• Communications for Statistical Applications and Methods
• /
• v.22 no.6
• /
• pp.599-604
• /
• 2015

Kendall's tau statistic has been applied to test an association of bivariate random variables. However, incomplete bivariate data with a truncation and a censoring results in incomparable or unorderable pairs. With such a partial information, Tsai (1990) suggested a conditional tau statistic and a test procedure for a quasi independence that was extended to more diverse cases such as double truncation and a semi-competing risk data. In this paper, we also employed a conditional tau statistic to estimate an association of bivariate interval censored data. The suggested method shows a better result in simulation studies than Betensky and Finkelstein's multiple imputation method except a case in cases with strong associations. The association of incubation time and infection time from an AIDS cohort study is estimated as a real data example.

• The Korean Journal of Applied Statistics
• /
• v.28 no.3
• /
• pp.583-592
• /
• 2015

Zero-inflation has recently attracted much attention in integer-valued time series. This article deals with conditional variance (volatility) modeling for the zero-inflated count time series. We incorporate zero-inflation property into integer-valued GARCH (INGARCH) via conditional Poisson and negative binomial marginals. The Cholera frequency time series is analyzed as a data application. Estimation is carried out using EM-algorithm as suggested by Zhu (2012).

• Communications for Statistical Applications and Methods
• /
• v.22 no.5
• /
• pp.507-518
• /
• 2015

It is not easy to select a linear mixed model since the main interest for model building could be different and the number of parameters in the model could not be clearly defined. In this paper, performance of conditional Akaike Information Criteria and its bias-corrected version are compared with marginal Bayesian and Akaike Information Criteria through a simulation study. The results from the simulation study indicate that bias-corrected conditional Akaike Information Criteria shows promising performance when candidate models exclude large models containing the true model, but bias-corrected one prefers over-parametrized models more intensively when a set of candidate models increases. Marginal Bayesian and Akaike Information Criteria also have some difficulty to select the true model when the design for random effects is nested.

• The Korean Journal of Applied Statistics
• /
• v.16 no.2
• /
• pp.217-224
• /
• 2003

The volatility in the financial data is usually measured by conditional variance. Two main streams for gauging conditional variance are stochastic volatility (SV) model and autoregressive type approach (GARCH). This article is conducting comparative study between SV and GARCH through the Korean Stock Prices Index (KOSPI) data. It is seen that SV model is slightly better than GARCH(1,1) in analyzing KOSPI data.

• International Commerce and Information Review
• /
• v.7 no.3
• /
• pp.269-286
• /
• 2005

The exchange rate volatility has been increased since the time when the floating exchange rate system was introduced in Korea. As a result, the increase of the exchange rate volatility raised the risk in international trades in Korea. The purpose of this study in to study the feature of exchange rate volatility and the main sources of its increase and to confirm whether the exchange rate volatility influence export volume and price of Korea. In the first place, I measured exchange rate volatility with two methods. The one is descriptive statistic method such as the width of daily exchange rate fluctuation and the rate of exchange rate devaluation. The other is the time varying conditional variance of exchange rate. Then, I studied the sources of exchange rate volatility. In the second place, I defined the exchange rate volatility as the time varying conditional variance and estimated it by using elastic a approach model which shows exchange rate is affected by itself and its conditional variance, I estimated its effects on export volumes and prices of electric home appliances, information & communication equal and semi-conductor. The result of this study is as follows. With presumed result EU and Korea because is not the goods which is to substantial competition relationship, The effect where the relative value change of presumed result expression anger and the dollar of import and export function goes mad to the import and export of Korea the income compared to is to export and it is appearing a lot. The EU goods is sold more expensively the Korean goods than from about length being caused by American market of the dollar and the balance of trade of Korea is visible like being visible the improvement of single breadth. Because the relationship of competition is weak but substantially there is to a short term and expression - the effect where the dollar rate fluctuation is big in Korean trade there is a possibility of saying that widely known it is not.

• Korean Management Science Review
• /
• v.28 no.2
• /
• pp.1-16
• /
• 2011

In this study we suggested two optimization models to answer a question from an investor standpoint : how many convertible bonds should one convert, and how many keep? One model minimizes certain risk to the minimum required expected return, the other maximizes the expected return subject to the maximum acceptable risk. In comparison with Markowitz portfolio models, which use the variance of return, our models used Conditional Value-at-Risk(CVaR) for risk measurement. As a coherent measurement, CVaR overcomes the shortcomings of Value-at-Risk(VaR). But there are still difficulties in solving CVaR including optimization models. For this reason, we adopted Rockafellar and Uryasev's[18, 19] approach. Then we could approximate the models as linear programming problems with scenarios. We also suggested to extend the models with credit risk, and applied examples of our models to Hynix 207CB, a convertible bond issued by the global semiconductor company Hynix.

• 한국연소학회:학술대회논문집
• /
• 2007.05a
• /
• pp.118-125
• /
• 2007

The firtst-order conditional moment closure (CMC) model is applied to CH4/air swirl diffusion flame in a gas turbine model combustor. The flow and mixing fields are calculated by fast chemistry assumption with SLFM library and a beta function pdf for mixture fraction. RNG k-e model is used to consider the swirl flame in a confined wall. Reacting scalar fields are calculated by elliptic CMC formulation with chemical kinetic mechanism, GRI Mech 3.0. Validation is done against measurement data for mean flow and scalar fields in the model combustor [1]. Results show reasonable agreement with the mean mixture fraction and its variance, while temperature is overpredicted as the level of local extinction increases. The second-order CMC model is needed to consider local extinction with considerable conditional fluctuations near the nozzle.

• Journal of the Korean Statistical Society
• /
• v.33 no.1
• /
• pp.107-128
• /
• 2004

Bivariate Laplace distributions for which both marginal distributions and Laplace are discussed. Three kinds of bivariate Laplace distributions which are extended bivariate exponential distributions of Gumbel (1960) are introduced in this paper. These symmetrical distributions are compared with asymmetrical distributions of Kotz et al. (2000). Their probability density functions, cumulative distribution functions are derived. Conditional skewnesses and kurtoses are also defined. Their correlation coefficients are calculated and compared with others. We proposed bivariate random vector generating methods whose distributions are bivariate Laplace. With sample means and medians obtained from generated random vectors, variance and covariance matrices of means and medians are calculated and discussed with those of bivariate normal distribution.

• Journal of the Korean Statistical Society
• /
• v.30 no.3
• /
• pp.511-527
• /
• 2001

This paper consider the testing problem of variance component for the unbalanced tow=-way error component model. We provide a conditional LM test statistic for testing zero individual(time) effects assuming that the other time-specific(individual)efefcts are present. This test is extension of Baltagi, Chang and Li(1998, 1992). Monte Carlo experiments are conducted to study the performance of this LM test.

• Journal of the Korean Statistical Society
• /
• v.26 no.2
• /
• pp.199-210
• /
• 1997

Using regression methods based on quasi-likelihood equation, one only needs to specify the conditional mean and variance functions for the response variable in the analysis. In this paper, an omnibus lack-of-fit test is proposed to test the validity of these two functions. Our test is consistent against the alternative under which either the mean or the variance is not the one specified in the null hypothesis. The large-sample null distribution of our test statistics can be approximated through simulations. Extensive numerical studies are performed to demonstrate that the new test preserves the prescribed type I error probability. Power comparisons are conducted to show the advantage of the new proposal.