Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Korean Journal of Applied Statistics
Journal Basic Information
Journal DOI :
The Korean Statistical Society
Editor in Chief :
Volume & Issues
Volume 7, Issue 2 - Sep 1994
Volume 7, Issue 1 - Feb 1994
Selecting the target year
On the behavior od Winsorized
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 1~7
Using a Monte-Carlo simulation technique we evaluate the empiricla distribution of a pseudo-chi-square statistic based on symmetrically Winsorized sum of squares when the population is normally distributed, and search for a chi-square distribution with appropriate degrees of freedom which can be referred to an approximate distribution for Winsorized chi-square.
Posterior density estimation of Kappa via Gibbs sampler in the beta-binomial model
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 9~19
Beta-binomial model, which is reparametrized in terms of the mean probability
of a positive deagnosis and the
of agreement, is widely used in psychology. When
is close to 0, inference about
become difficult because likelihood function becomes constant. We consider Bayesian approach in this case. To apply Bayesian analysis, Gibbs sampler is used to overcome difficulties in integration. Marginal posterior density functions are estimated and Bayesian estimates are derived by using Gibbs sampler and compare the results with the one obtained by using numerical integration.
Sensitivity analysis for performance measures in the M/M/1 Queue
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 21~34
In this paper we consider the M/M/1 Queue with mean inter arrival time
. We derive a sample path estimator for the derivative of steady state mean system time with respect to
. We also show that the derived sample path estimate can be expressed as a sum of the IPA estimate and the other effect. We have a similar result for the derivative of limiting probability
with respect to
An Overview of Group Sequential Procedures
Jae Won Lee ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 35~51
For ethical and economic reasons, clinicla trials must be repeatedly monitored for evidence of treatment benefit or harm. Repeated testing at conventional critical values can substantially inflate the overal type I error rate. To maintain acceptable levels, group sequential procedures have been developed for clinical trials. This article gives a brief overview of the group sequential procedures.
On the analysis of multistate survival data using Cox's regression model
Sung Chil Yeo ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 53~77
In a certain stochastic process, Cox's regression model is used to analyze multistate survival data. From this model, the regression parameter vectors, survival functions, and the probability of being in response function are estimated based on multistate Cox's partial likelihood and nonparametric likelihood methods. The asymptotic properties of these estimators are described informally through the counting process approach. An example is given to likelihood the results in this paper.
Weighted log rank test for late differences
Gyu Jin Jeong ; Sang Gue Park ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 79~88
Weighted log rank test is a widely applicable test when one is interested in detecting the differences between two groups. In man clinical trials it is common to see no differences in early experiments and does show significant differences later. We propose new weighted log rank test and illustrate it through an example. We also examine the empirical powers and show that the proposed test is more sensitive to detect late differences.
Estimator of the Mean Residual Life for Some Parametric Families
Kuey Chung Choi ; Kyung Hyun Nam ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 89~100
In this paper we consider a new estimator of mean residual life (MRL), based on the partial moment of the distribution. The parameters of a partial moment are estimated by its maximum likelihood estimators when the underlying distribution is known. Though the new estimator is not a consistent estimator of the MRL, it is shown to have smaller mean squared error than the well known empirical MRL estimator for certain parametric families. Numerical summaries of the mean squared errors of the new estimator are presented.
Software Reliability Model with Multiple Change-Points
Dong Hoon Lim ; Dong Hee Kim ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 101~111
In this paper, we can see that software reliability model has been improved by considering multiple change-points. The condition for the existence of maximum likelihood estimate of the initial error content of a program is given and the maximum likelihood estimations of multiple change-points are derived. We assess the performance of our multiple change-points model on numerical applicaiton.
Further development in the integration of multimodal functions by Monte Caro importance sampling
Man Suk Oh ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 113~130
The algorithm of Oh and Berger (1993) is extended to handle more general cases where the integrand $f(\theta)$ is not only multimodal but also skewed or has some undetected modes, each having curvature not much different from that of the nearest component. It runs Oh and Berger's algorithm in an iterative way, adding a component in each stage to the mixture importance function from previous stage for better approximation between $f(\theta)$ and the importance function.
A Study on Bayes and Empirical Bayes Estimates of Poisson Means under Asymmetric Loss Functions
Youn Shik Chung ; Chan Soo Kim ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 131~143
Under the asymmetric losses (entropy loss and Stein loss), we find the classes of Bayes and empiricla Bayes estimates for estimating the Poisson means when the distributin of means are believed a priori. Following the idea of Efron and Morris (1973), we have a computer simulation to compute a relative savings loss of proposed estimates as compared to the classical estimates.
Estimation from Incomplete Data in Multivariate Distributions under Stochastic Ordering
Kwang Mo Jeoung ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 145~157
For multivariate distributions satisfying stochastic ordering, we suggest maximum likelihood estimation with incomplete data via an EM algorithm. In this paper we restrict our attention to the contingency tables with partially cross-classified observations. We may use the existing isotonic regression program to implement EM algorithm, and we illustrate the estimation process through an example.
k-Sample Rank Tests for Umbrella Location-Scale Alternatives
Hee Moon Park ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 159~171
Some rank score tests are proposed for testing the equality of all sampling distribution functions against umbrella location-scale alternatives in k-sample problem. Only the case of known peak
is considered. Under the null hypothesis and a contiguous sequence of unbrella location-scale alternatives, the asymptotic properties of the proposed test statistics are investigated. Also, the asymptotic local powers are compared with each others. The results show that the tests based on the Chen-Wolfe rank analogue statistic are more powerful than others for unequally spaced umbrella location-scale alternatives and robust.
Asymptotically Efficient L-Estimation for Regression Slope When Trimming is Given
Sang Moon Han ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 173~182
By applying slope estimator under the arbitrary error distributions proposed by Han(1993), if we define regression quantiles to give upper and lower trimming part and blocks of data, we show the proposed slope estimator has asymptotically efficient slope estimator when the number of regression quantiles to from blocks of data goes to sufficiently large.
Sequential Designs for Complex Computer Experiments with an Application to a Nuclear Fusion Model
Jeong Soo Park ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 183~200
Data-adaptive sequential suboptimal designs for very complex computer simulation codes are considered based on a spatial prediction model. These designs are constructed for two simulators of the computational nuclear fusion devices model. The difficulty of constructing the optimal designs due to the irregular design region, and its alternatives are also discussed with some computational algorithms for obtaining the designs.
Detection of Influential Interaction Effects in Parameter Design
Sang Ik Kim ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 201~211
Ignoring interaction effects has been pointed out to be one of serious drawbacks in analysis of the parameter designs which are constructed by using orthogonal arrays. In this paper a detecting procedure of influential 2-factor inteactions with minimum expeimental runs is described, when each contrl factor has two levels. The presented method is based on the near orthogonal arrays which are very similar to orthogonal arrays in the statistical structure. And those arrarys are the same as trace-optimal balanced saturated two-level fractional factorial designs of resolution V.
Influence in Testing the Equality of Two Covariance Matrices
Myung Geun Kim ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 213~224
A diagnostic method useful for detecting outliers in testing the equality of two covariance metrics is developed using the influence curve approach. This method is easily generalized to more than two covariance matrices. A sample version for the influence measure of detecting outliers is considered based on the empirical distribution functions. The sample version includes as its component terms the well-known test statistic for detecting one outlier at a time introduced by Wilks and its generalization to the two-group case.
A Generalized Likelihood Ratio Test in Outlier Detection
Jang Sun Baek ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 225~237
A generalized likelihood ratio test is developed to detect an outlier associated with monitoring nuclear proliferation. While the classical outlier detection methods consider continuous variables only, our approach allows both continuous and discrete variables or a mixture of continuous and discrete variables to be used. In addition, our method is free of the normality assumption, which is the key assumption in most of the classical methods. The proposed test is constructed by applying the bootstrap to a generalized likelihood ratio. We investigate the performance of the test by studying the power with simulations.
Estimation for the Exponential ARMA Model
Won Kyung Kim ; In Kyu Kim ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 239~248
The Yule-Walker estimator and the approximate conditional least squares estimator of the parameter of the EARMA(1, 1) model are obtained. These two estimators are compared by simulation study. It is shown that the approximate conditional least squares estimator is better in the sense of the mean square error than the Yul-Walker estimator.
On the estimation of parameters for the growth curve of the Korean Population
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 249~261
The purpose of this research is to obtain a Simple Logistic Curve for the curve fitting of Korean total Population. Based on the population census data from 1949 to 1990, the parameters are estimated by 3-group method. As the results, intercensal populations of Korea from 1950 to 190 are estimated, and Korean total populations from 1991 to 2010 A.D. are projected. And we also can suggest the upper asymptote 58, 616 thousands of Korean total population.
On Bayes' uniform prior
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 263~268
Thomas Bayes assumed uniform prior for the location
of a billiard ball W in his historic 1764 paper. In this study, following mathematical derivation of the uniform distribution from several assumptions that are plausible on te billiard table, it is argued that the probabilistic meaning of Bayes' uniform prior (especially in Billiard Problem) is not just sujective but logical.
Minimum Chi-square estimation and the bootstrap
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 269~277
Bootstrap approximation is compared with ordinary asymptotic method in the context of minimum chi-square estimation through application in a real problem. Fixed interval search method is shown to be superior over a random interval search method or Newton-Raphson method. All the procedures are implemented by S-Plus functions.
Developing a Korean statistical package
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 279~288
Most of the statistical packages being used in Korea, such as SAS or SPSS, are imported from foreign countries. Since these package are written in English, it is not easy for Korean to learn the statistical packages. Also, most of the users except statistician use these expensive packages only to draw pictures and to make tables. We introduce a Korean statistical package which can be used easily for general public.
A study on the structure of concordance matrices of Li type PBIB designs
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 289~297
A block design will be said to have Property C if the concordance matrix can be expressed as a linear combination of Kronecker product of permutation matrices. No matrix inversions are necessary for the intrablock analysis of the block designs which possesses the Property C(Paik, 1985). In this paper, in order to show the Li type PBIB designs possesses the Property C, we suggest the structure of the concordance matrices of Li type PBIB designs are multi-nested block circulant pattern.
Detection of local structural chages in time series
Jae June Lee ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 299~311
In time series data, atypical observations are not rare. Several approaches have been proposed to detect a single outlier, but the effectiveness of those procedures is in doubt when patchy outliers are present. In this paper, the atypicality in patchy outliers is interpreted as a local structural change, and a model is introduced to entertain its effect on the series. Based on this model, a statistic and a procedure are proposed for identifying those local structural changes. The performance of the proposed procedure is evaluated through simulation study and the analysis of real data sets.
Jackknife parametric estimation in the two parameter exponential model with an identified outlier
Jung Soo Woo ; Chang Soo Lee ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 313~321
When a single identified outlier in a small sample is presented, the samll sample properties of the MLE's and its jackknife estimators of the location and scale parameters in an assumed exponential model will be considered by the method of permanent theory.
Discrete approximation to the optimal density in moment problems
Chang Kon Hong ;
Korean Journal of Applied Statistics, volume 7, issue 2, 1994, Pages 323~333
In this paper we present some approximation theorems related to the problem of finding optimal densities with prescribed moments. The implementation of the approximation theorems is to be done in some examples.