• The Korean Journal of Applied Statistics
• /
• v.7 no.2
• /
• pp.213-224
• /
• 1994

A diagnostic method useful for detecting outliers in testing the equality of two covariance metrics is developed using the influence curve approach. This method is easily generalized to more than two covariance matrices. A sample version for the influence measure of detecting outliers is considered based on the empirical distribution functions. The sample version includes as its component terms the well-known test statistic for detecting one outlier at a time introduced by Wilks and its generalization to the two-group case.

• Korean Journal of Materials Research
• /
• v.13 no.9
• /
• pp.598-605
• /
• 2003

The optimized conditions for the cross-sectional TEM sample preparation using tripod polisher and ion-beam miller was confirmed by AFM and TEM. For the TEM observation of interfaces including InGaN layers like InGaN/GaN MQW structures, the sample preparation by the only tripod polishing was useful due to the reduction of artifacts. On the other hand, in case of the thick nitride films like ELO, PE, and superlattice, both tripod polishing and controlled ion-beam milling were required to improve the reproducibility. As a result, the ion-beam milling with the $60^{\circ}$modulation showed the minimum height difference between film and sapphire interface and the ion-beam milling of the $80^{\circ}$modulation showed the broad observable width.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.29 no.1
• /
• pp.34-40
• /
• 2006

Many producers put sampling inspection policy into the way of their convenience. Examples of the convenience are irregular lot size and too small sample size. Because they don't use a standard sampling inspection policy, they can not guarantee the quality level of their products. In this study, we developed a user-centered design program which can calculate the AOQL of their products to their buyers in the case of irregular lot size and too small sample size. Also this program propose a linear inspection cost by Hald's model.

• Journal of the Korean Graphic Arts Communication Society
• /
• v.19 no.2
• /
• pp.58-67
• /
• 2001

Gamut mapping is a technique that acts on cross-media color reproduction to transform a color between devices for the purpose of enhancing the appearance or preserving the appearance of an image. Gamut mapping essentially produces color conversion error which depends the gamut mapping method, source and destination devices, and sample points for gamut modeling. For color space conversion between monitor colors and printer colors, empirical representation using sample measurements is currently widely utilized. Color samples are uniformly selected in the device space such as CMY or RGB, represented as color patches, and then measured. However, in the case of printer, these color samples are not evenly distributed inside the printer gamut and the color conversion error is increased. Accordingly, this paper introduces a equally distributed color sampling method in CIELAB space, a device- independent color space, to reduce color conversion error, and the performance is analyzed via color space conversion experiments using tetrahedral interpolation.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.3C no.6
• /
• pp.246-251
• /
• 2003

We report the theory of thin-sample Z -scan for materials, viz. diffusion-dominated photorefractives, having a nonlinearly induced phase that may be proportional to the spatial derivative of the intensity profile. The on-axis far-field intensity is approximately an even function of the scan distance on different positive and negative values for phase shift $\Delta$$\Phi$$_{o}$. In case of positive phase shift, the Z -scan graph shows a minimum and two maxima, while for the negative value, only one minimum is observed. The fact is that far-field beam profiles display beam distortion and shift of the peak as compared with Kerr-type or photovoltaic nonlinearities.s.

• Journal of the Korean Statistical Society
• /
• v.33 no.1
• /
• pp.1-24
• /
• 2004

This paper is concerned with statistical methods for multivariate data when the number p of variables is large compared to the sample size n. Such data appear typically in analysis of DNA microarrays, curve data, financial data, etc. However, there is little statistical theory for high dimensional data. On the other hand, there are some asymptotic results under the assumption that both and p tend to $\infty$, in some ratio p/n ${\rightarrow}$c. The results suggest that the new asymptotic results are more useful and insightful than the classical large sample asymptotics. The main purpose of this paper is to review some asymptotic results for high dimensional statistics as well as classical statistics under a high dimensional asymptotic framework.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.40 no.1
• /
• pp.95-104
• /
• 2017

This paper deals with solution methods for discrete and multi-valued optimization problems. The objective function of the problem incorporates noise effects generated in case that fitness evaluation is accomplished by computer based experiments such as Monte Carlo simulation or discrete event simulation. Meta heuristics including Genetic Algorithm (GA) and Discrete Particle Swarm Optimization (DPSO) can be used to solve these simulation based multi-valued optimization problems. In applying these population based meta heuristics to simulation based optimization problem, samples size to estimate the expected fitness value of a solution and population (particle) size in a generation (step) should be carefully determined to obtain reliable solutions. Under realistic environment with restriction on available computation time, there exists trade-off between these values. In this paper, the effects of sample and population sizes are analyzed under well-known multi-modal and multi-dimensional test functions with randomly generated noise effects. From the experimental results, it is shown that the performance of DPSO is superior to that of GA. While appropriate determination of population sizes is more important than sample size in GA, appropriate determination of sample size is more important than particle size in DPSO. Especially in DPSO, the solution quality under increasing sample sizes with steps is inferior to constant or decreasing sample sizes with steps. Furthermore, the performance of DPSO is improved when OCBA (Optimal Computing Budget Allocation) is incorporated in selecting the best particle in each step. In applying OCBA in DPSO, smaller value of incremental sample size is preferred to obtain better solutions.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1349-1357
• /
• 2013

In clinical research, sample size determination is one of the most important things. There are parametric method using t-test and non-parametric method suggested by Kim and Kim (2007) based on Wilcoxon's rank sum test for determining sample size in non-inferiority trials. In this paper, we propose sample size calculation method based on placements method suggested by Orban and Wolfe (1982) and using the power calculated by Kim (1994) in non-inferiority trials. We also compare proposed sample size with that using Kim and Kim (2007)'s formula and that of t-test for parametric methods. As the result, sample size calculated by proposed method based on placements is the smallest. Therefore, proposed method based on placements is better than parametric methods in case that it's hard to assume specific distribution function for population and also more efficient in terms of time and cost than method based on Wilcoxon's rank sum test.

• Management & Information Systems Review
• /
• v.28 no.3
• /
• pp.69-98
• /
• 2009

This study investigates in-sample and out-of-sample predictive abilities of accruals and accruals components with respect to future cash flows using models developed by Barth et al.(2001). In tests, data collected fromda62 Korean KOSPI and KOSDAQ listed firms for ccr4-2007 are used. Results of in-sample prediction tests are similar with those of Barth et al.(2001). Their accrual components model is better than other three models(NI only model, CF only model and NI-total accruals model) in future cash flows predictive ability. That is, in the case of in-sample prediction, accrual components excluding amortization have additional information contents for future cash flows. But in out-of-sample tests, the results are different. The model including operational cash flows(CF only model) shows best out-of-sample predictive ability with respect to future cash flows among above four prediction models. The accrual components model of Barth et al.(2001) has worst out-of-sample predictive ability. The results are robust to sensitivity analyses. In conclusion, we can't find the evidence that accruals and accrual components have predictive ability with respect to future cash flows in out-of-sample prediction tests. This results are consistent with results of Lev et al.(2005), and inconsistent with the belief of accounting standards formulating organizations such as FASB and KASB.

• Proceedings of the KIEE Conference
• /
• 1999.07d
• /
• pp.1849-1851
• /
• 1999

The PDP(Plasma Display Panel) barrier rib was fabricated by focused $Ar^+$ laser ($\lambda$=514nm) and Nd:YAG($\lambda$=532, 266 nm) laser irradiation. The depth of the etched groove increases with increasing a laser fluence. and decreasing a scan speed. Using the second harmonic of the Nd:YAG laser, the threshold laser fluence was $6.5mJ/cm^2$ for the sample of PDP barrier rib dried at $120^{\circ}C$. The thickness of $150{\mu}m$ of the sample on the glass was etched without any damage on the glass substrate by fluence of $19.5J/cm^2$. The barrier rib sample on hot plate was etched by Nd:YAG laser(532 nm) as increasing a temperature of the sample. In this case, the etch rate was $95{\mu}m/s$, $190{\mu}m/s$ at room temperature, $175^{\circ}C$ respectively.