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 19, Issue 6 - Nov 2012
Volume 19, Issue 5 - Sep 2012
Volume 19, Issue 4 - Jul 2012
Volume 19, Issue 3 - May 2012
Volume 19, Issue 2 - Mar 2012
Volume 19, Issue 1 - Jan 2012
Selecting the target year
Variable Selection with Log-Density in Logistic Regression Model
Kahng, Myung-Wook ; Shin, Eun-Young ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 1~11
DOI : 10.5351/CKSS.2012.19.1.001
We present methods to study the log-density ratio of the conditional densities of the predictors given the response variable in the logistic regression model. This allows us to select which predictors are needed and how they should be included in the model. If the conditional distributions are skewed, the distributions can be considered as gamma distributions. A simulation study shows that the linear and log terms are required in general. If the conditional distributions of xjy for the two groups overlap significantly, we need both the linear and log terms; however, only the linear or log term is needed in the model if they are well separated.
An Alternative Composite Estimator for the Take-Nothing Stratum of the Cut-Off Sampling
Hwang, Jong-Min ; Shin, Key-Il ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 13~22
DOI : 10.5351/CKSS.2012.19.1.013
Cut-off sampling that discards a part of the population from the sampling frame, is a widely used method for a business survey. Usually, to the estimate of population total, an accurate estimate of the total of the take-nothing stratum is required. Many estimators have been developed to estimate the total of the take-nothing stratum. Recently Kim and Shin (2011) suggested a composite estimator and showed the superiority of that estimator. In this paper, we suggest an alternative composite estimator obtained by combining BLUP estimator and a ratio estimator obtained by the small samples from the take-nothing stratum. Small simulation studies are performed for a comparison of the estimators and we confirm that the new suggested estimator is superior.
Approximate Variance of Least Square Estimators for Regression Coefficient under Inclusion Probability Proportional to Size Sampling
Kim, Kyu-Seong ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 23~32
DOI : 10.5351/CKSS.2012.19.1.023
This paper deals with the bias and variance of regression coefficient estimators in a finite population. We derive approximate formulas for the bias, variance and mean square error of two estimators when we select a fixed-size inclusion probability proportional to the size sample and then estimate regression coefficients by the ordinary least square estimator as well as the weighted least square estimator based on the selected sample data. Necessary and sufficient conditions for the comparison of the two estimators in terms of variance and mean square error are suggested. In addition, a simple example is introduced to numerically compare the variance and mean square error of the two estimators.
Nonparametric Procedures for Finding the Minimum Effective Dose in Each of Several Group
Bae, Su-Hyun ; Kim, Dong-Jae ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 33~45
DOI : 10.5351/CKSS.2012.19.1.033
The primary interest of drug development studies is to estimate the smallest dose that shows a significant difference from the zero-dose control. The smallest dose is called the Minimum Effective dose(MED). In this paper, we suggest a nonparametric procedure to simultaneously find the MED of each group based on placements. The Monte Carlo simulation is adapted to estimate the power and the family-wise error rate(FWE) of the new procedures with those of discussed nonparametric tests to find MED.
Some Remarks on Consistency Test of Add-on Test in Bioequivalence Trials
Ha, Myoung-Ho ; Park, Sang-Gue ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 47~55
DOI : 10.5351/CKSS.2012.19.1.047
The newly revised bioequivalence guideline of Korea allows the add-on test since July 1, 2008 when the initial bioequivalence trial fails to show the equivalence of two drugs. The statistical model of the add-on test and its two stage testing procedures are discussed. Some statistical points of consistency test in the add-on test are considered and the issue on the sample size of add-on test is discussed. Some reasonable alternative like Japan's guideline for bioequivalence studies is recommended to secure the proper use of an add-on study through some simulation studies.
Two-Stage Maximum Tolerated Dose Estimation by Stopping Rule in a Phase I Clinical Trial
Lee, Na-Mi ; Kim, Dong-Jae ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 57~64
DOI : 10.5351/CKSS.2012.19.1.057
Phase I clinical trials determine the maximum tolerated dose(MTD) of a new drug. In this paper, we proposed a two-stage MTD estimation method by a Stopping rule in a phase I clinical trial. The suggested MTD estimation method is compared to the standard design(SM3) and the continual reassessment method(CRM) using a Monte Carlo simulation study.
Hybrid Constrained Extrapolation Experimental Design
Kim, Young-Il ; Jang, Dae-Heung ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 65~75
DOI : 10.5351/CKSS.2012.19.1.065
In setting an experimental design for the prediction outside the experimental region (extrapolation design), it is natural for the experimenter to be very careful about the validity of the model for the design because the experimenter is not certain whether the model can be extended beyond the design region or not. In this paper, a hybrid constrained type approach was adopted in dealing model uncertainty as well as the prediction error using the three basic principles available in literature, maxi-min, constrained, and compound design. Furthermore, the effect of the distance of the extrapolation design point from the design region is investigated. A search algorithm was used because the classical exchange algorithm was found to be complex due to the characteristic of the problem.
Nonparametric Method Using an Alignment Method in a Randomized Block Design with Replications
Lee, Min-Hee ; Kim, Dong-Jae ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 77~84
DOI : 10.5351/CKSS.2012.19.1.077
Mack and Skillings (1980) proposed a typical nonparametric method in a randomized block design with replications. However, this method may lose information because of the use of average observations instead of individual observations. In this paper, we proposed a nonparametric method that employed an aligned method suggested by Hodges and Lehmann (1962) under a randomized block design with replications. In addition, the comparative results of a Monte Carlo power study are presented.
A Family of Extended NQD Bivariate Distributions with Continuous Marginals
Ryu, Dae-Hee ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 85~95
DOI : 10.5351/CKSS.2012.19.1.085
In this paper we define extended negative quadrant dependence which is weaker negative quadrant dependence and show conditions for having extended negative quadrant dependence property. We also derive generalized Farlie-Gumbel-Morgenstern uniform distributions that possess the extended quadrant dependence property.
Relationship between Physical Fitness and Basic Skill Factors for KTA Players Using the Partial Cannonical Correlation Biplot Removing the Linear Effect of the Set of Covariate Variables and Procrustes Analysis
Choi, Tae-Hoon ; Choi, Yong-Seok ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 97~105
DOI : 10.5351/CKSS.2012.19.1.097
The generalized canonical correlation biplot is a 2-dimensional plot to graphically investigate the relationship between more than three sets of variables and the relationship between observations and variables. Recently, Choi and Choi (2010) investigated the relationship physique, physical fitness and basic skill factors of Korea Tennis Association(KTA) players of using this biplot; however we consider the set of covariate variables affecting the linearly on two sets of variables. In this case, if we apply the generalized canonical correlation biplot, we cannot clearly interpret the other two sets of variables due to the effect of the set of covariate variables. Moreover, Yeom and Choi (2011) provided partial canonical correlation analysis that removed the linear effect of the set of covariate variables on two sets of variables. In addition, Procrustes analysis is a useful tool for comparing shape between configurations. In this study, we will investigate the relationship between physical fitness and basic skill factors of KTA players of using a partial canonical correlation biplot and Procrustes analysis. We compare shapes and shape variabilities for the generalized, partial and simple canonical correlation biplots.
Effect of Dimension in Optimal Dimension Reduction Estimation for Conditional Mean Multivariate Regression
Seo, Eun-Kyoung ; Park, Chong-Sun ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 107~115
DOI : 10.5351/CKSS.2012.19.1.107
Yoo and Cook (2007) developed an optimal sufficient dimension reduction methodology for the conditional mean in multivariate regression and it is known that their method is asymptotically optimal and its test statistic has a chi-squared distribution asymptotically under the null hypothesis. To check the effect of dimension used in estimation on regression coefficients and the explanatory power of the conditional mean model in multivariate regression, we applied their method to several simulated data sets with various dimensions. A small simulation study showed that it is quite helpful to search for an appropriate dimension for a given data set if we use the asymptotic test for the dimension as well as results from the estimation with several dimensions simultaneously.
Probabilities of Baccarat by Simulation
Zhu, Weicheng ; Park, Chang-Soon ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 117~128
DOI : 10.5351/CKSS.2012.19.1.117
In Baccarat, the gambler can bet on either the Player or Banker. The only gambler's strategy is to consider the previous winning history on the round. The winning probabilities of Player or Banker are calculated by simulation using R. Conditional winning probabilities given that Player or Banker has won i consecutive times are also calculated by simulation. Conditional winning probability implies that the sequence of Baccarat results is an almost independent sequence of events. It has been shown that the total amount of returns in each round of games is almost identical to a random walk. Thus, one possible strategy is to catch the trend(the Player or the Banker) of the random walk and to bet on that side of the trend.
A Study on the Bi-Aspect Test for the Two-Sample Problem
Hong, Seung-Man ; Park, Hyo-Il ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 129~134
DOI : 10.5351/CKSS.2012.19.1.129
In this paper we review a bi-aspect nonparametric test for the two-sample problem under the location translation model and propose a new one to accommodate a more broad class of underlying distributions. Then we compare the performance of our proposed test with other existing ones by obtaining empirical powers through a simulation study. Then we discuss some interesting features related to the bi-aspect test with a comment on a possible expansion for the proposed test as concluding remarks.
An EM Algorithm for a Doubly Smoothed MLE in Normal Mixture Models
Seo, Byung-Tae ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 135~145
DOI : 10.5351/CKSS.2012.19.1.135
It is well known that the maximum likelihood estimator(MLE) in normal mixture models with unequal variances does not fall in the interior of the parameter space. Recently, a doubly smoothed maximum likelihood estimator(DS-MLE) (Seo and Lindsay, 2010) was proposed as a general alternative to the ordinary maximum likelihood estimator. Although this method gives a natural modification to the ordinary MLE, its computation is cumbersome due to intractable integrations. In this paper, we derive an EM algorithm for the DS-MLE under normal mixture models and propose a fast computational tool using a local quadratic approximation. The accuracy and speed of the proposed method is then presented via some numerical studies.
Correlation Test by Reduced-Spread of Fuzzy Variance
Kang, Man-Ki ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 147~155
DOI : 10.5351/CKSS.2012.19.1.147
We propose some properties for a fuzzy correlation test by reduced-spread fuzzy variance for sample fuzzy data. First, we define the condition of fuzzy data for repeatedly observed data or that which includes error term data. By using the average of spreads for fuzzy numbers, we reduce the spread of fuzzy variance and define the agreement index for the degree of acceptance and rejection. Given a non-normal random fuzzy sample, we have bivariate normal distribution by apply Box-Cox power fuzzy transformation and test the fuzzy correlation for independence between the variables provided by the agreement index.
A Fast EM Algorithm for Gaussian Mixtures
Jung, Hye-Kyung ; Seo, Byung-Tae ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 157~168
DOI : 10.5351/CKSS.2012.19.1.157
The EM algorithm is the most important tool to obtain the maximum likelihood estimator in finite mixture models due to its stability and simplicity. However, its convergence rate is often slow because the conventional EM algorithm is based on a large missing data space. Several techniques have been proposed in the literature to reduce the missing data space. In this paper, we review existing methods and propose a new EM algorithm for Gaussian mixtures, which reduces the missing data space while preserving the stability of the conventional EM algorithm. The performance of the proposed method is evaluated with other existing methods via simulation studies.
Approximation of M/G/c Retrial Queue with M/PH/c Retrial Queue
Shin, Yang-Woo ; Moon, Dug-Hee ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 169~175
DOI : 10.5351/CKSS.2012.19.1.169
The sensitivity of the performance measures such as the mean and the standard deviation of the queue length and the blocking probability with respect to the moments of the service time are numerically investigated. The service time distribution is fitted with phase type(PH) distribution by matching the first three moments of service time and the M/G/c retrial queue is approximated by the M/PH/c retrial queue. Approximations are compared with the simulation results.
Robust Unit Root Tests with an Innovation Variance Break
Oh, Yu-Jin ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 177~182
DOI : 10.5351/CKSS.2012.19.1.177
A structural break in the level as well as in the innovation variance has often been exhibited in economic time series. In this paper we propose robust unit root tests based on a sign-type test statistic when a time series has a shift in its level and the corresponding volatility. The proposed tests are robust to a wide class of partially stationary processes with heavy-tailed errors, and have an exact binomial null distribution. Our tests are not affected by the size or location of the break. We set the structural break under the null and the alternative hypotheses to relieve a possible vagueness in interpreting test results in empirical work. The null hypothesis implies a unit root process with level shifts and the alternative connotes a stationary process with level shifts. The Monte Carlo simulation shows that our tests have stable size than the OLSE based tests.
Travel Behavior Analysis for Short-Term KTX Passenger Demand Forecasting
Kim, Han-Soo ; Yun, Dong-Hee ; Lee, Sung-Duk ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 183~192
DOI : 10.5351/CKSS.2012.19.1.183
This study analyzes the travel behavior for short-term demand forecasting model of KTX. This research suggests the following. First, the outlier criteria is considered to appropriate twice the standard deviation of the traffic. Second, the result of a homogeneity test using ANOVA analysis has been divided into weekdays(Mon Thu and weekends(Fri Sun). Third, a cluster analysis for O/D pairs using trip frequency, traffic averages and th distance between stations was performed.
Nonparametric M-Estimation for Functional Spatial Data
Attouch, Mohammed Kadi ; Chouaf, Benamar ; Laksaci, Ali ;
Communications for Statistical Applications and Methods, volume 19, issue 1, 2012, Pages 193~211
DOI : 10.5351/CKSS.2012.19.1.193
This paper deals with robust nonparametric regression analysis when the regressors are functional random fields. More precisely, we consider
-valued measurable strictly stationary spatial process, where
is a semi-metric space and we study the spatial interaction of
via the robust estimation for the regression function. We propose a family of robust nonparametric estimators for regression function based on the kernel method. The main result of this work is the establishment of the asymptotic normality of these estimators, under some general mixing and small ball probability conditions.