• Communications for Statistical Applications and Methods
• /
• v.21 no.4
• /
• pp.335-347
• /
• 2014

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.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.3
• /
• pp.137-149
• /
• 2005

This study proposes a framework enhancing the accuracy of estimation for project duration by combining linear Bayesian updating scheme with the learning curve effect. Activities in a particular project might share resources in various forms and might be affected by risk factors such as weather Statistical dependence stemming from such resource or risk sharing might help us learn about the duration of upcoming activities in the Bayesian model. We illustrate, using a Monte Carlo simulation, that for partially repetitive projects a higher degree of statistical dependence among activity duration results in more variation in estimating the project duration in total, although more accurate forecasting Is achievable for the duration of an individual activity.

• Journal of Magnetics
• /
• v.20 no.3
• /
• pp.290-294
• /
• 2015

To investigate the effects of alternating magnetic field intensity and stimulation time on the proliferation of human breast cancer cells (BT-20), we cultured the cells under a magnetic field with a saw tooth waveform of 2 kHz. The field intensities varied from 3 to 7 mT, and the stimulation time varied from 24 to 72 hours. Cell proliferation decreased dramatically to 40% during magnetic stimulation for 72 hours at 5 mT. However, the cells were not affected by a strong magnetic field of 7 mT. The p-values obtained using statistical package for social science software were below 0.05 for 5-7 mT. This means that the results have statistical significance. However, it is difficult to explain our results based on the physiology of cell membranes, which have various ionic flows at ion channels.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.533-542
• /
• 2002

In this paper, a covariate adjusted logrank test is considered for censored paired data under the Cox proportional hazard model. The proposed score test resembles the adjusted logrank test of Tsiatis, Rosner and Tritchler (1985), which is derived from the partial likelihood. The dependence structure for paired data is accommodated into the test statistic by using' sum of square type' variance estimators. Several weight functions are also considered, which produce a class of covariate adjusted weighted logrank tests. Asymptotic normality of the proposed test is established and simulation studies with moderate sample size show the proposed test works well, particularly when there are dependence structure between treatment and covariates.

• Journal of the Korean Statistical Society
• /
• v.25 no.2
• /
• pp.243-253
• /
• 1996

Let X and Y be random vectors in R$^{n}$ . A random vector X is 'more associated' than Y if and only if P(X $\in$ A ∩ B) - P(X $\in$ A)P(X $\in$ B) $\geq$ P(Y $\in$ A ∩ B)-P(Y $\in$ A)P(Y $\in$ B) for all open upper sets A and B. By requiring the above inequality to hold for some open upper sets A and B various notions of positive dependence orderings which are weaker than 'more associated' ordering are obtained. First a general theory is given and then the results are specialized to some concepts of a particular interest. Various properties and interrelationships are derived.

• Journal of the Korean Statistical Society
• /
• v.29 no.2
• /
• pp.201-217
• /
• 2000

The method of generalized estimating equations (GEE) has become very popular for the analysis of longitudinal data. We extend this work to the use of M-estimators; the resultant regression estimates are robust to heavy tailed errors and to outliers. The proposed method does not require correct specification of the dependence structure between observation, and allows for heterogeneity of the error. However, an estimate of the dependence structure may be incorporated, and if it is correct this guarantees a higher efficiency for the regression estimators. A goodness-of-fit test for checking the adequacy of the assumed M-estimation regression model is also provided. Simulation studies are conducted to show the finite-sample performance of the new methods. The proposed methods are applied to a real-life data set.

• Journal of the Korean Society of Safety
• /
• v.17 no.4
• /
• pp.126-132
• /
• 2002

By using the reference data, the empirical equations which describe the interrelationships of explosion properties and physical properties of n-chlorinated hydrocarbons have been derived. The properties which have been correlated are the lower and upper explosive limits, the stoichiometric coefficients, the heats of combustion, the carbon numbers. Also, the new equations using the mathematical and statistical methods for predicting the temperature dependence of lower explosive limits(LEL) of chlorinated hydrocarbons on the basis of the literature data are proposed. The fire and explosion properties calculated by the proposed equations in this research were a good agrement with literature data within a few A.A.P.E.(Average Absolute Percent Error) and A.A.D.(Average Absolute Deviation.) From a given explosive properties, by using the proposed equations, it is possible to predict to the fire and explosion characteristics for the other chlorinated hydrocarbons.

• Communications for Statistical Applications and Methods
• /
• v.23 no.3
• /
• pp.215-230
• /
• 2016

The powers of some tests for independence hypothesis against positive (negative) quadrant dependence in generalized Farlie-Gumbel-Morgenstern distribution are compared graphically by simulation. Some of these tests are usual linear rank tests of independence. Two other possible rank tests of independence are locally most powerful rank test and a powerful nonparametric test based on the $Cram{\acute{e}}r-von$ Mises statistic. We also evaluate the empirical power of the class of distribution-free tests proposed by Kochar and Gupta (1987) based on the asymptotic distribution of a U-statistic and the test statistic proposed by $G{\ddot{u}}ven$ and Kotz (2008) in generalized Farlie-Gumbel-Morgenstern distribution. Tests of independence are also compared for sample sizes n = 20, 30, 50, empirically. Finally, we apply two examples to illustrate the results.

• Journal of applied mathematics & informatics
• /
• v.7 no.3
• /
• pp.1059-1068
• /
• 2000

In this paper we introduce a new concept of weakly positive upper orthant dependence POD of hitting times of stochastic processes. This concept is weaker than the positively orthant dependent and it is closed under a certain statistical operations of W POD ordering. Examples are given to illustrate these concepts.

• IE interfaces
• /
• v.7 no.1
• /
• pp.81-91
• /
• 1994

Simulation is one of the most widely used techniques in operations research and management science, but there are several impediments to even wider acceptance and use of simulation. One of the more significant limitations is the dependence of simulation on statistical methodology. This research identifies eighteen different statistical issues in simulation methodology and develops an expert system which could through interactive dialog with simulation analysts offer advice on statistical approaches which might be used to deal with particular issues and to accomplish required statistical computations. This research revises the previous study published in Simulation by incorporating additional statistical issues in the expert system to enhance its performance in analyzing a given simulation problem with statistical methodologies. An overview of the revised system is given and illustrations of the capabilities of the system are presented.