced by
then the precise rate still holds. Some results in Fu and Zhang (2007) are improved to the complete moment case.
Spatial Prediction Based on the Bayesian Kriging with Box-Cox Transformation
Choi, Jung-Soon ; Park, Man-Sik ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 851~858
DOI : 10.5351/CKSS.2009.16.5.851
In the last decades, there has been much interest in climate variability because its change has dramatic effects on humanity. Especially, the precipitation data are measured over space and their spatial association is so complicated. So we should take into account such a spatial dependency structure while analyzing the data. However, in linear models for analyzing the data, data sets show severely skewed distribution. In the paper, we consider the Box-Cox transformation to satisfy the normal distribution prior to the analysis, and employ a Bayesian hierarchical framework to investigate the spatial patterns. The data set we considered is monthly average precipitation of the third quarter of 2007 obtained from 347 automated monitoring stations in Contiguous South Korea.
Estimations in a Skewed Double Weibull Distribution
Son, Hee-Ju ; Woo, Jung-Soo ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 859~870
DOI : 10.5351/CKSS.2009.16.5.859
We obtain a skewed double Weibull distribution by a double Weibull distribution, and evaluate its coefficient of skewness. And we obtain the approximate maximum likelihood estimator(AML) and moment estimator of skew parameter in the skewed double Weibull distribution, and hence compare simulated mean squared errors(MSE) of those estimators. We compare simulated MSE of two proposed reliability estimators in two independent skewed double Weibull distributions each with different skew parameters. Finally we introduce a skewed double Weibull distribution generated by a uniform kernel.
Burn-in Models: Recent Issues, Developments and Future Topics
Cha, Ji-Hwan ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 871~880
DOI : 10.5351/CKSS.2009.16.5.871
Recently, there has been much development on burn-in models in reliability area. Especially, the previous burn-in models have been extended to more general cases. For example, (i) burn-in procedures for repairable systems have been developed (ii) an extended assumption on the failure rate of the system has been proposed and (iii) a stochastic model for burn-in procedure in accelerated environment has been developed. In this paper, recent extensions and advances in burn-in models are introduced and some issues to be considered in the future study are discussed.
Visualizing SVM Classification in Reduced Dimensions
Huh, Myung-Hoe ; Park, Hee-Man ;
Communications for Statistical Applications and Methods, volume 16, issue 5, 2009, Pages 881~889
DOI : 10.5351/CKSS.2009.16.5.881
Support vector machines(SVMs) are known as flexible and efficient classifier of multivariate observations, producing a hyperplane or hyperdimensional curved surface in multidimensional feature space that best separates training samples by known groups. As various methodological extensions are made for SVM classifiers in recent years, it becomes more difficult to understand the constructed model intuitively. The aim of this paper is to visualize various SVM classifications tuned by several parameters in reduced dimensions, so that data analysts secure the tangible image of the products that the machine made.