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 21, Issue 6 - Nov 2014
Volume 21, Issue 5 - Sep 2014
Volume 21, Issue 4 - Jul 2014
Volume 21, Issue 3 - May 2014
Volume 21, Issue 2 - Mar 2014
Volume 21, Issue 1 - Jan 2014
Selecting the target year
Visualizations for Matched Pairs Models Using Modified Correspondence Analysis
Lee, Chanyoon ; Choi, Yong-Seok ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 275~284
DOI : 10.5351/CSAM.2014.21.4.275
Matched pairs are twice continuously measured data with the same categories. They can be represented as the square contingency tables. We can also consider symmetry and marginal homogeneity. Moreover, we can infer the matched pairs models; the symmetry model, the quasi-symmetry model, and the ordinal quasi-symmetry model. These inferences are involved in assumptions for special distributions. In this study, we visualize matched pairs models using modified correspondence analysis. Modified correspondence analysis can be used when square contingency tables are given; consequently, it is involved in the square and asymmetric correspondence matrix. This technique does not need assumptions for special distributions and is more helpful than the correspondence analysis to visualize matched pairs models.
Bayesian Semi-Parametric Regression for Quantile Residual Lifetime
Park, Taeyoung ; Bae, Wonho ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 285~296
DOI : 10.5351/CSAM.2014.21.4.285
The quantile residual life function has been effectively used to interpret results from the analysis of the proportional hazards model for censored survival data; however, the quantile residual life function is not always estimable with currently available semi-parametric regression methods in the presence of heavy censoring. A parametric regression approach may circumvent the difficulty of heavy censoring, but parametric assumptions on a baseline hazard function can cause a potential bias. This article proposes a Bayesian semi-parametric regression approach for inference on an unknown baseline hazard function while adjusting for available covariates. We consider a model-based approach but the proposed method does not suffer from strong parametric assumptions, enjoying a closed-form specification of the parametric regression approach without sacrificing the flexibility of the semi-parametric regression approach. The proposed method is applied to simulated data and heavily censored survival data to estimate various quantile residual lifetimes and adjust for important prognostic factors.
The General Linear Test in the Ridge Regression
Bae, Whasoo ; Kim, Minji ; Kim, Choongrak ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 297~307
DOI : 10.5351/CSAM.2014.21.4.297
We derive a test statistic for the general linear test in the ridge regression model. The exact distribution for the test statistic is too difficult to derive; therefore, we suggest an approximate reference distribution. We use numerical studies to verify that the suggested distribution for the test statistic is appropriate. A asymptotic result for the test statistic also is considered.
Goodness-of-Fit Test for the Normality based on the Generalized Lorenz Curve
Cho, Youngseuk ; Lee, Kyeongjun ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 309~316
DOI : 10.5351/CSAM.2014.21.4.309
Testing normality is very important because the most common assumption is normality in statistical analysis. We propose a new plot and test statistic to goodness-of-fit test for normality based on the generalized Lorenz curve. We compare the new plot with the Q-Q plot. We also compare the new test statistic with the Kolmogorov-Smirnov (KS), Cramer-von Mises (CVM), Anderson-Darling (AD), Shapiro-Francia (SF), and Shapiro-Wilks (W) test statistic in terms of the power of the test through by Monte Carlo method. As a result, new plot is clearly classified normality and non-normality than Q-Q plot; in addition, the new test statistic is more powerful than the other test statistics for asymmetrical distribution. We check the proposed test statistic and plot using Hodgkin's disease data.
Global and Local Views of the Hilbert Space Associated to Gaussian Kernel
Huh, Myung-Hoe ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 317~325
DOI : 10.5351/CSAM.2014.21.4.317
Consider a nonlinear transform
of x in
to Hilbert space H and assume that the dot product between
in H is given by <
>= K(x, x'). The aim of this paper is to propose a mathematical technique to take screen shots of the multivariate dataset mapped to Hilbert space H, particularly suited to Gaussian kernel
, which is defined by
> 0. Several numerical examples are given.
Continuous Time Approximations to GARCH(1, 1)-Family Models and Their Limiting Properties
Lee, O. ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 327~334
DOI : 10.5351/CSAM.2014.21.4.327
Various modified GARCH(1, 1) models have been found adequate in many applications. We are interested in their continuous time versions and limiting properties. We first define a stochastic integral that includes useful continuous time versions of modified GARCH(1, 1) processes and give sufficient conditions under which the process is exponentially ergodic and
-mixing. The central limit theorem for the process is also obtained.
Time-Varying Comovement of KOSPI 200 Sector Indices Returns
Kim, Woohwan ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 335~347
DOI : 10.5351/CSAM.2014.21.4.335
This paper employs dynamic conditional correlation (DCC) model to examine time-varying comovement in the Korean stock market with a focus on the financial industry. Analyzing the daily returns of KOSPI 200 eight sector indices from January 2008 to December 2013, we find that stock market correlations significantly increased during the GFC period. The Financial Sector had the highest correlation between the Constructions-Machinery Sector; however, the Consumer Discretionary and Consumer Staples sectors indicated a relatively lower correlation between the Financial Sector. In terms of model fitting, the DCC with t distribution model concludes as the best among the four alternatives based on BIC, and the estimated shape parameter of t distribution is less than 10, implicating a strong tail dependence between the sectors. We report little asymmetric effect in correlation dynamics between sectors; however, we find strong asymmetric effect in volatility dynamics for each sector return.
Comparison of Lasso Type Estimators for High-Dimensional Data
Kim, Jaehee ;
Communications for Statistical Applications and Methods, volume 21, issue 4, 2014, Pages 349~361
DOI : 10.5351/CSAM.2014.21.4.349
This paper compares of lasso type estimators in various high-dimensional data situations with sparse parameters. Lasso, adaptive lasso, fused lasso and elastic net as lasso type estimators and ridge estimator are compared via simulation in linear models with correlated and uncorrelated covariates and binary regression models with correlated covariates and discrete covariates. Each method is shown to have advantages with different penalty conditions according to sparsity patterns of regression parameters. We applied the lasso type methods to Arabidopsis microarray gene expression data to find the strongly significant genes to distinguish two groups.