• The Korean Journal of Applied Statistics
• /
• v.19 no.2
• /
• pp.349-360
• /
• 2006

PROC MIXED in SAS can be utilized to make inferences on parameters in a mixed model by use of Restricted Maximum Likelihood Estimation Method or Maximum Likelihood Estimation Method which has more merits than ANOVA method. A regression model with unbalanced nested error structure that belongs to a mixed model is used to construct confidence intervals on variances among groups, within groups, and regression coefficients in the model. PROC MIXED is applied to three different sample sizes for simulation. As a result of the simulation study, PROC MIXED generates confidence intervals on parameters that maintain the stated confidence coefficient in a large sample size. However, it does not generate confidence intervals that maintain the stated confidence coefficient for variance components among groups and intercept in a small sample size.

• Journal of the Korean Data and Information Science Society
• /
• v.28 no.3
• /
• pp.669-684
• /
• 2017

Mediation models are widely used in many fields of research and have recently gained attention in epidemiology. The mediation proportion is a standard measure to evaluate what part of the total exposure effect on an outcome may be explained by a particular mediator and to examine how important that pathway is relative to the overall exposure effect. A common question is how large a sample size is needed to achieve high statistical power or, equivalently, what magnitude of effect can be detected. Current power and sample size calculations for mediation analysis are limited and additional research is needed. We therefore propose a computer-intensive power analysis using the mediation proportion. We conduct simulation studies to calculate statistical powers and sample sizes. And then, we illustrate our power analysis using an example from the Adult Health Study of atomic-bomb survivors and demonstrate that the method is relatively straightforward to understand and compute.

• Progress in Superconductivity
• /
• v.5 no.2
• /
• pp.114-117
• /
• 2004

We fabricated large single grain YBa$_2$Cu$_3$O$_{x}$ (Y-123) superconductors. The single grain Y-123 was grown by top seeded melt growth (TSMG) method. In a conventional box furnace with uniform temperature distribution, it was very difficult to grow large single grain Y-123 superconductors due to the size limitation in growth. To overcome the size limitation, we applied a radial thermal gradient (lower temperature at sample center and higher temperature on the sample edge) to the TSMG process. In this case, large single grain Y-123 could be easily grown. This is attributed that the liquid of the sample edge was maintained at the high temperature compared to the growth front. Using this method, we successfully fabricated a large single grain Y-123 of 6.4 cm X6.4 cm

• Journal of Advanced Marine Engineering and Technology
• /
• v.12 no.3
• /
• pp.57-67
• /
• 1988

Although handicapped by the inability to bridge the size gap between small laboratory sample and large engineering component, the V charpy test sample method does possess certain advantages, such as each of preparation, simplicity of test method, speed, low cost in test machinery, and low cost per test. On the other hand, the COD test method does posses advantages, which reduce the size gap between the laboratory sample and actual engineering component. Consequently, the correlation between V charpy absorbed energy and the critical COD value is required for estimating critical COD value from the simple V charpy test results. In this paper, the high tensile strength steel AH36 plate specimens having a single edge cracked notch were investigated to find out the correlation between V charpy absorbed energy and critical COD value in the welded parts under such various welding methods as shielded metal arc welding, the submerged arc welding and the electro gas welding by means of V charpy impact test and static 3-point bending test. Main results obtained are as follow ; 1. The relationships between V charpy absorbed energy Wc' and critical COD value ($\delta_c$)show; $\delta_c$=0.0065 Wc'+0.1906. 2. Ductile- brittle transition behaviours can be estimated by means of fracture appearance and general yielding behaviours. 3. The V charpy absorbed energy of SMAW is higher than that of SAW, EGW and similar relationships are obtained in the COD tests.

• The Journal of Korean Medicine
• /
• v.25 no.1
• /
• pp.117-128
• /
• 2004

Objectives : This research was performed to investigate effect of Samul-tang-gamibang against focal cerebral ischemic damage after middle cerebral artery occlusion(MCAO). Methods : This research was used rats which were against focal cerebral ischemic damage by MCAO. It was used Zea Longa's theory and Belayev's methods to give rise to focal cerebral ischemic damage by MCAO. After 7days later, we drew out the brain and then had frozen and dyeing it and we had taken a picture to measure of the damaged area in each brain section. We determined the Neurological Index and tested the Foot-fault test and Roatated test to appraise the fall of motion ability result from cerebral ischemic damage. Results : The results of the experiment are as follows. 1. Samul-tang-gamibang reduced infarct size of sample group compared to control group at 7 day after MCAO. 2. Samul-tang-gamibang reduced infarct volume of sample group compared to control group at 7 day after MCAO. 3. Samul-tang-gamibang reduced foot-fault index of sample group compared to control group at 5,7 day after MCAO. Conclusions : Samul-tang-gamibang has protective effects against ischemic brain damage and had significant reduced infarct size and infarct volume of Rt-MCAO.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.27 no.9
• /
• pp.1335-1341
• /
• 2003

This paper describes the process of nanoparticle synthesis by laser ablation of microparticles and consolidated sample. We have generated nanoparticles by high-power pulsed laser ablation of AI, Cu and Ag microparticles using a Q-switched Nd:YAG laser (wavelength 355nm, FWHM 6ns, fluence $0.8{\sim}2.0J/cm^2$). Microparticles of mean diameter $18{\sim}80{\mu}m$ are ablated in the ambient air. The generated nanoparticles are collected on a glass substrate and the size distribution and morphology are examined using a scanning electron microscope and a transmission electron microscope. The effect of laser fluence, collector position and compacting pressure on the distribution of particle size is investigated. To better understand the process of laser ablation of microparticle(LAM), we investigated the Nd: YAG laser-induced breakdown of Cu microparticle using time-resolved optical shadow images. Nanosecond time-resolved images of the ablation process are also obtained by laser flash shadowgraphy. Based on the experimental results, discussions are made on the dynamics of ablation plume.

• Journal of the Korean Society of Industry Convergence
• /
• v.2 no.2
• /
• pp.61-68
• /
• 1999

The variety of crystalline structure and mechanical properties of PP filament treated with dry heat treatment at different draw ratio has been studied. Crystalline structure and mechanical properties of annealed PP filament at different draw ratio has been examined by XRD, UTM, and density method. Heat treatment has been carried out $100^{\circ}C$, $120^{\circ}C$ $140^{\circ}C$ for 30min. in dry oven. From the results of this study, it found the following facts. It was found that the crystallinity and crystallite size of (110) plane of sample were increased with increasing of annealed temperature and draw ratio. The crystalline form of annealed sample which was undrawn showed ${\alpha}$, ${\beta}$ mixing form below $120^{\circ}C$ and showed ${\alpha}$ form at $140^{\circ}C$. But the crystalline form of annealed sample which was drawn showed ${\alpha}$ form at $120^{\circ}C$. Initial modulus and tensile strength were increased with increasing of annealing temperature, and the degree of orientation was decreased with decreasing of annealing temperature.

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2005.06a
• /
• pp.151-157
• /
• 2005

For the treatment of regulatory clearance of the soils, a procedure for the radionuclides and radioactivity concentration analysis is under development. A strategy for soil sampling including random sampling after homogenization and standardization was set up. Statistical representativeness is considered for not only sampling strategy but also sample size. In this study, designed sample size was designed with confidence interval and error bound of soil using the pilot samples which were taken following the sampling strategy.

• Food Science of Animal Resources
• /
• v.34 no.6
• /
• pp.852-857
• /
• 2014

This study was carried out to develop a simple, convenient, and reproducible testing device to determine wettability and dispersibility of dairy powders. The testing device consists of a sieve ($150{\mu}m$) attached to a sample chamber, sensors mounted on a supporting body and a main control unit containing a display panel. The sensors detect the difference in electrical resistance between air and water. A timer is automatically triggered by the sensor when the bottom of sample-loaded chamber contacts water in the petri dish. Wettability and dispersibility of commercial skim milk powders (SMPs) produced at different heating strengths (low-, medium-, and high-heat SMP) are compared using the new testing device. Wettability of the SMPs were correlated with particle size and are found to increase in the order of medium-, low-, and high-heat SMP regardless of the amount of sample tested. Dispersibility of SMPs showed the same trend and high heat-SMP which has the smallest particle size resulted in the lowest dispersibility. Unlike existing methods, the new testing device can determine both wettability and dispersibility of powders and successfully detected differences among the samples.

• Korean Journal of Remote Sensing
• /
• v.18 no.3
• /
• pp.155-162
• /
• 2002

Neural networks have been focused on as a robust classifier for the remotely sensed imagery due to its statistical independency and teaming ability. Also the artificial neural networks have been reported to be more tolerant to noise and missing data. However, unlike the conventional statistical classifiers which use the statistical parameters for the classification, a neural network classifier uses individual training sample in teaming stage. The training performance of a neural network is know to be very sensitive to the discrepancy of the number of the training samples of each class. In this paper, the effect of the population discrepancy of training samples of each class was analyzed with three layered feed forward network. And a method for reducing the effect was proposed and experimented with Landsat TM image. The results showed that the effect of the training sample size discrepancy should be carefully considered for faster and more accurate training of the network. Also, it was found that the proposed method which makes teaming rate as a function of the number of training samples in each class resulted in faster and more accurate training of the network.