Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
search word
HOME
>
Journal Browse
>
About Journal
> Journal Vol & Issue
Communications for Statistical Applications and Methods
Journal Basic Information
pISSN :
2287-7843
eISSN :
2383-4757
Journal DOI :
10.5351/CSAM
Frequency :
Others
Publisher:
The Korean Statistical Society
Editor in Chief :
Byeong-Chan Seong
Volume & Issues
Volume 6, Issue 3 - Dec 1999
Volume 6, Issue 2 - Aug 1999
Volume 6, Issue 1 - Apr 1999
Selecting the target year
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004
2003
2002
2001
2000
1999
1998
1997
1996
1995
1994
All
1
Support Vector Machine for Linear Regression
Hwang, Changha ; Seok, Kyungha ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 337~344
Abstract
Support vector machine(SVM) is a new and very promising regression and classification technique developed by Vapnik and his group at AT&T Bell laboratories. This article provides a brief overview of SVM focusing on linear regression. We explain from statistical point of view why SVM might be attractive and how this could be compared with other linear regression techniques. Furthermore. we explain model selection based on VC-theory.
2
Asymptotic Properties of a Robust Estimator for Regression Models with Random Regressor
Chang, Sook-Hee ; Kim, Hae-Kyung ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 345~356
Abstract
This paper deals with the problem of estimating regression coefficients in nonlinear regression model having random regressor. The sufficient conditions for consistency of the
-estimator with random regressor are given and discussed in this paper. An example is given to illustrate the application of the main results.
3
A Simulation Approach for Testing Non-hierarchical Log-linear Models
Park, Hyun-Jip ; Hong, Chong-Sun ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 357~366
Abstract
Let us assume that two different log-linear models are selected by various model selection methods. When these are non-hierarchical it is not easy to choose one of these models. In this paper the well-known Cox's statistic is applied to compare these non-hierarchical log-linear models. Since it is impossible to obtain the analytic solution about the problem we proposed a alternative method by extending Pesaran and pesaran's (1993) simulation approach. We find that the values of proposed test statistic and the estimates are very much stable with some empirical results.
4
Determination of the Number of Components in Spectroscopy from the Multilinear Model Fitting
Kim, Choong-Rak ; Chung, Byung-Chull ; Lee, Choon-Hwan ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 367~374
Abstract
Biological specimens contain several components and multilinear models are very useful in analyzing these data. After fitting the model the number of components are determined by the change of mean squared error however this method is quite rule of thumb. in this paper we suggest a measure to decide the number of components based on the relative change of to mean squared error. Simulations are done and applications to real data set are given as illustrations.
5
Sensitivity Analysis for Ordered Categorical Data
Cho, Il-Hyun ; Park, Taesung ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 375~382
Abstract
Linear-by-linear association models are commonly used to analyze ordered categorical data. To fit these models appropriate scores need to be chosen. In this paper we perform sensitivity analyses in two-way contingency tables to investigate the effect of scores on goodness-of-fits and on tests of significance. In addition we show that the best score which yields the best fit of data can be selected based on the sensitivity analysis results.
6
Evaluating Predictive Ability of Classification Models with Ordered Multiple Categories
Oong-Hyun Sung ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 383~395
Abstract
This study is concerned with the evaluation of predictive ability of classification models with ordered multiple categories. If categories can be ordered or ranked the spread of misclassification should be considered to evaluate the performance of the classification models using loss rate since the apparent error rate can not measure the spread of misclassification. Since loss rate is known to underestimate the true loss rate the bootstrap method were used to estimate the true loss rate. thus this study suggests the method to evaluate the predictive power of the classification models using loss rate and the bootstrap estimate of the true loss rate.
7
Recurrence Relations in the Fisher Information in Order Statistics
Park, Sang-Un ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 397~402
Abstract
We first derive the Fisher information identity in order statistics in terms of the hazard rate by considering the Fisher information identity in terms of the hazard rate (Efron and Johnstone, 1990). Then we use the identity and show an interesting and useful result that some identities and recurrence relations for the Fisher information in order statistics can be directly obtained from those between the c.d.f.s of order statistics.
8
Block Replacement Policy by Multiple Choice with Used Items
Jeong, Hai-Sung ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 403~412
Abstract
A block replacement policy where at failure the item is either replaced by a new or used item or remains inactive until the next planned replacement is considered. in this paper our interests are focused on reusing all the used items created by the policy. Numerical results for the case where the underlying life distribution is gamma are obtained.
9
EWMA Control Charts to Monitor Correlation Coefficients
Chang, Duk-Joon ; Cho, Gyo-Young ; Lee, Jae-Man ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 413~422
Abstract
Multivariate EWMA control charts to simultaneously monitor correlation coefficients of correlated quality characteristics under multivariate normal process are proposed. Performances of the proposed charts are measured in terms of average run length(ARL). Numerical results show that smalle values for smoothing constant with accumulate-combine approach are preferred for detecting smalle shifts.
10
Accelerated Life Testings for System based on a Bivariate Exponential Model
Park, Byung-Gu ; Yoon, Sang-Chul ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 423~432
Abstract
Accelerated life testing of product is commonly used to reduced test time and costs. In this papers is considered when the product is a two component system with lifetimes following the bivariate exponential distribution of Sarkar(1987) using inverse power rule model. Also we derived the maximum likelihood estimators of parameters for asymptotic normality. We compare the mean square error of the proposed estimator for the life distribution under use conditions stree through Monte Carlo simulation.
11
A Model for a State-Dependent Deteriorating System
Lee, Ji-Yeon ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 433~442
Abstract
A model for a system whose deteriorating rate depends on the state is introduced. A repairman arrives according to Poisson process and increases the state of the system by the random amount if the state is below a threshold. If the system fails at arrival of the repairman it is assumed that the system is replaced by new one. The stationary distribution function of the state of the system and the expected life length of the system are deduced.
12
Mixed Replacement Designs for Life Testing with Interval Censoring
Tai Sup ; kesar Singh ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 443~456
Abstract
The estimation of mean lifetimes in presence of interval censoring with mixed replacement procedure are examined when the distribution s of lifetimes are exponential. it is assumed that due to physical restrictions and/or economic constraints the number of failures is investigated only at several inspection times during the lifetime test; thus there is interval censoring. Comparisons of mixed replacement designs are made with those with and without replacement The maximum likelihood estimator is found in an implicit form. The Cramer-Rao lower bound which is the asymptotic variance of the estimator is derived. The test conditions for minimizing the Cramer-Rao lower bound and minimizing the test costs within a desired width of the Cramer-Rao bound have been studied.
13
On Centralizing the Modified Systematic Sampling Method for Populations with Linear Trends
Kim, Hyuk-Joo ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 457~466
Abstract
Centered modified systematic sampling (CMSS)' was proposed by Kim(1985) for estimating the mean of a population with a linear trend. In the present paper a version of this sampling method is suggested. This version turns out to be efficient in the same degree as the original method from the viewpoint of the expected mean square error criterion. It is also shown to be quite an efficient method as compared with other existing methods. An illustrative example is given.
14
Change-point Estimators Using Rank Average in Location Change Model
Kim, Jeahee ; Jang, Heeyoon ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 467~478
Abstract
This paper deals with the problem of change-point estimation where there is one level change in location with iid errors. A change-point estimator using rank average is proposed with the proof of its consistency. A comparison study of various change-point estimators is done by simulation on the mean the proportion and the variance when the errors are from the normal and the double exponential distributions.
15
Page Type Test for Ordered Alternatives on Multiple Ranked Set Samples.
Kim, Dong-Hee ; Kim, Young-Cheol ; Kim, Hyun-Gee ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 479~486
Abstract
In this paper we propose the test statistic for ordered alternatives on multiple ranked set samples. Since the proposed test statistic is Page type its asymptotic properties are easily obtained. From the simulation works we calculate the power of test statistic(
) under the underlying distributions such as uniform normal double exponential logistic and Cauchy distribution.
16
Hierarchical Bayes Estimators of the Error Variance in Balanced Fixed-Effects Two-Way ANOVA Models
Kim, Byung-Hwee ; Dong, Kyung-Hwa ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 487~500
Abstract
We propose a class of hierarchical Bayes estimators of the error variance under the relative squared error loss in balanced fixed-effects two-way analysis of variance models. Also we provide analytic expressions for the risk improvement of the hierarchical Bayes estimators over multiples of the error sum of squares. Using these expressions we identify a subclass of the hierarchical Bayes estimators each member of which dominates the best multiple of the error sum of squares which is known to be minimax. Numerical values of the percentage risk improvement are given in some special cases.
17
A Comparative Study on Bayes Estimators for the Multivariate Normal Mcan
Kim, Dal-Ho ; Lee, In suk ; Kim, Hyun-Sook ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 501~510
Abstract
In this paper, we consider a comparable study on three Bayes procedures for the multivariate normal mean estimation problem. In specific we consider hierarchical Bayes empirical Bayes and robust Bayes estimators for the normal means. Then three procedures are compared in terms of the four comparison criteria(i.e. Average Relative Bias (ARB) Average Squared Relative Bias (ASRB) Average Absolute Bias(AAB) Average Squared Deviation (ASD) using the real data set.
18
Robustness in the Hierarchical Bayes Estimation of Normal Means
Kim, Dal-Ho ; Park, Jin -Kap ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 511~522
Abstract
The paper considers the problem of robustness in hierarchical bayesian models. In specific we address Bayesian robustness in the estimation of normal means. We provide the ranges of the posterior means under
-contamination class as well as the density ratio class of priors. For the class of priors that are uniform over a specified interval we investigate the sensitivity as to the choice of the intervals. The methods are illustrated using the famous baseball data of Efron and Morris(1975).
19
Bayesian Methods for Generalized Linear Models
Paul E. Green ; Kim, Dae-Hak ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 523~532
Abstract
Generalized linear models have various applications for data arising from many kinds of statistical studies. Although the response variable is generally assumed to be generated from a wide class of probability distributions we focus on count data that are most often analyzed using binomial models for proportions or poisson models for rates. The methods and results presented here also apply to many other categorical data models in general due to the relationship between multinomial and poisson sampling. The novelty of the approach suggested here is that all conditional distribution s can be specified directly so that staraightforward Gibbs sampling is possible. The prior distribution consists of two stages. We rely on a normal nonconjugate prior at the first stage and a vague prior for hyperparameters at the second stage. The methods are demonstrated with an illustrative example using data collected by Rosenkranz and raftery(1994) concerning the number of hospital admissions due to back pain in Washington state.
20
On the Development of Statistical Software using Microsoft COM Technology on the Internet Environment
Han, Kyung-Soo ; Kim, Seok-Ki ; Choi, Sook-Hee ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 533~542
Abstract
Widespread of internet causes rapid changes in many areas of statistics such as statistical computation and education. In this paper the efficient methods for statistical software development on the internet environment are introduced. Also the developed examples about monte-carlo permutation tests for two-way contingency tables using Microsoft COM (Component Obejct Model) technology are presented.
21
Estimation of Maximal Tolerated Dose in Sequential Phase I Clinical Trials
Park, In-Hye ; Song, Hae-Hiang ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 543~564
Abstract
The principal aim of a sequential phase I clinical trial in which the toxicity reponses of a group of patient(s) determine the dose level of the next patient(s) group is to estimate the maximal tolerated dose(MTD) of a new drug, In this paper we compared with a simulation study the performance of the MTD estimates that are determined by a stopping rule in a design and also those that are determined by analyzing the data after a clinical trial is terminated. To the latter belong the mean median mode and maximum likelihood estimates. For the Standard Methods the stopping rule MTD is quite inefficient but the median MTD has a best efficiency and is robust with respect to the three different toxicity curves. The problem of non-convergence of MLE MTD is severe. A more improved MTD estimate is produced by combining the advantages of the various MTD estimates and its efficiency is better than the single median MTD estimate especially for the toxicity curve of an unlucky choice of dose levels. The simulation results suggest that simple types of phase I designs can be combined with relatively standard analytic techniques to provide a more efficient MTD estimate.
22
Application of Convariance Process to Tests for Censored Paired Data
Jeong, Gyu-Jin ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 565~584
Abstract
the covariance process of two martingales provides a useful tool to capture the dependence structure for paired censored data. in this paper it is applied to modify the variances of weighted logrank tests in order to take account of dependence between paired subjects. In the process of modification a 'variance correction term' is introduced. Some variance estimators based on separate samples are considered together. Performance of the estimators are compared through simulation studies. Several independence tests for bivariate sruvival date are also proposed which are naturally reduced from the weighted logrank tests accomodating dependence structure. Simulation studies are carried out to compare the independence tests. Both the weighted logrank tests and the independence tests are illustrated by an example.
23
Almost Sure Convergence of Randomly Weighted Sums with Application to the Efrom Bootstrap
Kim, Tae-Sung ; Kim, Hyuk-Joo ; Seok, Eun-Yang ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 585~594
Abstract
Let {
, 1
j
n,j
1} be a triangular array of random variables which are neither independent nor identically distributed. The almost sure convergences of randomly weighted partial sums of the form
$X_{nj} are studied where {Wnj 1
j
n, j
1} is a triangular array of random weights. Application regarding the Efron bootstrap is also introduced.
24
A Simple Geometric Approach to Evaluating a Bivariate Normal Orthant Probability
Lee, Kee-Won ; Kim, Yoon-Tae ; Kim, U-Jung ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 595~600
Abstract
We present a simple geometric approach which uses polar transformation and elementary trigonometry to evaluating an orthant probability in a bivariate normal distribution. Figures are provided to illustrate the situation for varying correlation coefficient. We derive the distribution of the sample correlation coefficient from a bivariate normal distribution when the sample size is 2 as an application.
25
Assessment and Interpretation of Bioequivalence for Two Drug Formulations using Crossover Design
Ko, Seoung-gon ; Oh, Hyun-Sook ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 601~610
Abstract
Crossover design is officially except for special occasions recommended by KFDA and FDA for assessing Bioequivalence between two drugs one for reference and the other for innovator. Such design is regarded as a special case of latin square split-polt or repeated measurement design and its main difference with other designing methods is that each subject in an experiment is exposed two drugs in sequence. Therefore general statistical analysis is not suitable since the model for this experiment includes carryover effect in addition to period and sequence effect. in this paper analysis for crossover model with two drugs and its interpretation are mainly discussed and an example is given for illustration.
26
Estimations for a Uniform Scale Parameter in the Presence of an Outlier
Woo, Jungsoo ; Lee, Changsoo ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 611~620
Abstract
We shall propose several estimators and confidence intervals for the scale parameter in a uniform distribution with the presence of a generalized uniform outlier and obtain mean squared errors(MSE) for their proposed estimators. And we shall compare numerical MSE's for the proposed several estimators of the scale parameter. Also we shall compare numerically expected lengths of confidence intervals of the scale parameter in a uniform distribution with the presence of a generalized uniform outlier.
27
Comparative Study of Confidence Intervals for Relative Ratio
Park, Sang-Gue ; Oh, You-Jin ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 621~634
Abstract
Consider the several methods of constructing interval for relative ration from two independent binomial samples. The special interests are gives in the cases of low rates and small samples. bias-corrected and accelerated bootstrap method is proposed to overcome are the non-efficiency of current methods based on asymptotic resuts. Simulation studies are presented to demonstrate the performance of the proposed method.
28
A Study on Computing Method of the Individual Scholastic Evaluation in the Comparative School Record
Chung, Yeon-soo ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 635~644
Abstract
This study aims at solving the problem in the application method of the comparative school record which is currently being discussed in depth among colleges. The application method of Kay O. Lee and Yeon Soo Cung(1997) which was appied in the 1999 Korean air force Academy Admission Process was found to be problematic in the following respects. First the setting of the standard which divides all the high schools in kora into five groups relative to their scholastic level is somewhat vague and subjective secondly the difference among those levels which resulted from the five grouping could greatly influence on the admission of the applicants and thirdly there is no standard in choosing those few promising individuals with high scholastic aptitude test results from the low level groups such as level four and five,. Therefore this study suggests and introduces a nationwide individual scholastic evaluation that would complement the limits and problems in the application method of the comparative school record.
29
The Limits of Bivariate Q-Q Plots Based on Matching that Minimizes a Distance
Kim, Nam-Hyun ;
Communications for Statistical Applications and Methods, volume 6, issue 2, 1999, Pages 645~658
Abstract
One of the most popular graphical techniques for goodness of fit problems is the quantile-quantile plot(Q-Q plot) Easton and McCulloch(1990) suggested a way of generalizing Q-Q plots to multivariate cases bases on finding a matching between the points of the data set whose shape is being examined and a reference sample. in this paper we investigated the asymptotic behavior of the generalized Q-Q plot for bivariate cases. As a result we concluded that the standard univariate Q-Q plot and the generalized Q-Q plot have the same limit if two variables are independent.