• Communications for Statistical Applications and Methods
• /
• 제20권5호
• /
• pp.347-356
• /
• 2013

We propose a sequential method to construct approximate confidence limits for the ratio of two independent sequences of binomial variates with unequal sample sizes. Due to the nonexistence of an unbiased estimator for the ratio, we develop the procedure based on a modified maximum likelihood estimator (MLE). We generalize the results of Cho and Govindarajulu (2008) by defining the sample-ratio when sample sizes are not equal. In addition, we investigate the large-sample properties of the proposed estimator and its finite sample behavior through numerical studies, and we make comparisons from the sample information view points.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2006년도 춘계학술대회
• /
• pp.523-532
• /
• 2006

• 응용통계연구
• /
• 제19권3호
• /
• pp.535-544
• /
• 2006

분산 성분 모형 하에서 분산 성분들의 함수에 대한 통계적인 추론, 특히 소표본 하에서의 신뢰구간에 대한 방법들은 오랜 기간에 걸쳐서 여러 가지 방법들이 개발되어져 왔다. 그 대표적인 방법이 Graybill and Wang(1980)에 의해 제안된 수정 대표본 방법에 의거한 신뢰구간 추정법이며 현재까지 다양한 실험계획 방법 하에서 분산 성분들의 여러 가지 형태의 함수들에 대하여 확장과 개량이 이루어져 왔다. 본 연구에서는 분산 성분 모형의 균형 실험 가정 하에서 분산 성분들의 선형 결합이 관심있는 모수일 때 분산 분석에 의해 얻어진 수정 대표본 신뢰구간의 실제 포함확률을 툴스트랩 보정을 이용하여 개선하는 방법에 대하여 논의한다. 붓스트랩 보정을 이용함으로서 신뢰구간의 포함 확률의 정도는 점근적 이차 차수까지 개선되며 특히 선형 결합의 계수들이 모두 양수이고 결합의 수가 증가할 경우 수정 대표본 신뢰구간의 포함확률이 주어진 신뢰계수보다 항상 커지게 되는 단점을 개선할 수 있음을 보인다. 제안된 붓스트랩 보정 신뢰구간의 효율을 소표본의 경우에 모의실험을 통하여 평가한다.

• 응용통계연구
• /
• 제17권1호
• /
• pp.105-117
• /
• 2004

본 논문에서는 선형추세를 갖는 모집단의 평균을 추정하기 위한 새로운 방법을 제시하였다. 이 방법은 변형계통추출에 의하여 표본을 뽑은 뒤 표본의 단순평균이 아니라 조정된 추정량을 사용하여 모평균을 추정하는 방법이다. 조정된 추정량을 정하는 데에 최소제곱법을 사용하였다. 제시된 방법은 선형 추세가 강할수록 효율적이라는 것이 밝혀졌으며, 무한초모집단 모형의 랜덤오차항의 분산인 $\sigma$$^2$이 매우 크지만 않다면 전통적인 방법들에 비해 상대적으로 효율적인 것으로 나타났다.

• Communications for Statistical Applications and Methods
• /
• 제30권1호
• /
• pp.65-73
• /
• 2023

Contemporary biomedical data often involve an ill-posed problem owing to small sample size and large number of multi-collinear variables. Partial least squares (PLS) method could be a plausible alternative to an ill-conditioned ordinary least squares. However, in the case of a PLS model that includes a random-effect, how to deal with a random-effect or mixed effects remains a widely open question worth further investigation. In the present study, we propose a modified multivariate PLS method implementing mixed-effect model (PLSM). The advantage of PLSM is its versatility in handling serial longitudinal data or its ability for taking a randomeffect into account. We conduct simulations to investigate statistical properties of PLSM, and showcase its real clinical application to predict treatment outcome of esthetic surgical procedures of human faces. The proposed PLSM seemed to be particularly beneficial 1) when random-effect is conspicuous; 2) the number of predictors is relatively large compared to the sample size; 3) the multicollinearity is weak or moderate; and/or 4) the random error is considerable.

• 전기의세계
• /
• 제30권6호
• /
• pp.375-385
• /
• 1981

New algorithms are derived for nonlinear programming problems which are characterized by their large variables and equality and inequality constraints. The algorithms are based upon the introduction of the Dependent-Variable-Elimination method, Independent-Variable-Reduction method, Optimally-Ordered-Triangular-Factorization method, Equality-Inequality-Sequential-Satisfaction method, etc. For a case study problem relating to the optimal determination of load flow in a 10-bus, 13-line sample power system, several approaches are undertaken, such as SUMT, Lagrange's Multiplier method, sequential applications of linear and quadratic programming method. For applying the linear programming method, the conventional simplex algorithm is modified to the large-system-oriented one by the introduction of the Two-Phase method and Variable-Upper-Bounding method, thus resulting in remarkable savings in memory requirements and computing time. The case study shows the validity and effectivity of the algorithms presented herein.

• Applied Microscopy
• /
• 제47권2호
• /
• pp.77-83
• /
• 2017

Drastic development of ubiquitous devices requires more advanced batteries with high specific capacitance and high rate capability. Large-area microstructure characterization across the stacks of cathode, electrolyte and anode might reveal the origin of the instability or degradation of batteries upon cycling charge. In this study, sample preparation methods to observe the cross-section view of the electrodes for battery in SEM and several imaging tips are reviewed. For an accurate evaluation of the microstructure, ion milling which flats the surface uniformly is recommended. Pros and cons of cross-section polishing (CP) with Ar ion and focused ion beam (FIB) with Ga ion were compared. Additionally, a modified but new cross-section milling technique utilizing precision ion polishing system (PIPS) which can be an alternative method of CP is developed. This simple approach will make the researchers have more chances to prepare decent large-area cross-section electrode for batteries.

• 한국재료학회지
• /
• 제23권10호
• /
• pp.543-549
• /
• 2013

The purpose of this paper was to investigate the effect of a high-energy milling (HEM) process on the particle morphology and the correlation between a thermal treatment and tetragonal/monoclinic nanostructured zirconia powders obtained by a precipitation process. To eliminate chloride residue ions from hydrous zirconia, a modified washing method was used. It was found that the used washing method was effective in removing the chloride from the precipitated gel. In order to investigate the effect of a pre-milling process on the particle morphology of the precipitate, dried $Zr(OH)_4$ was milled using a HEM machine with distilled water. The particle size of the $Zr(OH)_4$ powder exposed to HEM reduced to 100~150 nm, whereas that of fresh $Zr(OH)_4$ powder without a pre-milling process had a large and irregular size of 100 nm~1.5 ${\mu}m$. Additionally, modified heat treatment process was proposed to achieve nano-sized zirconia having a pure monoclinic phase. It was evident that two-step calcining process was effective in perfectly eliminating the tetragonal phase, having a small average particle of ~100 nm with good uniformity compared to the sample calcined by a single-step process, showing a large average particle size of ~300 nm with an irregular particle shape and a broad particle size distribution. The modified method is considered to be a promising process for nano-sized zirconia having a fully monoclinic phase.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1989년도 춘계학술대회
• /
• pp.35-37
• /
• 1989

A new MR angiography technique using a composite sequence for the suppression of static sample signals is proposed and verified with experiments. When the composite [$90^{\circ}-{\tau}-180^{\circ}-2{\tau}-180^{\circ}-{\tau}$] sequence is applied, the large signal from the static sample is sufficiently suppressed but the signal from fresh inflow sample of which amplitude. is observed without suppression. These properties are appropriate for angiographic applications. In this paper, a modified line scan method (Block line scan angiography) incorporated with the composite [$90^{\circ}-{\tau}-180^{\circ}-2{\tau}-180^{\circ}-{\tau}$] sequence is used to obtain flow-only images, i.e., angiograms. The block line scan method improves the resolution in the flow-direction at the expense of imaging time. With the composite sequence, there is no need for subtraction procedure as in the most conventional angiographic methods. Experimental results for a phantom and a normal volunteer with KAIS 2.0 Tesla MRI system are shown.

• Nuclear Engineering and Technology
• /
• 제35권6호
• /
• pp.581-595
• /
• 2003

Transport lattice codes require the resonance integral tables for the resonant nuclides where the resonance integral is a function of the background cross section and can be prepared through a special program solving the slowing down equation. In case the cross section libraries do not include the resonance integral table for the resonant nuclides, the computational prediction produces a large error. We devised a new method using a Monte Carlo calculation for the effective resonance cross sections to solve this problem provisionally. We extended this method to obtain the resonance integral table for general purpose. The MCNP code is used for the effective resonance integrals and the LIBERTE code for the effective background cross sections. We modified the HELIOS library with the effective cross sections and the resonance integral tables obtained by the newly developed Monte Carlo method, and performed sample calculations using HELIOS and LIBERTE. The results showed that this method is very effective for the resonance treatment.