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 8, Issue 3 - Dec 2001
Volume 8 - Nov 2001
Volume 8, Issue 2 - Aug 2001
Volume 8, Issue 1 - Apr 2001
Selecting the target year
Regression Diagnostic Using Residual Plots
Oh, Kwang-Sik ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 311~317
It is necessary to check the linearity of selected covariates in regression diagnostics. There are various graphical methods using residual plots such as partial residual plots, augmented partial residual plots and combining conditional expectation and residual plots. In this paper, we propose the modified pseudolikelihood ratio test statistics based on these residual plots to test linearity of selected covariate. These test statistics which measure the distance between the nonparametric and parametric models are derived as a ratio of quadratic forms. The approximate distribution of these statistics is calculated numerically by using three moments. The power comparison of these statistics is given.
A Note on a Fuzzy Linear Regression Model for Fuzzy Input-output Date Using Real Coefficients
Hong, Dug-Hun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 319~325
In this note, we propose a simple fuzzy linear regression model for fuzzy input-output data based on Tanaka's approach. Then an LP-based method to derived the satisfying solution of the decision making is developed.
Efficiency of Aggregate Data in Non-linear Regression
Huh, Jib ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 327~336
This work concerns estimating a regression function, which is not linear, using aggregate data. In much of the empirical research, data are aggregated for various reasons before statistical analysis. In a traditional parametric approach, a linear estimation of the non-linear function with aggregate data can result in unstable estimators of the parameters. More serious consequence is the bias in the estimation of the non-linear function. The approach we employ is the kernel regression smoothing. We describe the conditions when the aggregate data can be used to estimate the regression function efficiently. Numerical examples will illustrate our findings.
The Sequential Testing of Multiple Outliers in Linear Regression
Park, Jinpyo ; Park, Heechang ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 337~346
In this paper we consider the problem of identifying and testing the outliers in linear regression. first we consider the problem for testing the null hypothesis of no outliers. The test based on the ratio of two scale estimates is proposed. We show the asymptotic distribution of the test statistic by Monte Carlo simulation and investigate its properties. Next we consider the problem of identifying the outliers. A forward sequential procedure based on the suggested test is proposed and shown to perform fairly well. The forward sequential procedure is unaffected by masking and swamping effects because the test statistic is based on robust estimate.
Influence Analysis on a Test Statistic in Canonical Correlation Analysis
Jung, Kang-Mo ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 347~355
We propose a method for detecting influential observations that have a large influence on the likelihood ratio test statistic for the two sets of variables are uncorrelated with one another. For this purpose we derive a local influence measure for the likelihood ratio test statistic under certain perturbation scheme. An illustrative example is given to show the effectiveness of the proposed method on the identification of influential observations.
Goodness of Link Tests for Binary Response Data
Yeo, In-Kwon ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 357~366
The present paper develops a method to check the propriety of link functions for binary data. In order to parameterize a certain type of goodness of the link, a family of link functions indexed by a shape parameter is proposed. I first investigate the maximum likelihood estimation of the shape parameter as well as regression parameters and then derive their large sample behaviors of the estimators. A score test is considered to evaluate the goodness of the current link function. For illustration, I employ two families of power transformations, the modulus transformation by John and Draper (1980) and the extended power transformation by Yeo and Johnson (2000), which are appropriate to detect symmetric and asymmetric inadequacy of the selected link function. respectively.
Partial Diallel Crosses Using Group Divisible Designs
Jong SeongGong Sun ; Kim, Gong-Sun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 367~374
In this paper, a method based on group divisible designs is presented for constructing some partial diallel crosses. We discuss in detail a particular inbred line, i.e., p lines divided into two groups with p
lines and p
lines. These designs are obtained by regarding the number of lines as treatments. In specially we study and compare the efficiency factors of the constructed partial diallel crosses with or without repeated blocks.
A Sampling Design of the Agricultural Machine Estimated Sales Survey
Park, Jinwoo ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 375~382
The agricultural machine estimated sales survey is a survey to estimate annual sales quantities of eight major agricultural machines such as tracter, combine, etc. The purpose of this study is to design a multipurpose sample for the agricultural machine estimated sales survey. Main achievements of this study are to present an efficient stratification criterion and to suggest a reasonable estimation method by using the concept of post-stratification.
Multi-Level Skip-Lot Sampling Plan
Cho, Gyo-Young ; Ahn, Young-Sun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 383~394
This paper is a generalization of single and two-level skip-lot sampling plans to n-level. On every skipping inspection of the n-level skip-lot sampling plan, not only the number of consecutive lots to be accepted but also the fraction of lots to be inspected can be freely choosed. The general formulas of the operating characteristic function, average fraction inspected, average sample number and average outgoing quality in n-level skip-lot sampling plan are derived. The operating characteristic curves, average sample number and average outgoing quality of a reference plan, two-level and five-level skip-lot sampling plans are compared.
Nonparametric Test for Umbrella Alternatives with the Known Peak on Ranked-Set Samples
Kim, Dong-Hee ; Kim, Kyung-Hee ; Kim, Hyun-Gee ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 395~406
In this paper, we propose the test statistic for the umbrella alternatives on c-samples ranked set samples(RSS), where the peak of the umbrella is known. We obtain the asymptotic property of the proposed test statistic and the asymptotic relative efficiencies of the proposed test statistic with respect to U-statistic based on simple random samples(SRS). From the simulation work, we compare the empirical powers of the proposed test statistic with U-statistic based on SRS.
Bayes Prediction for Small Area Estimation
Lee, Sang-Eun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 407~416
Sample surveys are usually designed and analyzed to produce estimates for a large area or populations. Therefore, for the small area estimations, sample sizes are often not large enough to give adequate precision. Several small area estimation methods were proposed in recent years concerning with sample sizes. Here, we will compare simple Bayesian approach with Bayesian prediction for small area estimation based on linear regression model. The performance of the proposed method was evaluated through unemployment population data form Economic Active Population(EAP) Survey.
Nonparametric Bayesian Estimation for the Exponential Lifetime Data under the Type II Censoring
Lee, Woo-Dong ; Kim, Dal-Ho ; Kang, Sang-Gil ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 417~426
This paper addresses the nonparametric Bayesian estimation for the exponential populations under type II censoring. The Dirichlet process prior is used to provide nonparametric Bayesian estimates of parameters of exponential populations. In the past, there have been computational difficulties with nonparametric Bayesian problems. This paper solves these difficulties by a Gibbs sampler algorithm. This procedure is applied to a real example and is compared with a classical estimator.
Semiparametric Bayesian multiple comparisons for Poisson Populations
Cho, Jang Sik ; Kim, Dal Ho ; Kang, Sang Gil ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 427~434
In this paper, we consider the nonparametric Bayesian approach to the multiple comparisons problem for I Poisson populations using Dirichlet process priors. We describe Gibbs sampling algorithm for calculating posterior probabilities for the hypotheses and calculate posterior probabilities for the hypotheses using Markov chain Monte Carlo. Also we provide a numerical example to illustrate the developed numerical technique.
Bayes Estimators for Reliablity of a k-Unit Standby System with Perfect Switch
Lee, Changsoo ; Kim, Keehwan ; Park, Youngmi ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 435~442
Bayes estimators and generalized ML estimators for reliability of a k-unit hot standby system with the perfect switch based upon a complete sample of failure times observed from an exponential distribution using noninformative, generalized uniform, and gamma priors for the failure rate are proposed, and MSE's of proposed several estimators for the standby system reliability are compared numerically each other through the Monte Carlo simulation.
Statistical Analysis of Bioequivalence Study in 2x3 Cross-over Design
Lim, Nam-Kyoo ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 443~452
The 2x3 cross-over design is proposed for the bioequivalence of two test drug formulations with a reference drug formulation. Oh et al.(1999) and Park et al.(1998) derived 3x2 cross-over design and discussed its benefits, since the 3x3 cross-over design may not be of practical design. We discuss the statistical issues for2x3 cross-over design and show its statistical properties. Bioequivalence problem in 2x3 cross-over design is considered statistically and an illustrated example is given.
Probabilistic Safety Assessment of Nuclear Power Plants Using Bayes Method
Shim, Kyu-Bark ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 453~464
A commercial nuclear power station contains at least tow emergency diesel generators(EDG) to control the risk of severe core damage during station blackout accidents. Therefore, the reliability of the EDG's to start and load-run on demand must be maintained at a sufficiently high level. Probabilistic safety assessments(PSA) are increasingly being used to quantify the public risk of operating potentially hazardous systems such as nuclear power reactors. In this paper, to perform PSA, we will introduce three different types of data and use Bayes procedure to estimate the error rate of nuclear power plant EDG, and using practical examples, illustrate which method is more reasonable in our situation
A Suggestion for Randomized Response Technique using Fuzzy Logic
Choi, Kyung-Ho ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 465~471
Randomized response technique is a survey technique for eliminating evasive answer bias. But this technique has a problem. This procedure suffers from linguistic expression in randomizing device. Thus for solving the problem, in this paper, we suggested the randomized response technique using fuzzy logic.
The Limit Distribution of a Modified W-Test Statistic for Exponentiality
Kim, Namhyun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 473~481
Shapiro and Wilk (1972) developed a test for exponentiality with origin and scale unknown. The procedure consists of comparing the generalized least squares estimate of scale with the estimate of scale given by the sample variance. However the test statistic is inconsistent. Kim(2001) proposed a modified Shapiro-Wilk's test statistic based on the ratio of tow asymptotically efficient estimates of scale. In this paper, we study the asymptotic behavior of the statistic using the approximation of the quantile process by a sequence of Brownian bridges and represent the limit null distribution as an integral of a Brownian bridge.
A Study on Goodness-of-fit Test for Density with Unknown Parameters
Hang, Changkon ; Lee, Minyoung ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 483~497
When one fits a parametric density function to a data set, it is usually advisable to test the goodness of the postulated model. In this paper we study the nonparametric tests for testing the null hypothesis against general alternatives, when the null hypothesis specifies the density function up to unknown parameters. We modify the test statistic which was proposed by the first author and his colleagues. Asymptotic distribution of the modified statistic is derived and its performance is compared with some other tests through simulation.
K-function Test for he Spatial Randomness among the Earthquakes in the Korean Peninsula
Baek, Jangsung ; Bae, Jong-Sung ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 499~505
Kim and Baek (2000) tested the spatial randomness for he earthquake occurrence in the Korean Peninsula by using the nearest-neighbor test statistics and empirical distribution functions. The K-function, however, has obvious advantages over the methods used in Kim and Baek (2000), such as it does not depend on the shape of the study region and is an effective summary of spatial dependence over a wide range of scales. We applied the K-function method for testing the randomness to both of the historical and the instrumental seismicity data. It was found that he earthquake occurrences for historical and instrumental seismicity data are not random and clustered rather than scattered.
Development of Multivariate Analysis System by Using SAS/AF and SCL
Han, Sang-Tae ; Kang, Hyuncheol ; Lee, Seong-Keon ; Jang, Myung-Seok ; Lee, Duck-Ki ; Ryu, Dong-Kyun ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 507~514
In recent years, the development and the embodiment of information analysis system has been sprightly carried out in several fields of study. In this study, as and extension of these studies, we develop a system for multivariate analysis which might be widely used in social and natural sciences. This multivariate analysis system is developed by using multivariate analysis procedures in SAS/STAT software. Also, the system supply users with he environment of GUI(Graphical User Interface), which is constructed with AF(application frame) and SCL(screen control language) of SAS software, in order to help users to use the system with easy.
Introduction to the History of Statistics Development in Italy
Kim, Joo-Hwan ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 515~530
Recently Korean statistician have more chance to work with other researcher in other countries at international level. Especially the 53rd Scientist meeting of he International Statistical Institute(ISI) will be held in Seoul, Rep. of Korea at Aug 22-29, 2001. The fields of Statistics in Korea have been affected a lot from American Statistical Society. In this research communication, I would like to introduce a short history of he Italian statistical society and their major research topic and outputs. The contents will help us to understand the Italian statistician, and it can be a conner-stone to the future relationship between Korean statistician and Italian statistician.
A Comparison of Capabilities of Data Mining Tools
Choi, Youn-Seok ; Kim, Jong-Geoun ; Lee, Jong-Hee ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 531~541
In this study, we compare the capabilities of the data mining tools of the most updated version objectively and provide the useful information in which enterprises and universities chose them. In particular, we compare the SAS/Enterprise Miner 3.0, SPSS/Clementine 5.2 and IBM/Intelligent Miner 6.1 which are well known and easily gotten.
Neural Network Forecasting Using Data Mining Classifiers Based on Structural Change: Application to Stock Price Index
Oh, Kyong-Joo ; Han, Ingoo ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 543~556
This study suggests integrated neural network modes for he stock price index forecasting using change-point detection. The basic concept of this proposed model is to obtain significant intervals occurred by change points, identify them as change-point groups, and reflect them in stock price index forecasting. The model is composed of three phases. The first phase is to detect successive structural changes in stock price index dataset. The second phase is to forecast change-point group with various data mining classifiers. The final phase is to forecast the stock price index with backpropagation neural networks. The proposed model is applied to the stock price index forecasting. This study then examines the predictability of integrated neural network models and compares the performance of data mining classifiers.
A Realtime Analytical System of Football Game
Min, Dae-kee ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 557~564
The objective of he study is to record the real conditions along with the soccer ball that is, each player's ball keeping time, the number football keeping, accuracy of passing to other player, direction, etc., on a real-time basis, measure them in numbers and get necessary analyzed output as much as one needs. The study consists of the following stages: (1) Record the data by drawing through Visual Interface on a real-time basis; (2) Graphic windows to display the recorded data item by item in graphic; (3) Form windows to display the individual or team scores anytime when needed; (4) Windows to display the analyzed data in visualized form. The effect of the study is threefold: (1) It inputs all the game-related data on a real-time basis, which was impossible before and shows analyzed contents during the game enabling each tea manager o use; (2) In cse of TV broadcasting or newspaper articles, it explains objectively the situations of he game to the TV viewers or readers; (3) After the game, it provides importance information on each team's playing ability and individual player's technical improvement through data analysis.
Ergodicity of Nonlinear Autoregression with Nonlinear ARCH Innovations
Hwang, S.Y. ; Basawa, I.V. ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 565~572
This article explores the problem of ergodicity for the nonlinear autoregressive processes with ARCH structure in a very general setting. A sufficient condition for the geometric ergodicity of the model is developed along the lines of Feigin and Tweedie(1985), thereby extending classical results for specific nonlinear time series. The condition suggested is in turn applied to some specific nonlinear time series illustrating that our results extend those in the literature.
Noise-free Distributions Comparison of Bayesian Wavelet Threshold for Image Denoise
Choi, Ilsu ; Rhee, Sung-Suk ; Ahn, Yunkee ;
Communications for Statistical Applications and Methods, volume 8, issue 2, 2001, Pages 573~579
Wavelet thresholding is a method for he reduction of noise in image. Wavelet coefficients of image are correlated in local characterization. Thee correlations also appear in he original pixel representation of the image, and they do not follow from the characterizations of the wavelet transform. In this paper, we compare noise-free distributions of Bayes approach to improve the classical threshold algorithm.