• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.747-758
• /
• 2013

The covariance matrix is important in multivariate statistical analysis and a sample covariance matrix is used as an estimator of the covariance matrix. High dimensional data has a larger dimension than the sample size; therefore, the sample covariance matrix may not be suitable since it is known to perform poorly and event not invertible. A number of covariance matrix estimators have been recently proposed with three different approaches of shrinkage, thresholding, and modified Cholesky decomposition. We compare the performance of these newly proposed estimators in various situations.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.30 no.8
• /
• pp.78-86
• /
• 2002

The GPS carrier phase measurements include integer ambiguities and the decorrelation process on the variance-covariance matrix is necessary to resolve these ambiguities efficiently. In this paper, we introduce a new method for the ambiguity de-correlation. This method divides the variance-covariance matrix into 4 smaller blocks and decorrelates them separately. The decorrelation of each block is processed recursively so that the result of the previous step is not affected by the next step. A couple of numerical examples chosen in random show that this method is better than or comparable to other decorrelation methods, however, the speed of this is relatively faster because the computations are performed on small blocks of the variance-covariance matrix.

• The Korean Journal of Applied Statistics
• /
• v.35 no.4
• /
• pp.569-577
• /
• 2022

Simulation studies are often conducted when it is difficult to compare the performance of nonparametric estimators theoretically. Kim and Kim (2021) showed that more systematic and accurate comparisons can be made if you analyze the simulation results using a regression model,. This study is a complementary study on Kim and Kim (2021). In the variance-covariance matrix for the error term of the regression model, only heteroscedasticity was considered and covariance was ignored in the previous study. When covariance is considered together with the heteroscedasticity, the variance-covariance matrix becomes a block diagonal matrix. In this study, a method of estimating and using the block diagonal variance-covariance matrix for the analysis was presented. This allows you to find more pairs of estimators with significant performance differences while ensuring the nominal confidence level.

• Communications for Statistical Applications and Methods
• /
• v.3 no.1
• /
• pp.131-143
• /
• 1996

다변량 층화임의추출에서 한 변수의 Neyman 최적배분은 다른 변수에 대한 층화분산을 최소화시키지 못하는 결과를 초래할 수도 있다. 따라서 다변량 자료의 경우 '최적'배분 대신에 '절충'배분이 도입되어 왔다. 이 연구에서는 각 변수별 Neyman 최적배분에 근거해서 얻은 층화표본평균벡터의 공분산 행렬에 가장 잘 적합되는 층별로 동일한 크기의 절충배분을 찾고자 한다. 이에 적절한 기준 다섯가지를 제시하고 예를 통해 비교, 분석하였다.

• The Korean Journal of Financial Management
• /
• v.19 no.2
• /
• pp.27-48
• /
• 2002

본 논문은 이자율의 기간 구조가 차익 거래의 기회가 없도록 움직일 때 새로운 평균만기 측 정치인 AR 평균만기(arbitrage-free duration)을 도출하고 선물가격과 선도가격과의 관계를 분석한다. 지금까지 평균만기에 관한 많은 연구들은 수익률 곡선이 특정한 형태로 이동한다는 가정 하에서 평균만기를 유도하고 이에 근거하여 채권가격의 변동치를 측정하고 있다. 본 논문에서는 기존의 평균만기의 가정을 완화한 AR 평균만기를 도출하였다. 여기서 제시하는 AR 평균만기는 기존의 Macaulay 평균만기를 포함하는 일반화한 측정치라고 할 수 있다. 아울러 본 논문에서는 선물가격과 선도가격사이에 존재하는 이론적 관계를 규명하고자 하였다. 선물가격은 선도가격에 비해 할인된 가격이라는 것을 보이고 이자율 변동위험이 선물가격의 할인정도에 미치는 영향을 모형화 하였다. 최근 들어 선물을 이용한 채권 면역화에 대한 실증연구에 관심이 지속적으로 증가하고 있다. 전통적 실증연구 방법론에서는 먼저, 선물가격과 기초채권 가격사이에 존재하는 분산-공분산 행렬을 추정한다. 그런 후 추정된 분산-공분산 행렬을 바탕으로 이자율 위험 헤징 전략을 수립한 후 이 전략에 대한 실증 분석을 수행하였다. 그러나, 전통적 접근법의 가장 큰 문제는 비안정적(non-stationary)인 분산-공분산 행렬을 적절히 고려할 수 없었다는 점이다. 따라서, 본 연구의 결과를 기반으로 하면 최적의 헷징 전략을 수립하기 위한 이론적 기틀을 수립할 수 있을 것이다.

• The Korean Journal of Applied Statistics
• /
• v.33 no.3
• /
• pp.281-296
• /
• 2020

Repeated outcomes from the same subjects are referred to as longitudinal data. Analysis of the data requires different methods unlike cross-sectional data analysis. It is important to model the covariance matrix because the correlation between the repeated outcomes must be considered when estimating the effects of covariates on the mean response. However, the modeling of the covariance matrix is tricky because there are many parameters to be estimated, and the estimated covariance matrix should be positive definite. In this paper, we consider analysis of multivariate longitudinal data via two modeling methodologies for the covariance matrix for multivariate longitudinal data. Both methods describe serial correlations of multivariate longitudinal outcomes using a modified Cholesky decomposition. However, the two methods consider different decompositions to explain the correlation between simultaneous responses. The first method uses enhanced linear covariance models so that the covariance matrix satisfies a positive definiteness condition; in addition, and principal component analysis and maximization-minimization algorithm (MM algorithm) were used to estimate model parameters. The second method considers variance-correlation decomposition and hypersphere decomposition to model covariance matrix. Simulations are used to compare the performance of the two methodologies.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.7
• /
• pp.94-100
• /
• 2001

When using a sample covariance matrix data in paucity of snapshots, adaptive matched field processing will have problem in inverting covariance matrix due to the rank deficiency. The general solutions are diagonal loading and eigenanalysis methods, but there is a significant bias in the power output. This paper presents a quantitative study of bias of power output and the performance of source localization through the simulation and the measured data analysis in fixed source case using the diagonal loading method for the minimum variance processor. Results show that the bias in power output is reduced and the performance of source localization is improved when the number of snapshots is greater than the number of array sensors.

• The Journal of the Acoustical Society of Korea
• /
• v.35 no.5
• /
• pp.395-402
• /
• 2016

In this paper, a wideband adaptive beamforming approach for an acoustic vector sensor linear array is presented. It is a very important issue to estimate the stable covariance matrix for adaptive beamforming. In the conventional wideband adaptive beamforming based on coherent signal-subspace (CSS) processing, the error of bearing estimates is resulted from the focusing matrix estimation and the large number of data snapshot is necessary. To alleviate the estimation error and snapshot deficiency in estimating covariance matrix, the steered covariance matrix method in the pressure sensor is extended to the vector sensor array, and the subarray technique is incorporated. By this technique, more accurate azimuth estimates and a stable covariance matrix can be obtained with a small number of data snapshot. Through simulation, the azimuth estimation performance of the proposed beamforming method and a wideband adaptive beamforming based on CSS processing are assessed.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.11a
• /
• pp.147-152
• /
• 2005

본 논문에서는 k개의 포아송 확률변수가 서로 종속 되어 있는 다변량 포아송 분포를 따를 때, 주어진 분산-공분산 행렬 구조를 유지하는 다변량 포아송 확률난수 생성방법에 대해 다루었다. 특히, 확률난수를 생성하기 위해 선형방정식을 푸는 두 가지 수치해석 알고리즘을 제안하였으며, Park 등 (1996)의 다변량 베르누이 확률난수 생성에 활용된 알고리즘과의 연관성을 다루었다.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.2
• /
• pp.68-72
• /
• 2000

Matched field processing technique is performed by considering complex underwater environments. Specially, the performance of minimum variance processor is greatly degraded by eigenvalue problem. In this paper, we propose the minimum variance matched field processor using shaping matrix. This shaping matrix makes that the input covariance matrix is invertible and enhances the desired acoustic source component. It was proved effectively range/depth localization of the proposed method with simulated data and vertical array data collected by NATO SACLANT Center north of the island of Elba off the Italian west coast.