• Journal of the Korean Statistical Society
• /
• v.27 no.1
• /
• pp.11-23
• /
• 1998

A Bayes criterion for testing the equality of covariance matrices of two multivariate normal distributions is proposed and studied. Development of the criterion invloves calculation of Bayes factor using the imaginary sample method introduced by Spiegelhalter and Smith (1982). The criterion is designed to develop a Bayesian test criterion, so that it provides an alternative test criterion to those based upon asymptotic sampling theory (such as Box's M test criterion). For the constructed criterion, numerical studies demonstrate routine application and give comparisons with the traditional test criteria.

• Geomechanics and Engineering
• /
• v.32 no.1
• /
• pp.49-68
• /
• 2023

The three-dimensional failure criterion is essential for maintaining wellbore stability and sand production problem. The convenient factor for a stable wellbore is mud weight and borehole orientation, i.e., mud window design and selection of borehole trajectory. This study proposes a new three-dimensional failure criterion with linear relation of three in-situ principal stresses. The number of failure criteria executed to understand the phenomenon of rock failure under in-situ stresses is the Mohr-Coulomb criterion, Hoek-Brown criterion, Mogi-Coulomb criterion, and many more. A new failure criterion is the extended Mohr-Coulomb failure criterion with the influence of intermediate principal stress (σ₂). The influence of intermediate principal stress is considered as a weighting of (σ₂) on the mean effective stress. The triaxial compression test data for eleven rock types are taken from the literature for calibration of material constant and validation of failure prediction. The predictions on rock samples using new criteria are the best fit with the triaxial compression test data points. Here, Drucker-Prager and the Mogi-Coulomb criterion are also implemented to predict the failure for eleven different rock types. It has been observed that the Drucker-Prager criterion gave over prediction of rock failure. On the contrary, the Mogi-Coulomb criterion gave an equally good prediction of rock failure as our proposed new 3D failure criterion. Based on the yield surface of a new 3D linear criterion it gave the safest prediction for the failure of the rock. A new linear failure criterion is recommended for the unique solution as a linear relation of the principal stresses rather than the dual solution by the Mogi-Coulomb criterion.

• Communications for Statistical Applications and Methods
• /
• v.6 no.1
• /
• pp.193-205
• /
• 1999

An approximate Bayes criterion for Behrens-Fisher problem (testing equality of means of two normal populations with unequal variances) is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approachintroduced by Spiegelhalter and Smith (1982). The proposed criterion is designed to develop a Bayesian test criterion having a closed form, so that it provides an alternative test to those based upon asymptotic sampling theory (such as Welch's t test). For the suggested Bayes criterion, numerical study gives comparisons with a couple of asymptotic classical test criteria.

• Communications for Statistical Applications and Methods
• /
• v.9 no.2
• /
• pp.411-423
• /
• 2002

In this paper, we propose a split criterion for binary decision trees. The proposed criterion selects the optimal split by measuring the prediction success of the candidate splits at a given node. The criterion is shown to have the property of exclusive preference. Examples are given to demonstrate the properties of the criterion.

• Journal of the Korean Statistical Society
• /
• v.28 no.1
• /
• pp.107-124
• /
• 1999

An approximate Bayes criterion for multivariate Behrens-Fisher problem is proposed and examined. Development of the criterion involves derivation of approximate Bayes factor using the imaginary training sample approach introduced by Speigelhalter and Smith (1982). The criterion is designed to develop a Bayesian test, so that it provides an alternative test to other tests based upon asymptotic sampling theory (such as the tests suggested by Bennett(1951), James(1954) and Yao(1965). For the derived criterion, numerical studies demonstrate routine application and give comparisons with the classical tests.

• Journal of applied mathematics & informatics
• /
• v.9 no.1
• /
• pp.303-310
• /
• 2002

The cyryptographic strength of a Feistel cipher depends strongly on the properties of its S-boxes, which are the strict avalanche criterion(SAC), the propagation criterion(PC) and GAC(the global avalanche criterion). In this paper global avalanche characteristics of S-boxes of the SEED are in-vestigated and compared to global avalanche characteristics of S-boxes of S-boxes of the Data Encryption Standard(DES).

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.6 no.4
• /
• pp.1082-1095
• /
• 2014

In this paper, a new criterion for the identification of slamming events is formulated. This criterion is based on the analysis of the high-frequency response, expressed in terms of the amidships VBM, which occurs after the slams. For this reason, it is named 'whipping' criterion underlining that is based on the analysis of global effects than on the kinematic description of the impact dynamics that was provided by Ochi criterion. Both the new 'whipping' criterion and the Ochi criterion are presented and compared also with respect to their practical application to the experimental data collected in the seakeeping tests with an elastic segmented model.

• Journal of environmental and Sanitary engineering
• /
• v.13 no.1
• /
• pp.123-134
• /
• 1998

The study was performed to investigate the differences among various evaluation criteria for noise-induced hearing loss(NIHL). The subjects were 100 workers who had received detailed audiometric examinations after the periodic annual examination for hearing loss. The evaluation criteria included were as follows: The criterion I was NIHL of 50dB or greater at 4,000Hz in either ear which is one of the legal requirements for determining occupational hearing loss in Korea. The criterion II was NIHL of 40dB or greater by 4-divided classification(a+b+c+d/4 at 500Hz(a), 1,000Hz(b), 2,000Hz(c), 4,000Hz(d)) which is also one of the legal requirements for determining occupational hearing loss in Korea. The criterion III was NIHL of 31dB of greater by 6-divided classification(a+2b+2c+d/6) which is the workers' compensation standard. The criterion IV was NIHL of 40dB or greater by 6-divided classification(a+2b+2c+d/6), the criterion used to prohibite workers to be employed in the noisy workplace. The criterion V was NIHL of 40dB or greater by 3-divided classification(a+b+c/3) which is the guideline of the Japanes Labour Department. The results were as follows; 1. The percentage of workers with NIHL by the criterion I was the highest(96%) and covered all workers with NIHL diagnosed by other criteria. Therefore, this criterion was the most sensitive one for early detection of NIHL among various evaluation criteria. 2. The percentage of workers with NIHL by the criterion II was 29% of the subjects, but all of them could be diagnosed as having NIHL by the criterion I and 33.1% of the NIHL by the criterion III could not be covered by the criterion II. Thus, this criterion was not considered suitable as an initial step for determining occupational hearing loss. 3. The percentage of workers with NIHL by the criterion III was 45% of the subjects. This percentage was 46.9% of the NIHL by the criterion I and was estimated to cover 3.6% of all noise exposed workers. 4. The percentage of workers with NIHL by the criterion IV was 28% of the subjects, but 37.8% of the NIHL by the criterion III and 70.8% of the NIHL by the criterion I were not covered by the criterion. Therefore, these workers could have been employed in the noisy workplaces. 5. Employed relocation which was one of the post management methods was an option in the criterion I in Korea and in the criterion V in Japan. The number of NIHL by the criterion I was 6.7times greater than that by the criterion V. Thus, although employee relocation was not used exclusively, many more workers with NIHL could have been relocated. In conclusion, this study revealed that the criteria being used for managing occupational hearing loss showed a lack uniformity among them. In addition, since these criteria are all relied on the total threshold shifts caused by the noise exposure at the time of hearing test with no consideration given to the past noise exposure history nor age, it can be said that they are not an effective tool for occupational hearing loss management. Since legal requirements are usually followed after being diagnosed as having NIHL, it is recommended that a uniform diagnostic criterion should be used to minimize confusion. Pre-employment hearing tests should also be utilized so as to managing occupational hearing loss after employment rather than being used as a legal roadblock of prohibiting workers with mild hearing loss from being employed. Thus, what is needed is an establishment of a rational criterion for occupational hearing loss management rather than for legal requirements.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.119-133
• /
• 2017

Corrected Akaike's information criterion (AICc) is known to have better finite sample properties. However, Akaike's information criterion (AIC) is still widely used to select an optimal prediction model among several candidate models due to of a lack of research on benefits obtained using AICc. In this paper, we compare the performance of AIC and AICc through numerical simulations and confirm the advantage of using AICc. In addition, we also consider the performance of quasi Akaike's information criterion (QAIC) and the corrected quasi Akaike's information criterion (QAICc) for binomial and Poisson data under overdispersion phenomenon.

• Steel and Composite Structures
• /
• v.34 no.5
• /
• pp.671-679
• /
• 2020

The new energy-based criterion, named Reinforcement Strain Energy Density (ReiSED), is proposed to investigate the fracture behavior of the cracked orthotropic materials in which the crack is embedded in the matrix along the fibers. ReiSED is an extension of the well-known minimum strain energy density criterion. The concept of the reinforced isotropic solid as an advantageous model is the basis of the proposed mixed-mode I/II criterion. This model introduces fibers as reinforcements of the isotropic matrix in orthotropic materials. The effects of fibers are qualified by defining reinforcement coefficients at tension and shear modes. These coefficients, called Reduced Stress (ReSt), provide the possibility of encompassing the fiber fraction in a fracture criterion for the first time. Comparing ReiSED fracture limit curve with experimental data proves the high efficiency of this criterion to predict the fracture behavior of orthotropic materials.