• 대한수학회보
• /
• 제55권4호
• /
• 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.

• Communications for Statistical Applications and Methods
• /
• 제6권2호
• /
• pp.487-500
• /
• 1999

We propose a class of hierarchical Bayes estimators of the error variance under the relative squared error loss in balanced fixed-effects two-way analysis of variance models. Also we provide analytic expressions for the risk improvement of the hierarchical Bayes estimators over multiples of the error sum of squares. Using these expressions we identify a subclass of the hierarchical Bayes estimators each member of which dominates the best multiple of the error sum of squares which is known to be minimax. Numerical values of the percentage risk improvement are given in some special cases.

• Journal of the Korean Data and Information Science Society
• /
• 제17권2호
• /
• pp.559-568
• /
• 2006

In this paper, we develop the noninformative priors for the linear mixed models when the parameter of interest is the ratio of variance components. We developed the first and second order matching priors. We reveal that the one-at-a-time reference prior satisfies the second order matching criterion. It turns out that the two group reference prior satisfies a first order matching criterion, but Jeffreys' prior is not first order matching prior. Some simulation study is performed.

• East Asian mathematical journal
• /
• 제34권3호
• /
• pp.239-248
• /
• 2018

In this paper, we derive a closed-form formula of a second-order approximation for a European corrected option price under stochastic elasticity of variance model mentioned in Kim et al. (2014) [1] [J.-H. Kim, J Lee, S.-P. Zhu, S.-H. Yu, A multiscale correction to the Black-Scholes formula, Appl. Stoch. Model. Bus. 30 (2014)]. To find the explicit-form correction to the option price, we use Mellin transform approaches.

• Communications for Statistical Applications and Methods
• /
• 제12권1호
• /
• pp.47-59
• /
• 2005

Expected mean square(EMS) is an important part of conducting the analysis of variance in the experimental design problem, especially in mixed or random models. We present a set of EMS rules for balanced factorial designs under no restriction on interaction. Also we point out how to use the variance component of SPSS or SAS procedure to obtain EMS.

• Journal of the Korean Statistical Society
• /
• 제9권1호
• /
• pp.97-108
• /
• 1980

Variance components model appears often in designing experiments including time series data analysis. This paper is investigating the properties of the various procedures in estimating variance components for the two-way random model without interaction under normality. In this age of computer-oriented computations, MINQUE is found to be quite practicla because of the robustness with respect to the design configurations and parameters. Also adjusted AOV type estimation procedure is found to yield superior results over the unadjusted one.

• 한국컴퓨터산업학회논문지
• /
• 제9권5호
• /
• pp.207-216
• /
• 2008

초장력 스프레드시트 기능의 엑셀 프로그램에서 자료를 통계적으로 분석하는 데이터분석 메뉴는 엑셀 2000 이후 수정 보완 되고 있지 않으며 그 활용도도 매우 저조하다. 본 연구에서는 엑셀 통계분석 메뉴 활용도 향상을 위하여 사용빈도가 높은 분산분석의 엑셀 메뉴 실행 결과와 계산식에 의한 이론 결과를 비교하고 고차원 분석 매크로를 개발하였다. 실자료를 엑셀 라이터분석 메뉴를 적용하여 얻은 결과와 계산식에 의한 이론 결과는 요인이 한개인 일원배치법이나 두개인 이원배치 법에서 모두 정확히 일치하였다. 즉 엑셀 데이터분석 메뉴의 신뢰성이 검증되었다. 고차원적인 분산분석법인 블록화된 분산분석 결과를 제공하는 매크로 및 일원분산분석법에서 평균 차이 있는 그룹들을 찾아내는 다중비교 분석방법 매크로를 엑셀 함수를 이용하여 개발하였다.

• Journal of Information Processing Systems
• /
• 제16권4호
• /
• pp.832-844
• /
• 2020

The degree of dispersion of a random variable can be described by the variance, which reflects the distance of the random variable from its mean. However, the time complexity of the traditional variance calculation algorithm is O(n), which results from full calculation of all samples. When the number of samples increases or on the occasion of high speed signal processing, algorithms with O(n) time complexity will cost huge amount of time and that may results in performance degradation of the whole system. A novel multi-step recursive algorithm for variance calculation of the time-varying data series with O(1) time complexity (constant time) is proposed in this paper. Numerical simulation and experiments of the algorithm is presented and the results demonstrate that the proposed multi-step recursive algorithm can effectively decrease computing time and hence significantly improve the variance calculation efficiency for time-varying data, which demonstrates the potential value for time-consumption data analysis or high speed signal processing.

• 응용통계연구
• /
• 제25권1호
• /
• pp.55-66
• /
• 2012

블랙-숄즈 모형이 실제 기초자산의 움직임을 반영하지 못한다는 사실이 실증연구에 의하여 밝혀진 이후 기초자산의 움직임을 레비확률과정을 이용하여 모형화한 옵션가격결정 모형들이 그 대안 중 하나로 연구되어 왔다. 본 논문에서는 블랙-숄즈 모형의 대안으로 제시된 레비모형 중 Variance Gamma 모형이 국내 주식시장에서의 기초자산의 움직임을 블랙-숄즈 모형보다 충실히 재현해내는지 알아보고자 한다. 이를 위하여 Madan 등 (1998)의 연구에서와 같이 로그수익률의 확률밀도함수와 옵션 가격 결정식을 바탕으로 KOSPI 200자료를 이용하여 모수를 추정하고 우도비 검정을 실시하였다. 또한, 옵션 가격을 추정한 후 모형 간의 비교를 위하여 다양한 통계량을 계산하고, 회귀분석을 통하여 변동성 스마일 현상이 교정되는지를 살펴보았다. 연구결과로부터 Variance Gamma 모형 하에서 추정된 옵션 가격이 블랙-숄즈 모형 하에서 추정된 그것보다 더 시장가격과 가까우나, 이 모형도 변동성 스마일 현상을 해결해주지는 못함을 확인할 수 있었다.

• Asian-Australasian Journal of Animal Sciences
• /
• 제23권3호
• /
• pp.302-307
• /
• 2010

The present study aimed to investigate the effects of maternal factors on body weight at hatching (day-old) and at six weeks of age in a commercial broiler line. A total of 6,765 records on body weight at day-old (BWTDO) and 115,421 records on body weight at six weeks of age (BWT6W), originated from a commercial broiler line during 14 generations, were used to estimate genetic parameters related to the effects of maternal traits on body weight of chicks immediately after hatch or six weeks thereafter. The data were analyzed using restricted maximum likelihood procedure (REML) and an animal model with DFREML software. Direct heritability ($h^{2}{_a}$), maternal heritability ($h^{2}{_m}$), and maternal environmental variance as the proportions of phenotypic variance ($c^{2}$) for body weight at day-old were estimated to be 0.050, 0.351, and 0.173, respectively. The respective estimated values for body weight at six weeks of age were 0.340, 0.022, and 0.030. The correlation coefficient between direct and maternal genetic effects for six-week-old body weight was found to be -0.335. Covariance components and genetic correlations were estimated using a bivariate analysis based on the best model determined by a univariate analysis. Between weights at hatching and at six week-old, the values of -0.07, 0.53 and 0.47 were found for the direct additive genetic variance, maternal additive genetic variance and permanent maternal environmental variance, respectively. The estimated correlation between direct additive genetic effect influencing weight at hatch and direct additive maternal effect affecting weight at six weeks of age was -0.21, whereas the correlation value of 0.15 was estimated between direct additive maternal effect influencing weight at hatch and direct additive genetic effect affecting weight at six-week-old. From the present findings, it can be concluded that the maternal additive genetic effect observed for weight at six weeks of age might be a factor transferred from genes influencing weight at hatch to weight at six-week-old.