• Communications for Statistical Applications and Methods
• /
• v.15 no.3
• /
• pp.403-409
• /
• 2008

In this paper we show that the peak of the type I error rate of the Oochran-Armitage trend test could be greater than the nominal level when $2\;{\times}\;C$ contingency tables obtained from two multinomial distributions are extremely unbalanced. This result justifies the use of the exact Cochran-Armitage trend test in extremely unbalanced $2\;{\times}\;C$ contingency tables.

• Communications for Statistical Applications and Methods
• /
• v.17 no.1
• /
• pp.67-77
• /
• 2010

In multinomial scheme with step-wise sampling, maximum likelihood estimates of multinomial probabilities are improved when some frequencies are merged. In this study, for cell probabilities in a I by J independent contingency tables, exact MLE and step-wise estimation methods are applied and the results are compared using MSE and Bias.

• Journal of Sasang Constitutional Medicine
• /
• v.11 no.1
• /
• pp.159-168
• /
• 1999

Purpose : Sasang Constitutional Medicine explains the pathology peculiar to constitution and suggests treatment for each constitution. In Sasang Constitutional Medicine hwnan beings are classified on four groups; Taeyangin, Taeumin, 5oyangin, Soeumin. These four constitution has their's own symptoms and treatments. In treatment, control of mind inclination, that is to say, moderation takes a very important role. But the study on heredity in Sasang Constitutional Medicine has not done not biological study but also statistical study. So we used several statistical methods and analyzed 163 samples. Methods : We implemented Fishers exact test for adjusting chi-squared test, kappa coefficient to estimate agreement of parent's and children's constitutions, and finally plotted bi-plot using correspondence analysis. Results : From Fisher's exact test result, we could know that parent's and children'S constitution's distribution had significant difference. In kappa coefficient, mother and daughter's estimated value produced highest result. In correspondence analysis we only plotted the case of mother and son for easy interpretation. Conclusion : In the study of heredity of SaSang constitution, we cannot know exactly the heredity of constitution in terms of biology or genetics. But this research can be helpful for further analysis, that is, a study of biological or genetical aspects. And we could conclude that in statistical aspects the heredity in SaSang constitution is meaningful.

• Structural Engineering and Mechanics
• /
• v.19 no.5
• /
• pp.551-566
• /
• 2005

Using two different, but related approaches, an exact dynamic stiffness matrix for a two-part beam-mass system is developed from the free vibration theory of a Bernoulli-Euler beam. The first approach is based on matrix transformation while the second one is a direct approach in which the kinematical conditions at the interfaces of the two-part beam-mass system are satisfied. Both procedures allow an exact free vibration analysis of structures such as a plane or a space frame, consisting of one or more two-part beam-mass systems. The two-part beam-mass system described in this paper is essentially a structural member consisting of two different beam segments between which there is a rigid mass element that may have rotatory inertia. Numerical checks to show that the two methods generate identical dynamic stiffness matrices were performed for a wide range of frequency values. Once the dynamic stiffness matrix is obtained using any of the two methods, the Wittrick-Williams algorithm is applied to compute the natural frequencies of some frameworks consisting of two-part beam-mass systems. Numerical results are discussed and the paper concludes with some remarks.

• Bulletin of the Korean Mathematical Society
• /
• v.55 no.4
• /
• pp.1303-1315
• /
• 2018

For principal component analysis (PCA) to efficiently analyze large scale matrices, it is crucial to find a few singular vectors in cheaper computational cost and under lower memory requirement. To compute those in a fast and robust way, we propose a new stochastic method. Especially, we adopt the stochastic variance reduced gradient (SVRG) method [11] to avoid asymptotically slow convergence in stochastic gradient descent methods. For that purpose, we reformulate the PCA problem as a unconstrained optimization problem using a quadratic penalty. In general, increasing the penalty parameter to infinity is needed for the equivalence of the two problems. However, in this case, exact penalization is guaranteed by applying the analysis in [24]. We establish the convergence rate of the proposed method to a stationary point and numerical experiments illustrate the validity and efficiency of the proposed method.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1998.04a
• /
• pp.200-205
• /
• 1998

Although discretization methods such as the transfer matrix method (TMM) and the finite element method (FEM) have played an important role in the design or analysis of rotor-bearing systems, continuous system modeling and analysis are often desirable especially for sensitivity analysis or design. The present paper proposes a comprehensive modeling procedure to obtain exact solution of general rotor-bearing systems. The proposed method considers a Timoshenko beam model and makes use of complex coordinate in the formulation. The proposed method provides exact eigensolutions and frequency response functions (FRFS) of general multi-stepped rotor-bearing systems. The first numerical example compares the proposed method with FEM. The numerical study proves that the proposed method is very efficient and useful for the analysis of rotor-bearing systems.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2005.11b
• /
• pp.53-56
• /
• 2005

Aircraft noise is a important problem to inhabitants near airports. INM is one of programs for determining the predicted noise impact in the vicinity of airports. It has been widely using for engineers to evaluate aircraft noise. However it is difficult to predict aircraft noise in case of lack of exact INM input data. The exact informations about a fighter plane are not known well for a security problem. This study presents methods of reducing errors between measurement and simulation when the exact INM input data is not known. Especially we adjusted the thrust force of aircraft engine and reduced the error.

• The Korean Journal of Applied Statistics
• /
• v.5 no.1
• /
• pp.9-17
• /
• 1992

In this paper we give a Bayesian approach to problems of estimation for the ratio in finite populations. Adopting the Ericson's superpopulatin approach in which the finite population of size N is viewed as arising form a random sample of N units from some superpopulation. We derive the exact posterior of the ratio under the noninformative prior on superpopulation parameters. Based on our results we compute an exact Bayesian confidence interval and compare this with the existing methods.

• Structural Engineering and Mechanics
• /
• v.15 no.1
• /
• pp.71-81
• /
• 2003

The governing differential equation for buckling of a one-step bar with the effect of shear deformation is established and its exact solution is obtained. Then, the exact solution is used to derive the eigenvalue equation of a multi-step bar. The new exact approach combining the transfer matrix method and the closed form solution of one step bar is presented. The proposed methods is convenient for solving the entire and partial buckling of one-step and multi-step bars with various end conditions, with or without shear deformation effect, subjected to concentrated axial loads. A numerical example is given explaining the proposed procedure and investigating the effect of shear deformation on the critical buckling force of a multi-step bar.

• Communications for Statistical Applications and Methods
• /
• v.22 no.4
• /
• pp.389-399
• /
• 2015

It is important not to overcalculate sample sizes for clinical trials due to economic, ethical, and scientific reasons. Kang and Kim (2014) investigated the accuracy of a well-known sample size calculation formula based on the approximate power for continuous endpoints in equivalence trials, which has been widely used for Development of Biosimilar Products. They concluded that this formula is overly conservative and that sample size should be calculated based on an exact power. This paper extends these results to binary endpoints for three popular metrics: the risk difference, the log of the relative risk, and the log of the odds ratio. We conclude that the sample size formulae based on the approximate power for binary endpoints in equivalence trials are overly conservative. In many cases, sample sizes to achieve 80% power based on approximate powers have 90% exact power. We propose that sample size should be computed numerically based on the exact power.