Earticle

본 논문은 금, 은, 백금, 팔라듐의 일별 가격 자료에 5가지 확산모형을 적용하여 최적 모형을 분석했다. Aït-Sahalia(2008)의 방법을 이용한 최우추정법(MLE)으로 추정한 결과, 금, 은, 팔라듐은 GD-GV 모형이, 백금은 CKLS 모형이 가장 적합했다. 공통적으로 추세보다 변동성 함수의 설명력이 컸으며, 가격 수준에 비례하여 변동성이 커지는 현상과 낮은 가격대에서의 약한 평균 회귀 경향이 확인되었다.

This paper investigates the dynamic behavior of gold, silver, platinum, and palladium prices using five diffusion models estimated via MLE with Aït-Sahalia’s (2008) approximation. The GD-GV model best explains gold, silver, and palladium, while the CKLS model fits platinum best. We find that the volatility function plays a more dominant role than the drift function for all metals. Additionally, results show that volatility increases with price levels, with weak evidence of mean-reversion in lower price ranges.

본 연구는 소프트웨어 NHPP 신뢰성 모형 (Goel--Okumo 모형, 지연된 S-형태 신뢰성모형 및 레일리분포 모형)의 예측능력을 분석하는 것을 목적으로 한다. 예측 능력분석은 두 가지 요인으로 분석이 될 것이다. 하나는 사용가능한 고장자료에 대한 적용성의 정도이고 다른 하나는 예측능력 정도이다. 각 모형의 모수 추정은 고장시간자료의 첫 번째 고장시점부터 80%가 되는 고장시간 자료를 사용하고 기법은 최우추정법을 이용 하였다. 모형의 예측 능력의 비교에 있어서는 가능한 고장 데이터의 마지막 20%가 되는 선택된 자료를 이용하였다. 이 연구를 통하여 소프트웨어 관리자들에게 소프트웨어 고장분석을 하는데 사전정보로 활용 할 수 있다.

This study aims to analyze the predict capability of some of the popular software NHPP reliability models(Goel-Okumo model, delayed S-shaped reliability model and Rayleigh distribution model). The predict capability analysis will be on two key factors, one pertaining to the degree of fitment on available failure data and the other for its prediction capability. Estimation of parameters for each model was used maximum likelihood estimation using first 80% of the failure data. Comparison of predict capability of models selected by validating against the last 20% of the available failure data. Through this study, findings can be used as priori information for the administrator to analyze the failure of software.

In this paper, we propose a new three-dimensional (3D) photon-counting integral imaging reconstruction method using a merging reconstruction process and maximum likelihood estimation (MLE). The conventional 3D photon-counting reconstruction method extracts photons from elemental images using a Poisson random process and estimates the scene using statistical methods such as MLE. However, it can reduce the photon levels because of an average overlapping calculation. Thus, it may not visualize 3D objects in severely low light environments. In addition, it may not generate high-quality reconstructed 3D images when the number of elemental images is insufficient. To solve these problems, we propose a new 3D photon-counting merging reconstruction method using MLE. It can visualize 3D objects without photon-level loss through a proposed overlapping calculation during the reconstruction process. We confirmed the image quality of our proposed method by performing optical experiments.

A sample with special missing pattern called a monotone sample or a monotone missing data pattern occurs in many applications. The statistical methods for analyzing a monotone sample have been developed by several analysts. The purpose of this paper is to introduce the maximum likelihood estimation of parameters when there is a multivariate normal sample with 2-step monotone pattern, and to present the maximum likelihood estimates of parameters in closed forms. These estimates can be obtained by maximizing the overall likelihood function which is expressed in terms of the marginal and conditional likelihood functions with respect to parameters. The maximum likelihood estimates presented are expected to he used to develop statistical methods for analyzing a multivariate normal sample with 2-step monotone pattern in applications.

Background/Objectives: This study was designed to compare the Varimax analysis of Principal Component Analysis(PCA) with the Exploratory Factor Analysis(EFA) method using Maximum Likelihood Estimation(MLE) and oblique rotation(Direct Oblimin) for the multicultural experience of university students. multicultural experience variables of college students were analyzed as two factors through Maximum Likelihood Estimation(MLE). Methods/Statistical analysis Q1, Q2, Q3 are multicultural direct experiences, and Q4, Q5, Q6, Q7 are multicultural indirect experiences. Findings: As a result of this study, it is suggested to use Maximum Likelihood Estimation(MLE) and oblique rotation(Direct Oblimin). As a prerequisite for applying the Maximum Likelihood Estimation(MLE), it is thought that Improvements/Applications it is necessary to increase the accuracy of the response rate by using the face-toface interview method when conducting a survey.

Time synchronization is critical for most distributed systems, especially for low-duty-cycle Wireless Sensor Networks(WSNs). Low-duty-cycle WSNs make use of time synchronization in many contexts(scheduling and sleeping, TDMA, Event Identification, data fusion, etc). A novel adaptive source time synchronization algorithm designed for low-duty-cycle WSNs, namely ASTS, is presented in the paper. The algorithm can be used for a small Low-Duty-Cycle WSN to be synchronized to a common clock, or used for a giant Low-Duty-Cycle WSN to be synchronized distributed. To improve the synchronization accuracy, all nodes estimate their time drifts relative to their neighbors using Maximum Likelihood Estimation, and get be synchronized to a common clock or their heads based on a vector of time drifts carried by the reference packet sent by the reference node. Simulation shows that the algorithm drastically improves the synchronization accuracy and scalability, and is much more applicable for low-duty-cycle WSNs than other synchronization algorithms.

Due to the wide application of range-based location algorithm for received signal strength, and according to the requirements of high accuracy and low power cost in the location algorithm for WSNs, in this paper, a Bayesian optimization RSSI and an indoor location algorithm for ILS were introduced by setting RRS ranging as location framework. Firstly, through analyzing the RSSI-based ranging model, an indoor location model was introduced. Secondly, in view of the influence on RSSI value caused by the indoor environment,the Bayesian probabilistic model was adopted to process the RSSI measured value and to screen out the "big probability" of RSSI value. Thirdly, Obtaining accurate measured data by estimating distance using method of minimum mean square error. Finally, Estimating the node location using least square method, and according to the TelosB node of Telos Series produced by company Crossbow, the ranging experiment can be designed and thus groups of experimental data were obtained and analyzed..The experimental results showed that the proposed location project greatly increased the location accuracy and decreased the computation complexity, and has obviously more advantage of running time over other location projects.

In this paper, an interaural time difference (ITD) estimation method is proposed for binaural speech separation in reverberant environments. First, the auditory signals are represented in the time-frequency (T-F) domain, and the ITD for each T-F bin is then estimated using generalized cross-correlation (GCC) with a maximum likelihood (ML) weighting function. In particular, the ML weighting function is designed to reduce the reverberation effect. Then, a mask is estimated by comparing the estimated ITD with the ITD corresponding to the location of the pre-defined target speech source. Finally, the target speech is separated by applying the mask to the auditory signals. It is shown that the proposed ITD estimation method outperforms a conventional cross-correlation-based ITD estimation method under reverberant conditions in terms of the signal-to-noise ratio (SNR) and signal-to-distortion ratio (SDR) of the separated speech signals.

공간상에서 원하는 목표물의 도래 방향 추정은 수신 안테나에 입사하는 신호의 입사 방향을 찾는 것이다. 본 논문에서는 최대 우도 추정 방법을 이용하여 원하는 목표물의 도래 방향을 추정하였다. 도래 방향 추정방법은 최대 우도 방법에서 수신 신호 한계점 이상의 신호에 특이 값 분해를 적용하여 최대 우도 추정의 첨예도를 계산하여 원하는 목표물을 추정하였다. 모의실험을 통하여 본 연구에서 제안된 방법의 성능을 기존 방법과 비교분석하였다. 목표물 도래방향 추정에서 본 연구에서 제안한 방법이 고유치 전개를 하지 않기 때문에 처리시간 단축에서 효과적이고 원하는 목표물의 방향을 정확히 추정하였다. 본 연구에서 제안한 방법이 목표물 추정에서 기존 방법보다 우수함을 나타내었다.

In spatial, desired target direction of arrival estimation is to find a incidental signal direction on receive antennas. In this paper, we were an estimation a desired target direction of arrival using maximum likelihood method. Direction of arrival estimation method estimated a desired target calculating the maximum likelihood sensitivity using singular value decomposition above threshold signals among receive signals in maximum likelihood method. Through simulation, we were analysis a performance to compare existing method and proposal method. In direction of arrival estimation, proposed method is effectivity to decrease processing time because it is not doing an eigen decomposition in direction of arrival estimation, and desired target correctly estimated. We showed that proposal method improve more target estimation than general method.

Poisson generalized linear mixed models(GLMMs) have been widely used for the analysis of clustered or correlated count data. For the inference marginal likelihood, which is obtained by integrating out random effects is often used. It gives maximum likelihood(ML) estimator, but the integration is usually intractable. In this paper, we propose how to obtain the ML estimator via Laplace approximation based on hierarchical-likelihood (h-likelihood) approach under the Poisson GLMMs. In particular, the h-likelihood avoids the integration itself and gives a statistically efficient procedure for various random-effect models including GLMMs. The proposed method is illustrated using two practical examples and simulation studies.

We define a crossing point $x_0$ such that f(x)$\geq$g(x) for x$\leq$$x_0$ and f(x)$\leq$g(x) for x>$x_0$ where f and g are probability density functions. We may encounter suchy situation when we compare two histograms from two independent observations. For example two contingency tables where initially admitted students and actually enrolled students are classified according to their high school ranking may show such situation, In this paper we consider maximum likelihood estimation of cell probabilities when a crossing point exists, We first assume a known crossing point and find an estimator. The estimation procedure for the case of unknown crossing point is just a straightforward extension. A real data is analyzed for an illustrative purpose.

The maximum likelihood estimation is discussed for the NLAR model with Laplacian marginals. Since the explicit form of the estimates cannot be obtained due to the complicated nature of the likelihood function we utilize the automatic computer optimization subroutine using a direct search complex algorithm. The conditional least square estimates are used as initial estimates in maximum likelihood procedures. The results of a simulation study for the maximum likelihood estimates of the NLAR(1) and the NLAR(2) models are presented.

Five diffusion models are estimated using three different foreign exchange rates to find an appropriate model for each. Daily spot exchange rates expressed as the prices of 1 euro, 1 British pound and 100 Japanese yen in US dollars, respectively denoted by USD/EUR, USD/GBP, and USD/100JPY, are used. The maximum likelihood estimation method is implemented after deriving an approximate log-transition density function (log-TDF) of the diffusion processes because the true log-TDF is unknown. Of the five models, the most general model is the best fit for the USD/GBP, and USD/100JPY exchange rates, but it is not the case for the case of USD/EUR. Although we could not find any evidence of the mean-reverting property for the USD/EUR exchange rate, the USD/GBP, and USD/ 100JPY exchange rates show the mean-reversion behavior. Interestingly, the volatility function of the USD/EUR exchange rate is increasing in the exchange rate while the volatility functions of the USD/GBP and USD/100Yen exchange rates have a U-shape. Our results reveal that more care has to be taken when determining a diffusion model for the exchange rate. The results also imply that we may have to use a more general diffusion model than those proposed in the literature when developing economic theories for the behavior of the exchange rate and pricing foreign currency options or derivatives.

The purpose of this paper is to estimate a general continuous-time diffusion model for short term interest rates using Korean data. The model is general enough to encompass almost all of the diffusion models suggested in the literature to explain the dynamics of short term interest rates. We approximate the true but unknown conditional transition probability density function of the diffusion process using Ait-Sahalia’s (2008) irreducible method to conduct maximum likelihood estimation. The overnight call rate and the 91 day CD rate have been adopted as a proxy for the short term interest rate. Overall, estimation results are quite similar for both interest rates. We could not find any significant evidence of nonlinearity in the drift in either data series. However, for both interest rates, a linear drift term is statistically different from zero at high interest rates. We could obtain very significant estimates for the parameters in the volatility function for all models and all data sets. The volatility term is an increasing function of the interest rates. We also found some evidence that the underlying data generating process might change over time.

Penalized least squares methods are important tools to simultaneously select variables and estimate parameters in linear regression. The penalized maximum likelihood can also be used for the same purpose assuming that the error distribution falls in a certain parametric family of distributions. However, the use of a certain parametric family can suffer a misspecification problem which undermines the estimation accuracy. To give sufficient flexibility to the error distribution, we propose to use the symmetric log-concave error distribution with LASSO penalty. A feasible algorithm to estimate both nonparametric and parametric components in the proposed model is provided. Some numerical studies are also presented showing that the proposed method produces more efficient estimators than some existing methods with similar variable selection performance.

Panel data sets have been developed in various areas, and many recent studies have analyzed panel, or longitudinal data sets. Maximum likelihood (ML) may be the most common statistical method for analyzing panel data models; however, the inference based on the ML estimate will have an inflated Type I error because the ML method tends to give a downwardly biased estimate of variance components when the sample size is small. The under estimation could be severe when data is incomplete. This paper proposes the restricted maximum likelihood (REML) method for a random effects panel data model with a censored dependent variable. Note that the likelihood function of the model is complex in that it includes a multidimensional integral. Many authors proposed to use integral approximation methods for the computation of likelihood function; however, it is well known that integral approximation methods are inadequate for high dimensional integrals in practice. This paper introduces to use the moments of truncated multivariate normal random vector for the calculation of multidimensional integral. In addition, a proper asymptotic standard error of REML estimate is given.

Many studies have estimated a mixture of binomial distributions. This paper considers an extension, a mixture of shifted binomial distributions, and the estimation of the distribution. The range of each component binomial distribution is rst evaluated and then for each possible value of shifted parameters, the EM algorithm is employed to estimate those parameters. From a set of possible value of shifted parameters and corresponding estimated parameters of the distribution, the likelihood of given data is determined. The simulation results verify the performance of the proposed method.

A receiver operating characteristic (ROC) curve plots the true positive rate of a classier against its false positive rate, both of which are accuracy measures of the classier. The ROC curve has several interesting geometrical properties, including concavity which is a necessary condition for a classier to be optimal. In this paper, we study the nonparametric maximum likelihood estimator (NPMLE) of a concave ROC curve and its modification to reduce bias. We characterize the NPMLE as a solution to a geometric programming, a special type of a mathematical optimization problem. We find that the NPMLE is close to the convex hull of the empirical ROC curve and, thus, has smaller variance but positive bias at a given false positive rate. To reduce the bias, we propose a modification of the NPMLE which minimizes the $L_1$ distance from the empirical ROC curve. We numerically compare the finite sample performance of three estimators, the empirical ROC curve, the NMPLE, and the modified NPMLE. Finally, we apply the estimators to estimating the optimal ROC curve of the variance-threshold classier to segment a low depth of field image and to finding a diagnostic tool with multiple tests for detection of hemophilia A carrier.

We obtain the approximate maximum likelihood estimators (AMLEs) for the scale and location parameters $\theta$ and $\mu$ in the three-parameter Weibull distribution based on Type-II censored samples. We also compare the AMLEs with the modified maximum likelihood estimators (MMLEs) in the sense of the mean squared error (MSE) based on complete sample.