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 7, Issue 3 - Dec 2000
Volume 7, Issue 2 - Aug 2000
Volume 7, Issue 1 - Apr 2000
Selecting the target year
Outlier Identification in Regression Analysis using Projection Pursuit
Kim, Hyojung ; Park, Chongsun ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 633~641
In this paper, we propose a method to identify multiple outliers in regression analysis with only assumption of smoothness on the regression function. Our method uses single-linkage clustering algorithm and Projection Pursuit Regression (PPR). It was compared with existing methods using several simulated and real examples and turned out to be very useful in regression problem with the regression function which is far from linear.
Fuzzy Linear Regression Model Using the Least Hausdorf-distance Square Method
Choi, Sang-Sun ; Hong, Dug-Hun ; Kim, Dal-Ho ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 643~654
In this paper, we review some class of t-norms on which fuzzy arithmetic operations preserve the shapes of fuzzy numbers and the Hausdorff-distance between fuzzy numbers as the measure of distance between fuzzy numbers. And we suggest the least Hausdorff-distance square method for fuzzy linear regression model using shape preserving fuzzy arithmetic operations.
Testing for A Change Point by Model Selection Tools in Linear Regression Models
Yoon, Yong-Hwa ; Kim, Jong-Tae ; Cho, Kil-Ho ; Shin, Kyung-A ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 655~665
Several information criterions, Schwarz information criterion (SIC), Akaike information criterion (AIC), and the modified Akaike information criterion (
), are proposed to locate a change point in the multiple linear regression model. These methods are applied to a stock Exchange data set and compared to the results.
Identifying Multiple Leverage Points ad Outliers in Multivariate Linear Models
Yoo, Jong-Young ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 667~676
This paper focuses on the problem of detecting multiple leverage points and outliers in multivariate linear models. It is well known that he identification of these points is affected by masking and swamping effects. To identify them, Rousseeuw(1985) used robust estimators of MVE(Minimum Volume Ellipsoids), which have the breakdown point of 50% approximately. And Rousseeuw and van Zomeren(1990) suggested the robust distance based on MVE, however, of which the computation is extremely difficult when the number of observations n is large. In this study, e propose a new algorithm to reduce the computational difficulty of MVE. The proposed method is powerful in identifying multiple leverage points and outlies and also effective in reducing the computational difficulty of MVE.
Improved Algorithm for Case-Deletion Diagnostic in Mixed Linear Models
Lee, Jang-Teak ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 677~686
Outliers may occur with respect to any of the random components in mixed linear models. We develop a use of simple, inexpensive updating formulas to consider the effect of case-deletion for mixed linear models. The method described here requires inversions of an n x n matrix, where n is the number of nonempty cells. A numerical example illustrates the use of computational formulas.
Identification of Multiple Outlying Cells in Multi-way Tables
Lee, Jong Cheol ; Hong, Chong Sun ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 687~698
An identification method is proposed in order to detect more than one outlying cells in multi-way contingency tables. The iterative proportional fitting method is applied to get expected values of several suspected outlying cells. Since the proposed method uses minimal sufficient statistics under quasi log-linear models, expected counts of outlying cells could be estimated under any hierarchical log-linear models. This method is an extension of the backwards-stepping method of Simonoff(1988) and requires les iteration to identify outlying cells.
Constrained Estimation of the Numbers of Trials in Several Binomial Populations
Oh, Myongsik ; Lee, Eun-Kyoung ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 699~709
The constrained maximum likelihood estimation of the number of trials in several binomial populations under order restriction, such as simple order, is discussed. The estimation procedure is based on, so called, pool adjacent violators algorithm. Three handy estimators are given and their performances are compared using an artificial example.
MARS Modeling for Ordinal Categorical Response Data: A Case Study
Kim, Ji-Hyun ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 711~720
A case study of modeling ordinal categorical response data with the MARS method is done. The study is to analyze the effect of some personal characteristics and socioeconomic status on the teenage marijuana use. The MARS method gave a new insight into the data set.
A Conditional Randomized Response Model for Detailed Survey
Lee, Gi-Sung ; Hong, Ki-Hak ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 721~729
In this paper, we propose a new conditional randomized response model that has improved the Carr et al.'s model in view of he variance and the protection of privacy of respondents. We show that he suggested model is more effective and protective than the Loynes' model and Carr et al.' model.
Conditional Least Squares Estimators of the Parameters of the NLAR(p) Time Series Model
Kim, Won-Kyung ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 731~739
Conditional least square estimators for the parameters of he NLAR(p) time series models are obtained. it is also shown that these estimators are consistent and asymptotically normal.
Evaluation of the Block Effects in Response Surface Designs with Random Block Effects over Cuboidal Regions
Park, Sang-Hyun ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 741~757
In may experimental situations, whenever a block design is used, the block effect is usually considered to be fixed. There are, however, experimental situations in which it should be treated as random. The choice of a blocking arrangement for a response surface design can have a considerable effect on estimating the mean response and on the size of he prediction variance even if the experimental runs re the same. Therefore, care should be exercised in the selection of blocks. In this paper, in the presence of a random block effect, we propose a graphical method or evaluating the effect of blocking in response surface designs using cuboidal regions. This graphical method can be used to investigate how the blocking has influence on the prediction variance throughout all experimental regions of interest when this region is cuboidal, and compare the block effects in the cases of the orthogonal and non-orthogonal block designs, respectively.
fractional Factorial Design Excluded SOme Debarred Combinations
Choi, Byoung-Chul ; Kim, Hyuk-Joo ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 759~766
In order to design fractional factorial experiments which include some debarred combinations, we should select defining contrasts so that those combinations are to be excluded. Choi(1999) presented a method of selectign defining contrasts to construct orthogonal 3-level fractional factorial experiments which exclude some debarred combinations. In this paper, we extend Choi's method to general p-level fractional factorial experiments to select defining contrasts which cold exclude some debarred combinations.
Improved Estimation of Poisson Menas under Balanced Loss Function
Chung, Younshik ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 767~772
Zellner(1994) introduced the notion of a balanced loss function in the context of a general liner model to reflect both goodness of fit and precision of estimation. We study the perspective of unifying a variety of results both frequentist and Bayesian from Poisson distributions. We show that frequentist and Bayesian results for balanced loss follow from and also imply related results for quadratic loss functions reflecting only precision of estimation. Several examples are given for Poisson distribution.
A Combined Process Control Procedure by Monitoring and Repeated Adjustment
Park, Changsoon ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 773~788
Statistical process control (SPC) and engineering process control (EPC) are based on different strategies for processes quality improvement. SPC reduces process variability by detecting and eliminating special causes of process variation. while EPC reduces process variability by adjusting compensatory variables to keep the quality variable close to target. Recently there has been needs for a process control proceduce which combines the tow strategies. This paper considers a combined scheme which simultaneously applies SPC and EPC techniques to reduce the variation of a process. The process model under consideration is an integrated moving average(IMA) process with a step shift. The EPC part of the scheme adjusts the process back to target at every fixed monitoring intervals, which is referred to a repeated adjustment scheme. The SPC part of the scheme uses an exponentially weighted moving average(EWMA) of observed deviation from target to detect special causes. A Markov chain model is developed to relate the scheme's expected cost per unit time to the design parameters of he combined control scheme. The expected cost per unit time is composed of off-target cost, adjustment cost, monitoring cost, and false alarm cost.
A Family of Tests for Trend Change in Mean Residual Life with Known Change Point
Na, Myung-Hwan ; Kim, Jae-Joo ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 789~798
The mean residual function is the expected remaining life of an item at age x. The problem of trend change in the mean residual life is great interest in the reliability and survival analysis. In this paper, we develop a family of test statistics for testing whether or not the mean residual life changes its trend. The asymptotic normality of the test statistics is established. Monte Carlo simulations are conducted to study the performance of our test statistics.
Nonparametric Test for Multivariate Location Translation Alternatives
Na, Jong-Hwa ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 799~809
In this paper we propose a nonparametric one sided test for location parameters in p-variate(p
2) location translation model. The exact null distributions of test statistics are calculated by permutation principle in the case of relatively small sample sizes and the asymptotic distributions are also considered. The powers of various tests are compared through computer simulation and thep-values with real data are also suggested through example.
Data-Driven Smooth Goodness of Fit Test by Nonparametric Function Estimation
Kim, Jongtae ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 811~816
The purpose of this paper is to study of data-driven smoothing goodness of it test, when the hypothesis is complete. The smoothing goodness of fit test statistic by nonparametric function estimation techniques is proposed in this paper. The results of simulation studies for he powers of show that the proposed test statistic compared well to other.
Bayesian Analysis for Random Effects Binomial Regression
Kim, Dal-Ho ; Kim, Eun-Young ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 817~827
In this paper, we investigate the Bayesian approach to random effect binomial regression models with improper prior due to the absence of information on parameter. We also propose a method of estimating the posterior moments and prediction and discuss some general methods for studying model assessment. The methodology is illustrated with Crowder's Seeds Data. Markov Chain Monte Carlo techniques are used to overcome the computational difficulties.
Bayesian Estimations of the Smaller and Larger for Two Pareto Scale Parameters
Woo, Jungsoo ; Lee, Changsoo ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 829~836
We shall derive Bayes estimators for he smaller and larger of two Pareto scale parameters with a common known shape parameter when the order of the scales is unknown and sample sizes are equal under squared error loss function. Also, we shall obtain biases and man squared errors for proposed Bayes estimators, and compare numerically performances for the proposed Bayes estimators.
A Note on Bootstrapping M-estimators in TAR Models
Kim, Sahmyeong ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 837~843
Kreiss and Franke(192) and Allen and Datta(1999) proposed bootstrapping the M-estimators in ARMA models. In this paper, we introduce the robust estimating function and investigate the bootstrap approximations of the M-estimators which are solutions of the estimating equations in TAR models. A number of simulation results are presented to estimate the sampling distribution of the M-estimators, and asymptotic validity of the bootstrap for the M-estimators is established.
A Note on the Weak Negative Dependence Structure
Baek, J.I. ; Kim, T.S. ; Park, D.H. ; Lim, J.H. ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 845~858
In this paper new results are obtained for multivariate processes which help us to identify weak negative orthant dependent(WNOD) structures among hitting times of the processes. Furthermore, an approach to derive dependence properties among the processes is proposed and a partial solution to the question tat what kinds of the dependence properties, when they are imposed on processes, are reflected as analogous properties of corresponding hitting times is give. Examples are given to illustrate these concepts.
A Simulation Study for the Confidence Intervals of p by Using Average Coverage Probability
Kim, Daehak ; Jeong, Hyeong-Chul ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 859~869
In this paper, various methods for finding confidence intervals for p of binomial parameter are reviewed. Also we introduce tow bootstrap confidence intervals for p. We compare the performance of bootstrap methods with other methods in terms of average coverage probability by Monte Carlo simulation. Advantages of these bootstrap methods are discussed.
Comparison of Perturbation Analysis Estimate and Forward Difference Estimate in a Markov Renewal Process
Park, Heung-sik ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 871~884
Using simulation, we compare the perturbation analysis estimate and the forward difference estimate for the first and second derivatives of performance measures in a Markov renewal process. We find the perturbation analysis estimate has much les mean squared error than the traditional forward difference estimate.
Latent Variable Fit to Interlaboratory Studies
Jeon, Gyeongbae ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 885~897
The use of an unweighted mean and of separate tests is part of the current practice for analyzing interlaboratory studies, and we hope to improve on this method. We fit, using maximum likelihood(ML), a rather intricate, multi-parameter measurement model with the material's true value as a latent variable in a situation where quite serviceable regression and ANOVA calculations have already been developed. The model fit leads to both a weighted estimate of he overall mean, and to tests for equality of means, slopes and variances. Maximum likelihood tests for difference among variances poses a challenge in that the likelihood can easily becoem unbounded. Thus the major objective become to provide a useful test of variance equality.
A Comparison of Some Approximate Confidence Intervals for he Poisson Parameter
Kim, Daehak ; Jeong, Hyeong-Chul ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 899~911
In this paper, we reviewed thirteen methods for finding confidence intervals for he mean of poisson distribution. Bootstrap confidence intervals are also introduced. Two bootstrap confidence intervals are compared with the other existing eleven confidence intervals by using Monte Carlo simulation with respect to the average coverage probability of Woodroofe and Jhun (1989).
Implementation of Estimation and Inference on the Web
Kang, Heemo ; Sim, Songyong ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 913~926
An electronic statistics text on the web is implemented. The introduced text provide interactive instructions on the statistical estimation and inference. As a by-product, we also provide a calculation of quantiles and p-value of t-distribution and standard normal distribution. This program was written in JAVA programming language.
Internet Poll System
Kim, Yon-Hyong ; Oh, Min-Gweon ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 927~935
In this paper we propose a poll system n the internet. This system expects to increase the confidence of the internet poll results by sampling theory(proportional allocation). This system provides a cross-tale and result of hypothesis test which plays an important role for decision making. These results do offer a few statistical packages(such as SAS, SPSS) in the world wide web.
Interpretation of Data Mining Prediction Model Using Decision Tree
Kang, Hyuncheol ; Han, Sang-Tae ; Choi, Jong-Ho ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 937~943
Data mining usually deal with undesigned massive data containing many variables for which their characteristics and association rules are unknown, therefore it is actually not easy to interpret the results of analysis. In this paper, it is shown that decision tree can be very useful in interpreting data mining prediction model using two real examples.
Internet Survey Methodology
Lee, Hae-Yong ; Kim, Kee-Whan ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 945~953
Since early 1960s, when the telephone survey was used in the research area for he first tie, there has been existed various methods to gather the information by survey. The existing survey methodology called PAPI(Paper-And-Pen Interveiw), due to the appearance of Personal Computer, might well be developed progressively. Mid-1980s, Internet was advanced remarkably in terms of technology. from early 1990s, in addition it served as a stepping-stone for progressive collecting method. Internet Survey is now called WWW Survey and expected that it will substitute for most surveys from now on. We explain the role and the characteristics for Internet Survey as one of he various data collecting methods. Furthermore, we draw the futures about questionnaires, data collecting and statistical analysis with it.
A Note on Spacings
Kim, S.H. ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 955~958
In this paper, it will be shown that if the distribution function F of X is increasing (decresign) failure rate, then the spacings are engatively( Positively) dependent. Some numberical exmamples are illustrated.
Some Asymptotic Properties of Conditional Covariance in the Item Response Theory
Kim, Hae-Rim ;
Communications for Statistical Applications and Methods, volume 7, issue 3, 2000, Pages 959~966
A dimensionality assessment procedure DETECT uses the property of being near zero of conditional covariances as an indication of unidimensionality .This study provides the convergent properties to zero of conditional covariances when the dta is unidimensional, with which DETECT extends its theoretical grounds.